[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-K-Dense-AI-qiskit-zh-CN":3,"guides-for-K-Dense-AI-qiskit":3491,"similar-k171tct2jf3hry8hymbp41p1qd86m8mb-zh-CN":3492},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":259,"isFallback":242,"parentExtension":264,"providers":265,"relations":271,"repo":273,"tags":3488,"workflow":3489},1778691799740.491,"k171tct2jf3hry8hymbp41p1qd86m8mb",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools. Best for IBM hardware execution, quantum error mitigation, and enterprise quantum computing. For Google hardware use cirq; for gradient-based quantum ML use pennylane; for open quantum system simulations use qutip.",{"claudeCode":12},"K-Dense-AI/claude-scientific-skills","Qiskit","https://github.com/K-Dense-AI/claude-scientific-skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":240,"workflow":257},1778694003140.6387,"kn785adtw00xqxxx2frkm7438d86m6m1","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"practices":204,"prerequisites":209,"promptVersionExtension":214,"promptVersionScoring":215,"purpose":216,"rationale":217,"score":218,"summary":219,"tags":220,"targetMarket":227,"tier":228,"useCases":229,"workflow":234},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,90,94,98,102,106,109,112,115,119,122,125,128,131,134,137,141,145,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly names the problem space of IBM quantum computing, including specific use cases like Qiskit Runtime and IBM optimization tools, and explicitly mentions targeting IBM Quantum hardware.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers significant value over a generic LLM by providing curated access to the Qiskit framework, its optimization tools, and integration with specific IBM Quantum hardware and services, steering behavior beyond default capabilities.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill bundle appears complete for its stated purpose, offering installation, circuit building, execution primitives, transpilation, and visualization, covering the full lifecycle for using the Qiskit framework.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses on the IBM quantum computing framework (Qiskit), including its core capabilities and execution on IBM hardware, without bundling unrelated tools or domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's scope, clearly outlining its purpose, target audience, and comparing it to alternative frameworks like Cirq, PennyLane, and Qutip.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This skill does not expose explicit tools; its functionality is accessed via Qiskit Python libraries through LLM code generation based on the SKILL.md.",{"category":45,"check":46,"severity":24,"summary":47},"Documentation","Configuration & parameter reference","The referenced setup.md and other reference files provide detailed installation, authentication, and IBM Quantum account setup instructions, covering necessary configurations.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","As this is a skill-based extension that generates code rather than exposing specific tools, tool naming conventions do not apply.",{"category":33,"check":52,"severity":42,"summary":53},"Minimal I/O surface","This skill generates code that interacts with the Qiskit library, rather than exposing specific tools with defined input/output schemas.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The SKILL.md specifies an 'Apache-2.0 license', which is a permissive open-source license, indicating usability for various projects.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The repository shows recent commits within the last 3 months, indicating active maintenance.",{"category":59,"check":63,"severity":24,"summary":64},"Dependency Management","The SKILL.md includes installation instructions using `uv pip`, and the README mentions dependencies are handled by individual skills, suggesting a managed approach to third-party dependencies.",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","The skill documentation (references/setup.md) mentions saving API tokens but does not echo resolved secret values into output or debug logs, and advises setting tokens as environment variables.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill focuses on providing documentation and examples for Qiskit usage; it does not appear to load or execute untrusted third-party data as instructions.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill relies on the Qiskit library, which is installed via `uv pip`, and does not involve runtime downloads of code or instructions from remote URLs that are not part of the committed bundle.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill's purpose is to guide Qiskit usage through code generation; it does not involve file system operations outside of the standard Python package installation process.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","The skill's content consists of documentation and code examples for Qiskit, with no evidence of detached-process spawns or deny-retry loops.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill does not contain instructions to read or submit confidential data; outbound calls would be part of the Qiskit library's functionality, which is not directly controlled by the skill's instructions.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled content (SKILL.md, README.md, references) appears free of hidden-steering tricks; all descriptions are clean printable ASCII.",{"category":66,"check":88,"severity":24,"summary":89},"Opaque code execution","The skill's content is primarily documentation and readable Python code examples, with no evidence of obfuscation, base64 payloads, or runtime script fetching.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The skill's instructions focus on Qiskit library usage and do not make structural assumptions about the user's project organization beyond standard Python environment setup.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","The repository has a closure rate of ~87% (33 closed / 38 total issues in last 90 days) with a low number of open issues (5), indicating active engagement from maintainers.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The SKILL.md frontmatter specifies 'Apache-2.0 license' and the README indicates a MIT license, suggesting a versioning strategy. The trust signals show a pushedAt date, and the README mentions regular updates.",{"category":103,"check":104,"severity":42,"summary":105},"Code Execution","Validation","This skill generates code that uses Qiskit; validation and sanitization of inputs would be handled by the Qiskit library itself or the agent's execution environment, not by the skill's direct code.",{"category":66,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","The skill itself does not perform destructive operations; it guides the user in writing Qiskit code, where destructive operations would be at the discretion of the user and Qiskit library's functions.",{"category":103,"check":110,"severity":24,"summary":111},"Error Handling","The skill's documentation points to Qiskit's robust error handling capabilities and best practices for quantum workflows, implying that errors generated by Qiskit code will be handled appropriately.",{"category":103,"check":113,"severity":42,"summary":114},"Logging","The skill itself does not perform actions requiring logging; logging would be handled by the Qiskit library or the agent's execution environment.",{"category":116,"check":117,"severity":42,"summary":118},"Compliance","GDPR","The skill focuses on quantum computing and does not operate on personal data. Any data handled by Qiskit code would be specific to quantum computations.",{"category":116,"check":120,"severity":24,"summary":121},"Target market","The skill targets general quantum computing use and does not exhibit regional or jurisdictional logic, thus its target market is global.",{"category":91,"check":123,"severity":24,"summary":124},"Runtime stability","The skill relies on standard Python and the Qiskit library, which are cross-platform. Installation instructions via `uv pip` support various OS environments.",{"category":45,"check":126,"severity":24,"summary":127},"README","The README file is extensive, clearly states the repository's purpose (scientific skills), lists included skills, and provides getting started instructions.",{"category":33,"check":129,"severity":42,"summary":130},"Tool surface size","This is a skill-based extension that generates code, rather than exposing specific tools or commands with a defined surface size.",{"category":40,"check":132,"severity":42,"summary":133},"Overlapping near-synonym tools","This extension does not expose explicit tools, so the concept of overlapping near-synonym tools is not applicable.",{"category":45,"check":135,"severity":24,"summary":136},"Phantom features","All features advertised in the README and SKILL.md, such as Qiskit installation, circuit building, execution, and visualization, have corresponding documentation and examples within the provided references.",{"category":138,"check":139,"severity":24,"summary":140},"Install","Installation instruction","The README provides clear installation instructions using `npx` and `gh skill`, and the SKILL.md details Python package installation with `uv pip`, including setup for IBM Quantum accounts.",{"category":142,"check":143,"severity":24,"summary":144},"Errors","Actionable error messages","The skill's documentation and references (e.g., troubleshooting sections) provide guidance on potential issues like missing dependencies, API limits, and authentication errors, offering remediation steps or links to further documentation.",{"category":146,"check":147,"severity":148,"summary":149},"Execution","Pinned dependencies","info","The skill instructs users to install Qiskit via `uv pip`, which handles dependency management. While explicit pinning isn't shown in the SKILL.md, `uv` typically manages dependencies effectively. The use of `uv pip install qiskit` implies latest version installation, not pinned.",{"category":33,"check":151,"severity":42,"summary":152},"Dry-run preview","As this skill generates Qiskit code rather than executing direct commands, a dry-run preview is not applicable in the traditional sense. The generated code can be reviewed before execution.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The skill guides users on using Qiskit's primitives, which are designed with error handling and state management in mind. Specific Qiskit jobs may have timeouts, and the use of sessions/batch mode can help manage retries.",{"category":116,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The skill itself does not emit telemetry. Any telemetry would be a function of the Qiskit library or the agent's underlying system, which are assumed to follow standard telemetry practices.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The skill's purpose is precisely defined as the IBM quantum computing framework (Qiskit), with clear instructions on when to use it (targeting IBM Quantum hardware, Qiskit Runtime) and when not to (mentioning alternatives like Cirq, PennyLane).",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The SKILL.md frontmatter is concise and self-contained, summarizing the core capability and providing trigger phrases, well within the character limit.",{"category":45,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md body is well-structured and uses separate reference files for detailed procedures, keeping the main file concise and adhering to progressive disclosure.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md effectively uses relative paths to link to detailed `references/*.md` files for each sub-task, demonstrating excellent progressive disclosure.",{"category":170,"check":174,"severity":42,"summary":175},"Forked exploration","This skill is documentation-focused and does not involve deep exploration or code review that would require a forked context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The SKILL.md and its references provide numerous end-to-end, ready-to-use Python code examples for various Qiskit functionalities, demonstrating inputs, invocations, and expected outcomes.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The documentation, particularly in sections like 'Troubleshooting' and 'Best Practices,' addresses potential issues like installation errors, backend availability, and circuit depth, along with recovery steps.",{"category":103,"check":183,"severity":42,"summary":184},"Tool Fallback","This skill does not rely on external MCP servers or custom tools; it guides the usage of the Qiskit Python library, which is self-contained after installation.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The skill's documentation implicitly guides users to set up environments and use simulators first, suggesting a workflow that halts if prerequisites are not met, and Qiskit itself provides error handling.",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill is self-contained and focuses solely on Qiskit. It does not implicitly rely on or silently handle tasks from adjacent skills; cross-skill coordination is not applicable here.",1778694003022,"This skill provides comprehensive documentation and examples for using Qiskit, the IBM quantum computing framework. It covers installation, circuit building, execution on simulators and IBM Quantum hardware, optimization, visualization, and integration with various quantum algorithms.",[195,196,197,198,199],"Detailed Qiskit installation and setup guides","Comprehensive circuit building capabilities","Execution on simulators and IBM Quantum hardware","Circuit optimization and transpilation","Visualization of circuits, results, and states",[201,202,203],"Providing alternatives to IBM Quantum hardware","Covering quantum computing frameworks other than Qiskit","Deep dives into theoretical quantum physics beyond Qiskit applications",[205,206,207,208],"Quantum circuit design","Hardware-specific optimization","Hybrid quantum-classical algorithms","Best practices for execution and analysis",[210,211,212,213],"Python 3.8+ (or recommended version)","uv package manager","Qiskit and visualization dependencies","IBM Quantum account and API token (for hardware execution)","3.0.0","4.4.0","To enable users to effectively leverage the Qiskit quantum computing framework for building, optimizing, and executing quantum circuits, particularly when targeting IBM Quantum hardware.","Highest finding is 'info' on pinned dependencies, indicating generally high quality across all checks. The skill is well-documented, secure, and actively maintained.",99,"High-quality skill for using the Qiskit quantum computing framework effectively and safely.",[221,222,223,224,225,226],"quantum-computing","qiskit","ibm-quantum","python","circuit-design","simulation","global","verified",[230,231,232,233],"Targeting IBM Quantum hardware for quantum computations","Working with Qiskit Runtime for production workloads","Needing IBM optimization tools for quantum circuits","Learning and implementing quantum algorithms with Qiskit",[235,236,237,238,239],"Install Qiskit and set up IBM Quantum account (references/setup.md)","Build quantum circuits using gates and operations (references/circuits.md)","Optimize circuits for hardware via transpilation (references/transpilation.md)","Execute circuits using Sampler or Estimator primitives (references/primitives.md)","Analyze and visualize results (references/visualization.md)",{"codeQuality":241,"collectedAt":243,"documentation":244,"maintenance":247,"security":254,"testCoverage":256},{"hasLockfile":242},true,1778693980586,{"descriptionLength":245,"readmeSize":246},377,42038,{"closedIssues90d":248,"forks":249,"hasChangelog":250,"openIssues90d":251,"pushedAt":252,"stars":253},33,2317,false,5,1778498315000,20978,{"hasNpmPackage":250,"license":255,"smitheryVerified":250},"MIT",{"hasCi":242,"hasTests":242},{"updatedAt":258},1778694003140,{"basePath":260,"githubOwner":261,"githubRepo":262,"locale":18,"slug":222,"type":263},"scientific-skills/qiskit","K-Dense-AI","claude-scientific-skills","skill",null,{"evaluate":266,"extract":268},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":267,"targetMarket":227,"tier":228},[221,222,223,224,225,226],{"commitSha":269,"license":270},"HEAD","Apache-2.0",{"repoId":272},"kd79rphh5gexy91xmpxc05h5mh86mm9r",{"_creationTime":274,"_id":272,"identity":275,"providers":276,"workflow":3484},1778691790211.49,{"githubOwner":261,"githubRepo":262,"sourceUrl":14},{"classify":277,"discover":3461,"github":3464},{"commitSha":269,"extensions":278},[279,293,323,341,358,380,412,426,434,456,478,490,510,548,596,663,675,685,705,869,889,906,927,937,947,971,989,1118,1133,1149,1165,1189,1198,1218,1228,1246,1284,1303,1313,1332,1346,1356,1376,1393,1413,1423,1445,1473,1491,1515,1534,1553,1568,1597,1619,1699,1720,1741,1756,1780,1799,1813,1844,1854,1866,1882,1914,1955,1977,1998,2013,2045,2073,2081,2095,2115,2144,2157,2178,2190,2208,2227,2298,2314,2324,2343,2365,2378,2395,2415,2433,2457,2478,2504,2522,2538,2556,2583,2615,2634,2649,2668,2699,2712,2720,2734,2748,2758,2780,2796,2838,2865,2893,2902,2925,2945,2957,2980,2993,3008,3029,3049,3068,3086,3104,3112,3171,3190,3212,3227,3274,3283,3305,3322,3380,3390,3452],{"basePath":280,"description":281,"displayName":282,"installMethods":283,"rationale":284,"selectedPaths":285,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/adaptyv","How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`.","adaptyv",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/adaptyv/SKILL.md",[286,289],{"path":287,"priority":288},"SKILL.md","mandatory",{"path":290,"priority":291},"references/api-endpoints.md","medium","rule",{"basePath":294,"description":295,"displayName":296,"installMethods":297,"rationale":298,"selectedPaths":299,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/aeon","This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.","aeon",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/aeon/SKILL.md",[300,301,303,305,307,309,311,313,315,317,319,321],{"path":287,"priority":288},{"path":302,"priority":291},"references/anomaly_detection.md",{"path":304,"priority":291},"references/classification.md",{"path":306,"priority":291},"references/clustering.md",{"path":308,"priority":291},"references/datasets_benchmarking.md",{"path":310,"priority":291},"references/distances.md",{"path":312,"priority":291},"references/forecasting.md",{"path":314,"priority":291},"references/networks.md",{"path":316,"priority":291},"references/regression.md",{"path":318,"priority":291},"references/segmentation.md",{"path":320,"priority":291},"references/similarity_search.md",{"path":322,"priority":291},"references/transformations.md",{"basePath":324,"description":325,"displayName":326,"installMethods":327,"rationale":328,"selectedPaths":329,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/anndata","Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.","anndata",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/anndata/SKILL.md",[330,331,333,335,337,339],{"path":287,"priority":288},{"path":332,"priority":291},"references/best_practices.md",{"path":334,"priority":291},"references/concatenation.md",{"path":336,"priority":291},"references/data_structure.md",{"path":338,"priority":291},"references/io_operations.md",{"path":340,"priority":291},"references/manipulation.md",{"basePath":342,"description":343,"displayName":344,"installMethods":345,"rationale":346,"selectedPaths":347,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/arboreto","Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.","arboreto",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/arboreto/SKILL.md",[348,349,351,353,355],{"path":287,"priority":288},{"path":350,"priority":291},"references/algorithms.md",{"path":352,"priority":291},"references/basic_inference.md",{"path":354,"priority":291},"references/distributed_computing.md",{"path":356,"priority":357},"scripts/basic_grn_inference.py","low",{"basePath":359,"description":360,"displayName":361,"installMethods":362,"rationale":363,"selectedPaths":364,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/astropy","Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.","astropy",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/astropy/SKILL.md",[365,366,368,370,372,374,376,378],{"path":287,"priority":288},{"path":367,"priority":291},"references/coordinates.md",{"path":369,"priority":291},"references/cosmology.md",{"path":371,"priority":291},"references/fits.md",{"path":373,"priority":291},"references/tables.md",{"path":375,"priority":291},"references/time.md",{"path":377,"priority":291},"references/units.md",{"path":379,"priority":291},"references/wcs_and_other_modules.md",{"basePath":381,"description":382,"displayName":383,"installMethods":384,"rationale":385,"selectedPaths":386,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/autoskill","Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.","autoskill",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/autoskill/SKILL.md",[387,388,390,392,394,396,398,400,402,404,406,408,410],{"path":287,"priority":288},{"path":389,"priority":291},"references/https-proxy.md",{"path":391,"priority":291},"references/screenpipe-config.yaml",{"path":393,"priority":357},"scripts/autoskill.py",{"path":395,"priority":357},"scripts/backends.py",{"path":397,"priority":357},"scripts/cluster.py",{"path":399,"priority":357},"scripts/doctor.py",{"path":401,"priority":357},"scripts/fetch_window.py",{"path":403,"priority":357},"scripts/match_skills.py",{"path":405,"priority":357},"scripts/promote.py",{"path":407,"priority":357},"scripts/redact.py",{"path":409,"priority":357},"scripts/run.py",{"path":411,"priority":357},"scripts/synthesize.py",{"basePath":413,"description":414,"displayName":415,"installMethods":416,"rationale":417,"selectedPaths":418,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/benchling-integration","Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.","benchling-integration",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/benchling-integration/SKILL.md",[419,420,422,424],{"path":287,"priority":288},{"path":421,"priority":291},"references/api_endpoints.md",{"path":423,"priority":291},"references/authentication.md",{"path":425,"priority":291},"references/sdk_reference.md",{"basePath":427,"description":428,"displayName":429,"installMethods":430,"rationale":431,"selectedPaths":432,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/bgpt-paper-search","Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone.","bgpt-paper-search",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/bgpt-paper-search/SKILL.md",[433],{"path":287,"priority":288},{"basePath":435,"description":436,"displayName":437,"installMethods":438,"rationale":439,"selectedPaths":440,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/biopython","Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.","biopython",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/biopython/SKILL.md",[441,442,444,446,448,450,452,454],{"path":287,"priority":288},{"path":443,"priority":291},"references/advanced.md",{"path":445,"priority":291},"references/alignment.md",{"path":447,"priority":291},"references/blast.md",{"path":449,"priority":291},"references/databases.md",{"path":451,"priority":291},"references/phylogenetics.md",{"path":453,"priority":291},"references/sequence_io.md",{"path":455,"priority":291},"references/structure.md",{"basePath":457,"description":458,"displayName":459,"installMethods":460,"rationale":461,"selectedPaths":462,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/bioservices","Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use biopython.","bioservices",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/bioservices/SKILL.md",[463,464,466,468,470,472,474,476],{"path":287,"priority":288},{"path":465,"priority":291},"references/identifier_mapping.md",{"path":467,"priority":291},"references/services_reference.md",{"path":469,"priority":291},"references/workflow_patterns.md",{"path":471,"priority":357},"scripts/batch_id_converter.py",{"path":473,"priority":357},"scripts/compound_cross_reference.py",{"path":475,"priority":357},"scripts/pathway_analysis.py",{"path":477,"priority":357},"scripts/protein_analysis_workflow.py",{"basePath":479,"description":480,"displayName":481,"installMethods":482,"rationale":483,"selectedPaths":484,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/cellxgene-census","Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.","cellxgene-census",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/cellxgene-census/SKILL.md",[485,486,488],{"path":287,"priority":288},{"path":487,"priority":291},"references/census_schema.md",{"path":489,"priority":291},"references/common_patterns.md",{"basePath":491,"description":492,"displayName":493,"installMethods":494,"rationale":495,"selectedPaths":496,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/cirq","Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.","cirq",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/cirq/SKILL.md",[497,498,500,502,504,506,508],{"path":287,"priority":288},{"path":499,"priority":291},"references/building.md",{"path":501,"priority":291},"references/experiments.md",{"path":503,"priority":291},"references/hardware.md",{"path":505,"priority":291},"references/noise.md",{"path":507,"priority":291},"references/simulation.md",{"path":509,"priority":291},"references/transformation.md",{"basePath":511,"description":512,"displayName":513,"installMethods":514,"rationale":515,"selectedPaths":516,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/citation-management","Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.","citation-management",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/citation-management/SKILL.md",[517,518,520,522,524,526,528,530,532,534,536,538,540,542,544,546],{"path":287,"priority":288},{"path":519,"priority":357},"assets/bibtex_template.bib",{"path":521,"priority":357},"assets/citation_checklist.md",{"path":523,"priority":291},"references/bibtex_formatting.md",{"path":525,"priority":291},"references/citation_validation.md",{"path":527,"priority":291},"references/google_scholar_search.md",{"path":529,"priority":291},"references/metadata_extraction.md",{"path":531,"priority":291},"references/pubmed_search.md",{"path":533,"priority":357},"scripts/doi_to_bibtex.py",{"path":535,"priority":357},"scripts/extract_metadata.py",{"path":537,"priority":357},"scripts/format_bibtex.py",{"path":539,"priority":357},"scripts/generate_schematic.py",{"path":541,"priority":357},"scripts/generate_schematic_ai.py",{"path":543,"priority":357},"scripts/search_google_scholar.py",{"path":545,"priority":357},"scripts/search_pubmed.py",{"path":547,"priority":357},"scripts/validate_citations.py",{"basePath":549,"description":550,"displayName":551,"installMethods":552,"rationale":553,"selectedPaths":554,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/clinical-decision-support","Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.","clinical-decision-support",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/clinical-decision-support/SKILL.md",[555,556,558,560,562,564,566,568,570,572,574,576,578,580,582,584,586,588,590,591,592,594],{"path":287,"priority":288},{"path":557,"priority":357},"assets/biomarker_report_template.tex",{"path":559,"priority":357},"assets/clinical_pathway_template.tex",{"path":561,"priority":357},"assets/cohort_analysis_template.tex",{"path":563,"priority":357},"assets/color_schemes.tex",{"path":565,"priority":357},"assets/example_gbm_cohort.md",{"path":567,"priority":357},"assets/recommendation_strength_guide.md",{"path":569,"priority":357},"assets/treatment_recommendation_template.tex",{"path":571,"priority":291},"references/README.md",{"path":573,"priority":291},"references/biomarker_classification.md",{"path":575,"priority":291},"references/clinical_decision_algorithms.md",{"path":577,"priority":291},"references/evidence_synthesis.md",{"path":579,"priority":291},"references/outcome_analysis.md",{"path":581,"priority":291},"references/patient_cohort_analysis.md",{"path":583,"priority":291},"references/treatment_recommendations.md",{"path":585,"priority":357},"scripts/biomarker_classifier.py",{"path":587,"priority":357},"scripts/build_decision_tree.py",{"path":589,"priority":357},"scripts/create_cohort_tables.py",{"path":539,"priority":357},{"path":541,"priority":357},{"path":593,"priority":357},"scripts/generate_survival_analysis.py",{"path":595,"priority":357},"scripts/validate_cds_document.py",{"basePath":597,"description":598,"displayName":599,"installMethods":600,"rationale":601,"selectedPaths":602,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/clinical-reports","Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation tools.","clinical-reports",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/clinical-reports/SKILL.md",[603,604,606,608,610,612,614,616,618,620,622,624,626,628,629,631,633,635,637,639,641,643,645,647,649,651,653,655,656,657,659,661],{"path":287,"priority":288},{"path":605,"priority":357},"assets/case_report_template.md",{"path":607,"priority":357},"assets/clinical_trial_csr_template.md",{"path":609,"priority":357},"assets/clinical_trial_sae_template.md",{"path":611,"priority":357},"assets/consult_note_template.md",{"path":613,"priority":357},"assets/discharge_summary_template.md",{"path":615,"priority":357},"assets/hipaa_compliance_checklist.md",{"path":617,"priority":357},"assets/history_physical_template.md",{"path":619,"priority":357},"assets/lab_report_template.md",{"path":621,"priority":357},"assets/pathology_report_template.md",{"path":623,"priority":357},"assets/quality_checklist.md",{"path":625,"priority":357},"assets/radiology_report_template.md",{"path":627,"priority":357},"assets/soap_note_template.md",{"path":571,"priority":291},{"path":630,"priority":291},"references/case_report_guidelines.md",{"path":632,"priority":291},"references/clinical_trial_reporting.md",{"path":634,"priority":291},"references/data_presentation.md",{"path":636,"priority":291},"references/diagnostic_reports_standards.md",{"path":638,"priority":291},"references/medical_terminology.md",{"path":640,"priority":291},"references/patient_documentation.md",{"path":642,"priority":291},"references/peer_review_standards.md",{"path":644,"priority":291},"references/regulatory_compliance.md",{"path":646,"priority":357},"scripts/check_deidentification.py",{"path":648,"priority":357},"scripts/compliance_checker.py",{"path":650,"priority":357},"scripts/extract_clinical_data.py",{"path":652,"priority":357},"scripts/format_adverse_events.py",{"path":654,"priority":357},"scripts/generate_report_template.py",{"path":539,"priority":357},{"path":541,"priority":357},{"path":658,"priority":357},"scripts/terminology_validator.py",{"path":660,"priority":357},"scripts/validate_case_report.py",{"path":662,"priority":357},"scripts/validate_trial_report.py",{"basePath":664,"description":665,"displayName":666,"installMethods":667,"rationale":668,"selectedPaths":669,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/cobrapy","Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.","cobrapy",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/cobrapy/SKILL.md",[670,671,673],{"path":287,"priority":288},{"path":672,"priority":291},"references/api_quick_reference.md",{"path":674,"priority":291},"references/workflows.md",{"basePath":676,"description":677,"displayName":678,"installMethods":679,"rationale":680,"selectedPaths":681,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/consciousness-council","Run a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. Use this skill whenever the user wants diverse viewpoints, needs help making a tough decision, asks for a council/panel/board discussion, wants to explore a problem from multiple angles, requests devil's advocate analysis, or says things like \"what would different experts think about this\", \"help me think through this from all sides\", \"council mode\", \"mind council\", or \"deliberate on this\". Also trigger when the user faces a dilemma, trade-off, or complex choice with no obvious answer.","consciousness-council",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/consciousness-council/SKILL.md",[682,683],{"path":287,"priority":288},{"path":684,"priority":291},"references/advanced-configurations.md",{"basePath":686,"description":687,"displayName":688,"installMethods":689,"rationale":690,"selectedPaths":691,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/dask","Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.","dask",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/dask/SKILL.md",[692,693,695,697,699,701,703],{"path":287,"priority":288},{"path":694,"priority":291},"references/arrays.md",{"path":696,"priority":291},"references/bags.md",{"path":698,"priority":291},"references/best-practices.md",{"path":700,"priority":291},"references/dataframes.md",{"path":702,"priority":291},"references/futures.md",{"path":704,"priority":291},"references/schedulers.md",{"basePath":706,"description":707,"displayName":708,"installMethods":709,"rationale":710,"selectedPaths":711,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/database-lookup","Search 78 public scientific, biomedical, materials science, and economic databases via REST APIs. Covers physics/astronomy (NASA, NIST, SDSS, SIMBAD), earth/environment (USGS, NOAA, EPA), chemistry/drugs (PubChem, ChEMBL, DrugBank, FDA, KEGG, ZINC, BindingDB), materials (Materials Project, COD), biology/genomics (Reactome, UniProt, STRING, Ensembl, NCBI Gene, GEO, GTEx, PDB, AlphaFold, InterPro, BioGRID, Gene Ontology, dbSNP, gnomAD, ENCODE, Human Protein Atlas, Human Cell Atlas), disease/clinical (COSMIC, Open Targets, ClinicalTrials.gov, OMIM, ClinVar, GDC/TCGA, cBioPortal, DisGeNET, GWAS Catalog), regulatory (FDA, USPTO, SEC EDGAR), economics/finance (FRED, World Bank, US Treasury), demographics (US Census, Eurostat, WHO). Use when looking up compounds, genes, proteins, pathways, variants, clinical trials, patents, economic indicators, or any public database API query.","database-lookup",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/database-lookup/SKILL.md",[712,713,715,717,719,721,723,725,727,729,731,733,735,737,739,741,743,745,747,749,751,753,755,757,759,761,763,765,767,769,771,773,775,777,779,781,783,785,787,789,791,793,795,797,799,801,803,805,807,809,811,813,815,817,819,821,823,825,827,829,831,833,835,837,839,841,843,845,847,849,851,853,855,857,859,861,863,865,867],{"path":287,"priority":288},{"path":714,"priority":291},"references/addgene.md",{"path":716,"priority":291},"references/alphafold.md",{"path":718,"priority":291},"references/alphavantage.md",{"path":720,"priority":291},"references/bea.md",{"path":722,"priority":291},"references/bindingdb.md",{"path":724,"priority":291},"references/biogrid.md",{"path":726,"priority":291},"references/bls.md",{"path":728,"priority":291},"references/brenda.md",{"path":730,"priority":291},"references/cbioportal.md",{"path":732,"priority":291},"references/census.md",{"path":734,"priority":291},"references/chebi.md",{"path":736,"priority":291},"references/chembl.md",{"path":738,"priority":291},"references/clinicaltrials.md",{"path":740,"priority":291},"references/clinpgx.md",{"path":742,"priority":291},"references/clinvar.md",{"path":744,"priority":291},"references/cod.md",{"path":746,"priority":291},"references/cosmic.md",{"path":748,"priority":291},"references/dailymed.md",{"path":750,"priority":291},"references/datacommons.md",{"path":752,"priority":291},"references/dbsnp.md",{"path":754,"priority":291},"references/disgenet.md",{"path":756,"priority":291},"references/drugbank.md",{"path":758,"priority":291},"references/ecb.md",{"path":760,"priority":291},"references/emdb.md",{"path":762,"priority":291},"references/ena.md",{"path":764,"priority":291},"references/encode.md",{"path":766,"priority":291},"references/ensembl.md",{"path":768,"priority":291},"references/epa.md",{"path":770,"priority":291},"references/eurostat.md",{"path":772,"priority":291},"references/fda.md",{"path":774,"priority":291},"references/federal-reserve.md",{"path":776,"priority":291},"references/fred.md",{"path":778,"priority":291},"references/gene-ontology.md",{"path":780,"priority":291},"references/geo.md",{"path":782,"priority":291},"references/gnomad.md",{"path":784,"priority":291},"references/gtex.md",{"path":786,"priority":291},"references/gwas-catalog.md",{"path":788,"priority":291},"references/hca.md",{"path":790,"priority":291},"references/hpo.md",{"path":792,"priority":291},"references/human-protein-atlas.md",{"path":794,"priority":291},"references/interpro.md",{"path":796,"priority":291},"references/jaspar.md",{"path":798,"priority":291},"references/kegg.md",{"path":800,"priority":291},"references/lincs-l1000.md",{"path":802,"priority":291},"references/materials-project.md",{"path":804,"priority":291},"references/metabolomics-workbench.md",{"path":806,"priority":291},"references/monarch.md",{"path":808,"priority":291},"references/mousemine.md",{"path":810,"priority":291},"references/nasa-exoplanet-archive.md",{"path":812,"priority":291},"references/nasa.md",{"path":814,"priority":291},"references/ncbi-gene.md",{"path":816,"priority":291},"references/ncbi-protein.md",{"path":818,"priority":291},"references/ncbi-taxonomy.md",{"path":820,"priority":291},"references/nist.md",{"path":822,"priority":291},"references/noaa.md",{"path":824,"priority":291},"references/omim.md",{"path":826,"priority":291},"references/opentargets.md",{"path":828,"priority":291},"references/openweathermap.md",{"path":830,"priority":291},"references/pdb.md",{"path":832,"priority":291},"references/pride.md",{"path":834,"priority":291},"references/pubchem.md",{"path":836,"priority":291},"references/quickgo.md",{"path":838,"priority":291},"references/reactome.md",{"path":840,"priority":291},"references/rummageo.md",{"path":842,"priority":291},"references/sdss.md",{"path":844,"priority":291},"references/sec-edgar.md",{"path":846,"priority":291},"references/simbad.md",{"path":848,"priority":291},"references/sra.md",{"path":850,"priority":291},"references/string.md",{"path":852,"priority":291},"references/tcga-gdc.md",{"path":854,"priority":291},"references/treasury.md",{"path":856,"priority":291},"references/ucsc-genome.md",{"path":858,"priority":291},"references/uniprot.md",{"path":860,"priority":291},"references/usgs.md",{"path":862,"priority":291},"references/uspto.md",{"path":864,"priority":291},"references/who.md",{"path":866,"priority":291},"references/worldbank.md",{"path":868,"priority":291},"references/zinc.md",{"basePath":870,"description":871,"displayName":872,"installMethods":873,"rationale":874,"selectedPaths":875,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/datamol","Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.","datamol",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/datamol/SKILL.md",[876,877,879,881,883,885,887],{"path":287,"priority":288},{"path":878,"priority":291},"references/conformers_module.md",{"path":880,"priority":291},"references/core_api.md",{"path":882,"priority":291},"references/descriptors_viz.md",{"path":884,"priority":291},"references/fragments_scaffolds.md",{"path":886,"priority":291},"references/io_module.md",{"path":888,"priority":291},"references/reactions_data.md",{"basePath":890,"description":891,"displayName":892,"installMethods":893,"rationale":894,"selectedPaths":895,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/deepchem","Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.","deepchem",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/deepchem/SKILL.md",[896,897,899,900,902,904],{"path":287,"priority":288},{"path":898,"priority":291},"references/api_reference.md",{"path":674,"priority":291},{"path":901,"priority":357},"scripts/graph_neural_network.py",{"path":903,"priority":357},"scripts/predict_solubility.py",{"path":905,"priority":357},"scripts/transfer_learning.py",{"basePath":907,"description":908,"displayName":909,"installMethods":910,"rationale":911,"selectedPaths":912,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/deeptools","NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.","deeptools",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/deeptools/SKILL.md",[913,914,916,918,920,922,923,925],{"path":287,"priority":288},{"path":915,"priority":357},"assets/quick_reference.md",{"path":917,"priority":291},"references/effective_genome_sizes.md",{"path":919,"priority":291},"references/normalization_methods.md",{"path":921,"priority":291},"references/tools_reference.md",{"path":674,"priority":291},{"path":924,"priority":357},"scripts/validate_files.py",{"path":926,"priority":357},"scripts/workflow_generator.py",{"basePath":928,"description":929,"displayName":930,"installMethods":931,"rationale":932,"selectedPaths":933,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/depmap","Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use for identifying cancer-specific vulnerabilities, synthetic lethal interactions, and validating oncology drug targets.","depmap",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/depmap/SKILL.md",[934,935],{"path":287,"priority":288},{"path":936,"priority":291},"references/dependency_analysis.md",{"basePath":938,"description":939,"displayName":940,"installMethods":941,"rationale":942,"selectedPaths":943,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/dhdna-profiler","Extract cognitive patterns and thinking fingerprints from any text. Use this skill when the user wants to analyze how someone thinks, understand cognitive style, profile writing or speech patterns, compare thinking styles between people, asks \"what's my thinking style\", \"analyze how this person reasons\", \"cognitive profile\", \"thinking pattern\", \"DHDNA\", \"digital DNA\", or wants to understand the mind behind any text. Also trigger when the user provides text and wants deeper insight into the author's reasoning patterns, decision-making style, or cognitive signature.","dhdna-profiler",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/dhdna-profiler/SKILL.md",[944,945],{"path":287,"priority":288},{"path":946,"priority":291},"references/advanced-profiling.md",{"basePath":948,"description":949,"displayName":950,"installMethods":951,"rationale":952,"selectedPaths":953,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/diffdock","Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.","diffdock",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/diffdock/SKILL.md",[954,955,957,959,961,963,965,967,969],{"path":287,"priority":288},{"path":956,"priority":357},"assets/batch_template.csv",{"path":958,"priority":357},"assets/custom_inference_config.yaml",{"path":960,"priority":291},"references/confidence_and_limitations.md",{"path":962,"priority":291},"references/parameters_reference.md",{"path":964,"priority":291},"references/workflows_examples.md",{"path":966,"priority":357},"scripts/analyze_results.py",{"path":968,"priority":357},"scripts/prepare_batch_csv.py",{"path":970,"priority":357},"scripts/setup_check.py",{"basePath":972,"description":973,"displayName":974,"installMethods":975,"rationale":976,"selectedPaths":977,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/dnanexus-integration","DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution.","dnanexus-integration",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/dnanexus-integration/SKILL.md",[978,979,981,983,985,987],{"path":287,"priority":288},{"path":980,"priority":291},"references/app-development.md",{"path":982,"priority":291},"references/configuration.md",{"path":984,"priority":291},"references/data-operations.md",{"path":986,"priority":291},"references/job-execution.md",{"path":988,"priority":291},"references/python-sdk.md",{"basePath":990,"description":991,"displayName":992,"installMethods":993,"rationale":994,"selectedPaths":995,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/docx","Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.","docx",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/docx/SKILL.md",[996,997,1000,1002,1004,1006,1008,1010,1012,1014,1016,1018,1020,1022,1024,1026,1028,1030,1032,1034,1036,1038,1040,1042,1044,1046,1048,1050,1052,1054,1056,1058,1060,1062,1064,1066,1068,1070,1072,1074,1076,1078,1080,1082,1084,1086,1088,1090,1092,1094,1096,1098,1100,1102,1104,1106,1108,1110,1112,1114,1116],{"path":287,"priority":288},{"path":998,"priority":999},"LICENSE.txt","high",{"path":1001,"priority":357},"scripts/__init__.py",{"path":1003,"priority":357},"scripts/accept_changes.py",{"path":1005,"priority":357},"scripts/comment.py",{"path":1007,"priority":357},"scripts/office/helpers/__init__.py",{"path":1009,"priority":357},"scripts/office/helpers/merge_runs.py",{"path":1011,"priority":357},"scripts/office/helpers/simplify_redlines.py",{"path":1013,"priority":357},"scripts/office/pack.py",{"path":1015,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd",{"path":1017,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd",{"path":1019,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd",{"path":1021,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd",{"path":1023,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd",{"path":1025,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd",{"path":1027,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd",{"path":1029,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd",{"path":1031,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd",{"path":1033,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd",{"path":1035,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd",{"path":1037,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd",{"path":1039,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd",{"path":1041,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd",{"path":1043,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd",{"path":1045,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd",{"path":1047,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd",{"path":1049,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd",{"path":1051,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd",{"path":1053,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd",{"path":1055,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd",{"path":1057,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd",{"path":1059,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd",{"path":1061,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd",{"path":1063,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd",{"path":1065,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd",{"path":1067,"priority":357},"scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd",{"path":1069,"priority":357},"scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd",{"path":1071,"priority":357},"scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd",{"path":1073,"priority":357},"scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd",{"path":1075,"priority":357},"scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd",{"path":1077,"priority":357},"scripts/office/schemas/mce/mc.xsd",{"path":1079,"priority":357},"scripts/office/schemas/microsoft/wml-2010.xsd",{"path":1081,"priority":357},"scripts/office/schemas/microsoft/wml-2012.xsd",{"path":1083,"priority":357},"scripts/office/schemas/microsoft/wml-2018.xsd",{"path":1085,"priority":357},"scripts/office/schemas/microsoft/wml-cex-2018.xsd",{"path":1087,"priority":357},"scripts/office/schemas/microsoft/wml-cid-2016.xsd",{"path":1089,"priority":357},"scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd",{"path":1091,"priority":357},"scripts/office/schemas/microsoft/wml-symex-2015.xsd",{"path":1093,"priority":357},"scripts/office/soffice.py",{"path":1095,"priority":357},"scripts/office/unpack.py",{"path":1097,"priority":357},"scripts/office/validate.py",{"path":1099,"priority":357},"scripts/office/validators/__init__.py",{"path":1101,"priority":357},"scripts/office/validators/base.py",{"path":1103,"priority":357},"scripts/office/validators/docx.py",{"path":1105,"priority":357},"scripts/office/validators/pptx.py",{"path":1107,"priority":357},"scripts/office/validators/redlining.py",{"path":1109,"priority":357},"scripts/templates/comments.xml",{"path":1111,"priority":357},"scripts/templates/commentsExtended.xml",{"path":1113,"priority":357},"scripts/templates/commentsExtensible.xml",{"path":1115,"priority":357},"scripts/templates/commentsIds.xml",{"path":1117,"priority":357},"scripts/templates/people.xml",{"basePath":1119,"description":1120,"displayName":1121,"installMethods":1122,"rationale":1123,"selectedPaths":1124,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/esm","Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.","esm",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/esm/SKILL.md",[1125,1126,1128,1130,1132],{"path":287,"priority":288},{"path":1127,"priority":291},"references/esm-c-api.md",{"path":1129,"priority":291},"references/esm3-api.md",{"path":1131,"priority":291},"references/forge-api.md",{"path":674,"priority":291},{"basePath":1134,"description":1135,"displayName":1136,"installMethods":1137,"rationale":1138,"selectedPaths":1139,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/etetoolkit","Phylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics.","etetoolkit",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/etetoolkit/SKILL.md",[1140,1141,1142,1144,1145,1147],{"path":287,"priority":288},{"path":898,"priority":291},{"path":1143,"priority":291},"references/visualization.md",{"path":674,"priority":291},{"path":1146,"priority":357},"scripts/quick_visualize.py",{"path":1148,"priority":357},"scripts/tree_operations.py",{"basePath":1150,"description":1151,"displayName":1152,"installMethods":1153,"rationale":1154,"selectedPaths":1155,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/exa-search","Web toolkit powered by Exa, tuned for scientific and technical content. Use this skill when the user needs to search the web or fetch/extract URL content. Covers: web search (semantic lookups, research, current info — with optional research-paper category and academic domain filtering) and URL extraction (fetching pages, articles, academic PDFs in batch). Use this skill for web-related tasks when the user wants high-quality search or scholarly filtering via category=research paper. Triggers on requests to search, look up, fetch a page, or extract an article.","exa-search",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/exa-search/SKILL.md",[1156,1157,1159,1161,1163],{"path":287,"priority":288},{"path":1158,"priority":291},"references/web-extract.md",{"path":1160,"priority":291},"references/web-search.md",{"path":1162,"priority":357},"scripts/exa_extract.py",{"path":1164,"priority":357},"scripts/exa_search.py",{"basePath":1166,"description":1167,"displayName":1168,"installMethods":1169,"rationale":1170,"selectedPaths":1171,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/exploratory-data-analysis","Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.","exploratory-data-analysis",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/exploratory-data-analysis/SKILL.md",[1172,1173,1175,1177,1179,1181,1183,1185,1187],{"path":287,"priority":288},{"path":1174,"priority":357},"assets/report_template.md",{"path":1176,"priority":291},"references/bioinformatics_genomics_formats.md",{"path":1178,"priority":291},"references/chemistry_molecular_formats.md",{"path":1180,"priority":291},"references/general_scientific_formats.md",{"path":1182,"priority":291},"references/microscopy_imaging_formats.md",{"path":1184,"priority":291},"references/proteomics_metabolomics_formats.md",{"path":1186,"priority":291},"references/spectroscopy_analytical_formats.md",{"path":1188,"priority":357},"scripts/eda_analyzer.py",{"basePath":1190,"description":1191,"displayName":1192,"installMethods":1193,"rationale":1194,"selectedPaths":1195,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/flowio","Parse FCS (Flow Cytometry Standard) files v2.0-3.1. Extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame, for flow cytometry data preprocessing.","flowio",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/flowio/SKILL.md",[1196,1197],{"path":287,"priority":288},{"path":898,"priority":291},{"basePath":1199,"description":1200,"displayName":1201,"installMethods":1202,"rationale":1203,"selectedPaths":1204,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/fluidsim","Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or geophysical flows. Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis.","fluidsim",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/fluidsim/SKILL.md",[1205,1206,1208,1210,1212,1214,1216],{"path":287,"priority":288},{"path":1207,"priority":291},"references/advanced_features.md",{"path":1209,"priority":291},"references/installation.md",{"path":1211,"priority":291},"references/output_analysis.md",{"path":1213,"priority":291},"references/parameters.md",{"path":1215,"priority":291},"references/simulation_workflow.md",{"path":1217,"priority":291},"references/solvers.md",{"basePath":1219,"description":1220,"displayName":1221,"installMethods":1222,"rationale":1223,"selectedPaths":1224,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/generate-image","Generate or edit images using AI models (FLUX, Nano Banana 2). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that is not a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.","generate-image",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/generate-image/SKILL.md",[1225,1226],{"path":287,"priority":288},{"path":1227,"priority":357},"scripts/generate_image.py",{"basePath":1229,"description":1230,"displayName":1231,"installMethods":1232,"rationale":1233,"selectedPaths":1234,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/geniml","This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.","geniml",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/geniml/SKILL.md",[1235,1236,1238,1240,1242,1244],{"path":287,"priority":288},{"path":1237,"priority":291},"references/bedspace.md",{"path":1239,"priority":291},"references/consensus_peaks.md",{"path":1241,"priority":291},"references/region2vec.md",{"path":1243,"priority":291},"references/scembed.md",{"path":1245,"priority":291},"references/utilities.md",{"basePath":1247,"description":1248,"displayName":1249,"installMethods":1250,"rationale":1251,"selectedPaths":1252,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/geomaster","Comprehensive geospatial science skill covering remote sensing, GIS, spatial analysis, machine learning for earth observation, and 30+ scientific domains. Supports satellite imagery processing (Sentinel, Landsat, MODIS, SAR, hyperspectral), vector and raster data operations, spatial statistics, point cloud processing, network analysis, cloud-native workflows (STAC, COG, Planetary Computer), and 8 programming languages (Python, R, Julia, JavaScript, C++, Java, Go, Rust) with 500+ code examples. Use for remote sensing workflows, GIS analysis, spatial ML, Earth observation data processing, terrain analysis, hydrological modeling, marine spatial analysis, atmospheric science, and any geospatial computation task.","geomaster",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/geomaster/SKILL.md",[1253,1254,1256,1258,1260,1262,1264,1266,1268,1270,1272,1274,1276,1278,1280,1282],{"path":287,"priority":288},{"path":1255,"priority":999},"README.md",{"path":1257,"priority":291},"references/advanced-gis.md",{"path":1259,"priority":291},"references/big-data.md",{"path":1261,"priority":291},"references/code-examples.md",{"path":1263,"priority":291},"references/coordinate-systems.md",{"path":1265,"priority":291},"references/core-libraries.md",{"path":1267,"priority":291},"references/data-sources.md",{"path":1269,"priority":291},"references/gis-software.md",{"path":1271,"priority":291},"references/industry-applications.md",{"path":1273,"priority":291},"references/machine-learning.md",{"path":1275,"priority":291},"references/programming-languages.md",{"path":1277,"priority":291},"references/remote-sensing.md",{"path":1279,"priority":291},"references/scientific-domains.md",{"path":1281,"priority":291},"references/specialized-topics.md",{"path":1283,"priority":291},"references/troubleshooting.md",{"basePath":1285,"description":1286,"displayName":1287,"installMethods":1288,"rationale":1289,"selectedPaths":1290,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/geopandas","Python library for working with geospatial vector data including shapefiles, GeoJSON, and GeoPackage files. Use when working with geographic data for spatial analysis, geometric operations, coordinate transformations, spatial joins, overlay operations, choropleth mapping, or any task involving reading/writing/analyzing vector geographic data. Supports PostGIS databases, interactive maps, and integration with matplotlib/folium/cartopy. Use for tasks like buffer analysis, spatial joins between datasets, dissolving boundaries, clipping data, calculating areas/distances, reprojecting coordinate systems, creating maps, or converting between spatial file formats.","geopandas",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/geopandas/SKILL.md",[1291,1292,1294,1296,1298,1300,1302],{"path":287,"priority":288},{"path":1293,"priority":291},"references/crs-management.md",{"path":1295,"priority":291},"references/data-io.md",{"path":1297,"priority":291},"references/data-structures.md",{"path":1299,"priority":291},"references/geometric-operations.md",{"path":1301,"priority":291},"references/spatial-analysis.md",{"path":1143,"priority":291},{"basePath":1304,"description":1305,"displayName":1306,"installMethods":1307,"rationale":1308,"selectedPaths":1309,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/get-available-resources","This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.","get-available-resources",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/get-available-resources/SKILL.md",[1310,1311],{"path":287,"priority":288},{"path":1312,"priority":357},"scripts/detect_resources.py",{"basePath":1314,"description":1315,"displayName":1316,"installMethods":1317,"rationale":1318,"selectedPaths":1319,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/gget","Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST searches, AlphaFold structures, enrichment analysis. Best for interactive exploration, simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.","gget",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/gget/SKILL.md",[1320,1321,1323,1325,1326,1328,1330],{"path":287,"priority":288},{"path":1322,"priority":291},"references/database_info.md",{"path":1324,"priority":291},"references/module_reference.md",{"path":674,"priority":291},{"path":1327,"priority":357},"scripts/batch_sequence_analysis.py",{"path":1329,"priority":357},"scripts/enrichment_pipeline.py",{"path":1331,"priority":357},"scripts/gene_analysis.py",{"basePath":1333,"description":1334,"displayName":1335,"installMethods":1336,"rationale":1337,"selectedPaths":1338,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/ginkgo-cloud-lab","Submit and manage protocols on Ginkgo Bioworks Cloud Lab (cloud.ginkgo.bio), a web-based interface for autonomous lab execution on Reconfigurable Automation Carts (RACs). Use when the user wants to run cell-free protein expression (validation or optimization), generate fluorescent pixel art, or interact with Ginkgo Cloud Lab services. Covers protocol selection, input preparation, pricing, and ordering workflows.","ginkgo-cloud-lab",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/ginkgo-cloud-lab/SKILL.md",[1339,1340,1342,1344],{"path":287,"priority":288},{"path":1341,"priority":291},"references/cell-free-protein-expression-optimization.md",{"path":1343,"priority":291},"references/cell-free-protein-expression-validation.md",{"path":1345,"priority":291},"references/fluorescent-pixel-art-generation.md",{"basePath":1347,"description":1348,"displayName":1349,"installMethods":1350,"rationale":1351,"selectedPaths":1352,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/glycoengineering","Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench). For glycoprotein engineering, therapeutic antibody optimization, and vaccine design.","glycoengineering",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/glycoengineering/SKILL.md",[1353,1354],{"path":287,"priority":288},{"path":1355,"priority":291},"references/glycan_databases.md",{"basePath":1357,"description":1358,"displayName":1359,"installMethods":1360,"rationale":1361,"selectedPaths":1362,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/gtars","High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.","gtars",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/gtars/SKILL.md",[1363,1364,1366,1368,1370,1372,1374],{"path":287,"priority":288},{"path":1365,"priority":291},"references/cli.md",{"path":1367,"priority":291},"references/coverage.md",{"path":1369,"priority":291},"references/overlap.md",{"path":1371,"priority":291},"references/python-api.md",{"path":1373,"priority":291},"references/refget.md",{"path":1375,"priority":291},"references/tokenizers.md",{"basePath":1377,"description":1378,"displayName":1379,"installMethods":1380,"rationale":1381,"selectedPaths":1382,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/histolab","Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.","histolab",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/histolab/SKILL.md",[1383,1384,1386,1388,1390,1392],{"path":287,"priority":288},{"path":1385,"priority":291},"references/filters_preprocessing.md",{"path":1387,"priority":291},"references/slide_management.md",{"path":1389,"priority":291},"references/tile_extraction.md",{"path":1391,"priority":291},"references/tissue_masks.md",{"path":1143,"priority":291},{"basePath":1394,"description":1395,"displayName":1396,"installMethods":1397,"rationale":1398,"selectedPaths":1399,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/hugging-science","Use when the user is doing AI/ML work in a scientific domain — biology, chemistry, physics, astronomy, climate, genomics, materials science, medicine, ecology, energy, conservation, engineering, mathematics, scientific reasoning, drug discovery, protein design, weather modeling, theorem proving, single-cell, PDE solving, or anything similar. Hugging Science (huggingscience.co) is a curated catalog of scientific datasets, models, blog posts, and interactive Spaces; the `hugging-science` org on Hugging Face hosts community datasets, models, and demo Spaces. This skill helps you discover the right resource AND actually use it — loading datasets via `datasets`, running models via `transformers` or the HF Inference API, calling Spaces like BoltzGen via `gradio_client`, and citing blog posts for methodology. Trigger this skill whenever a user mentions a scientific ML task, asks for \"a dataset/model for X\" where X is a scientific topic, wants to fine-tune on scientific data, asks about protein / molecule / genome / climate / materials / astronomy / pathology / weather ML, or needs AI tools for research — even if they never say \"Hugging Science\" explicitly. The catalog is purpose-built for LLM agents (it ships an `llms-full.txt`); prefer it over generic web search for these tasks.","hugging-science",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/hugging-science/SKILL.md",[1400,1401,1403,1405,1407,1409,1411],{"path":287,"priority":288},{"path":1402,"priority":291},"references/flagship-resources.md",{"path":1404,"priority":291},"references/topics-and-slugs.md",{"path":1406,"priority":291},"references/using-datasets.md",{"path":1408,"priority":291},"references/using-models.md",{"path":1410,"priority":291},"references/using-spaces.md",{"path":1412,"priority":357},"scripts/fetch_catalog.py",{"basePath":1414,"description":1415,"displayName":1416,"installMethods":1417,"rationale":1418,"selectedPaths":1419,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/hypogenic","Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.","hypogenic",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/hypogenic/SKILL.md",[1420,1421],{"path":287,"priority":288},{"path":1422,"priority":291},"references/config_template.yaml",{"basePath":1424,"description":1425,"displayName":1426,"installMethods":1427,"rationale":1428,"selectedPaths":1429,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/hypothesis-generation","Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic.","hypothesis-generation",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/hypothesis-generation/SKILL.md",[1430,1431,1433,1435,1437,1439,1441,1443,1444],{"path":287,"priority":288},{"path":1432,"priority":357},"assets/FORMATTING_GUIDE.md",{"path":1434,"priority":357},"assets/hypothesis_generation.sty",{"path":1436,"priority":357},"assets/hypothesis_report_template.tex",{"path":1438,"priority":291},"references/experimental_design_patterns.md",{"path":1440,"priority":291},"references/hypothesis_quality_criteria.md",{"path":1442,"priority":291},"references/literature_search_strategies.md",{"path":539,"priority":357},{"path":541,"priority":357},{"basePath":1446,"description":1447,"displayName":1448,"installMethods":1449,"rationale":1450,"selectedPaths":1451,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/imaging-data-commons","Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.","imaging-data-commons",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/imaging-data-commons/SKILL.md",[1452,1453,1455,1457,1459,1461,1463,1465,1467,1469,1471],{"path":287,"priority":288},{"path":1454,"priority":291},"references/bigquery_guide.md",{"path":1456,"priority":291},"references/cli_guide.md",{"path":1458,"priority":291},"references/clinical_data_guide.md",{"path":1460,"priority":291},"references/cloud_storage_guide.md",{"path":1462,"priority":291},"references/dicomweb_guide.md",{"path":1464,"priority":291},"references/digital_pathology_guide.md",{"path":1466,"priority":291},"references/index_tables_guide.md",{"path":1468,"priority":291},"references/parquet_access_guide.md",{"path":1470,"priority":291},"references/sql_patterns.md",{"path":1472,"priority":291},"references/use_cases.md",{"basePath":1474,"description":1475,"displayName":1476,"installMethods":1477,"rationale":1478,"selectedPaths":1479,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/infographics","Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web search for accurate data. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes.","infographics",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/infographics/SKILL.md",[1480,1481,1483,1485,1487,1489],{"path":287,"priority":288},{"path":1482,"priority":291},"references/color_palettes.md",{"path":1484,"priority":291},"references/design_principles.md",{"path":1486,"priority":291},"references/infographic_types.md",{"path":1488,"priority":357},"scripts/generate_infographic.py",{"path":1490,"priority":357},"scripts/generate_infographic_ai.py",{"basePath":1492,"description":1493,"displayName":1494,"installMethods":1495,"rationale":1496,"selectedPaths":1497,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/iso-13485-certification","Comprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems. Use when users need help with ISO 13485 QMS documentation, including (1) conducting gap analysis of existing documentation, (2) creating Quality Manuals, (3) developing required procedures and work instructions, (4) preparing Medical Device Files, (5) understanding ISO 13485 requirements, or (6) identifying missing documentation for medical device certification. Also use when users mention medical device regulations, QMS certification, FDA QMSR, EU MDR, or need help with quality system documentation.","iso-13485-certification",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/iso-13485-certification/SKILL.md",[1498,1499,1501,1503,1505,1507,1509,1511,1513],{"path":287,"priority":288},{"path":1500,"priority":357},"assets/templates/procedures/CAPA-procedure-template.md",{"path":1502,"priority":357},"assets/templates/procedures/document-control-procedure-template.md",{"path":1504,"priority":357},"assets/templates/quality-manual-template.md",{"path":1506,"priority":291},"references/gap-analysis-checklist.md",{"path":1508,"priority":291},"references/iso-13485-requirements.md",{"path":1510,"priority":291},"references/mandatory-documents.md",{"path":1512,"priority":291},"references/quality-manual-guide.md",{"path":1514,"priority":357},"scripts/gap_analyzer.py",{"basePath":1516,"description":1517,"displayName":1518,"installMethods":1519,"rationale":1520,"selectedPaths":1521,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/labarchive-integration","Electronic lab notebook API integration. Access notebooks, manage entries/attachments, backup notebooks, integrate with Protocols.io/Jupyter/REDCap, for programmatic ELN workflows.","labarchive-integration",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/labarchive-integration/SKILL.md",[1522,1523,1524,1526,1528,1530,1532],{"path":287,"priority":288},{"path":898,"priority":291},{"path":1525,"priority":291},"references/authentication_guide.md",{"path":1527,"priority":291},"references/integrations.md",{"path":1529,"priority":357},"scripts/entry_operations.py",{"path":1531,"priority":357},"scripts/notebook_operations.py",{"path":1533,"priority":357},"scripts/setup_config.py",{"basePath":1535,"description":1536,"displayName":1537,"installMethods":1538,"rationale":1539,"selectedPaths":1540,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/lamindb","This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.","lamindb",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/lamindb/SKILL.md",[1541,1542,1544,1546,1548,1549,1551],{"path":287,"priority":288},{"path":1543,"priority":291},"references/annotation-validation.md",{"path":1545,"priority":291},"references/core-concepts.md",{"path":1547,"priority":291},"references/data-management.md",{"path":1527,"priority":291},{"path":1550,"priority":291},"references/ontologies.md",{"path":1552,"priority":291},"references/setup-deployment.md",{"basePath":1554,"description":1555,"displayName":1556,"installMethods":1557,"rationale":1558,"selectedPaths":1559,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/latchbio-integration","Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.","latchbio-integration",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/latchbio-integration/SKILL.md",[1560,1561,1562,1564,1566],{"path":287,"priority":288},{"path":1547,"priority":291},{"path":1563,"priority":291},"references/resource-configuration.md",{"path":1565,"priority":291},"references/verified-workflows.md",{"path":1567,"priority":291},"references/workflow-creation.md",{"basePath":1569,"description":1570,"displayName":1571,"installMethods":1572,"rationale":1573,"selectedPaths":1574,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/latex-posters","Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.","latex-posters",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/latex-posters/SKILL.md",[1575,1576,1578,1580,1582,1584,1585,1587,1589,1591,1593,1594,1595],{"path":287,"priority":288},{"path":1577,"priority":357},"assets/baposter_template.tex",{"path":1579,"priority":357},"assets/beamerposter_template.tex",{"path":1581,"priority":357},"assets/poster_quality_checklist.md",{"path":1583,"priority":357},"assets/tikzposter_template.tex",{"path":571,"priority":291},{"path":1586,"priority":291},"references/latex_poster_packages.md",{"path":1588,"priority":291},"references/poster_content_guide.md",{"path":1590,"priority":291},"references/poster_design_principles.md",{"path":1592,"priority":291},"references/poster_layout_design.md",{"path":539,"priority":357},{"path":541,"priority":357},{"path":1596,"priority":357},"scripts/review_poster.sh",{"basePath":1598,"description":1599,"displayName":1600,"installMethods":1601,"rationale":1602,"selectedPaths":1603,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/literature-review","Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).","literature-review",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/literature-review/SKILL.md",[1604,1605,1607,1609,1611,1613,1614,1615,1617],{"path":287,"priority":288},{"path":1606,"priority":357},"assets/review_template.md",{"path":1608,"priority":291},"references/citation_styles.md",{"path":1610,"priority":291},"references/database_strategies.md",{"path":1612,"priority":357},"scripts/generate_pdf.py",{"path":539,"priority":357},{"path":541,"priority":357},{"path":1616,"priority":357},"scripts/search_databases.py",{"path":1618,"priority":357},"scripts/verify_citations.py",{"basePath":1620,"description":1621,"displayName":1622,"installMethods":1623,"rationale":1624,"selectedPaths":1625,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/markdown-mermaid-writing","Comprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based diagrams as the default documentation standard with full style guides (markdown + mermaid), 24 diagram type references, and 9 document templates.","markdown-mermaid-writing",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/markdown-mermaid-writing/SKILL.md",[1626,1627,1629,1631,1633,1635,1637,1639,1641,1643,1645,1647,1649,1651,1653,1655,1657,1659,1661,1663,1665,1667,1669,1671,1673,1675,1677,1679,1681,1683,1685,1687,1689,1691,1693,1695,1697],{"path":287,"priority":288},{"path":1628,"priority":357},"assets/examples/example-research-report.md",{"path":1630,"priority":291},"references/diagrams/architecture.md",{"path":1632,"priority":291},"references/diagrams/block.md",{"path":1634,"priority":291},"references/diagrams/c4.md",{"path":1636,"priority":291},"references/diagrams/class.md",{"path":1638,"priority":291},"references/diagrams/complex_examples.md",{"path":1640,"priority":291},"references/diagrams/er.md",{"path":1642,"priority":291},"references/diagrams/flowchart.md",{"path":1644,"priority":291},"references/diagrams/gantt.md",{"path":1646,"priority":291},"references/diagrams/git_graph.md",{"path":1648,"priority":291},"references/diagrams/kanban.md",{"path":1650,"priority":291},"references/diagrams/mindmap.md",{"path":1652,"priority":291},"references/diagrams/packet.md",{"path":1654,"priority":291},"references/diagrams/pie.md",{"path":1656,"priority":291},"references/diagrams/quadrant.md",{"path":1658,"priority":291},"references/diagrams/radar.md",{"path":1660,"priority":291},"references/diagrams/requirement.md",{"path":1662,"priority":291},"references/diagrams/sankey.md",{"path":1664,"priority":291},"references/diagrams/sequence.md",{"path":1666,"priority":291},"references/diagrams/state.md",{"path":1668,"priority":291},"references/diagrams/timeline.md",{"path":1670,"priority":291},"references/diagrams/treemap.md",{"path":1672,"priority":291},"references/diagrams/user_journey.md",{"path":1674,"priority":291},"references/diagrams/xy_chart.md",{"path":1676,"priority":291},"references/diagrams/zenuml.md",{"path":1678,"priority":291},"references/markdown_style_guide.md",{"path":1680,"priority":291},"references/mermaid_style_guide.md",{"path":1682,"priority":357},"templates/decision_record.md",{"path":1684,"priority":357},"templates/how_to_guide.md",{"path":1686,"priority":357},"templates/issue.md",{"path":1688,"priority":357},"templates/kanban.md",{"path":1690,"priority":357},"templates/presentation.md",{"path":1692,"priority":357},"templates/project_documentation.md",{"path":1694,"priority":357},"templates/pull_request.md",{"path":1696,"priority":357},"templates/research_paper.md",{"path":1698,"priority":357},"templates/status_report.md",{"basePath":1700,"description":1701,"displayName":1702,"installMethods":1703,"rationale":1704,"selectedPaths":1705,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/market-research-reports","Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix.","market-research-reports",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/market-research-reports/SKILL.md",[1706,1707,1708,1710,1712,1714,1716,1718],{"path":287,"priority":288},{"path":1432,"priority":357},{"path":1709,"priority":357},"assets/market_report_template.tex",{"path":1711,"priority":357},"assets/market_research.sty",{"path":1713,"priority":291},"references/data_analysis_patterns.md",{"path":1715,"priority":291},"references/report_structure_guide.md",{"path":1717,"priority":291},"references/visual_generation_guide.md",{"path":1719,"priority":357},"scripts/generate_market_visuals.py",{"basePath":1721,"description":1722,"displayName":1723,"installMethods":1724,"rationale":1725,"selectedPaths":1726,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/markitdown","Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.","markitdown",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/markitdown/SKILL.md",[1727,1728,1730,1731,1733,1735,1737,1739,1740],{"path":287,"priority":288},{"path":1729,"priority":357},"assets/example_usage.md",{"path":898,"priority":291},{"path":1732,"priority":291},"references/file_formats.md",{"path":1734,"priority":357},"scripts/batch_convert.py",{"path":1736,"priority":357},"scripts/convert_literature.py",{"path":1738,"priority":357},"scripts/convert_with_ai.py",{"path":539,"priority":357},{"path":541,"priority":357},{"basePath":1742,"description":1743,"displayName":1744,"installMethods":1745,"rationale":1746,"selectedPaths":1747,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/matchms","Spectral similarity and compound identification for metabolomics. Use for comparing mass spectra, computing similarity scores (cosine, modified cosine), and identifying unknown compounds from spectral libraries. Best for metabolite identification, spectral matching, library searching. For full LC-MS/MS proteomics pipelines use pyopenms.","matchms",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/matchms/SKILL.md",[1748,1749,1751,1753,1755],{"path":287,"priority":288},{"path":1750,"priority":291},"references/filtering.md",{"path":1752,"priority":291},"references/importing_exporting.md",{"path":1754,"priority":291},"references/similarity.md",{"path":674,"priority":291},{"basePath":1757,"description":1758,"displayName":1759,"installMethods":1760,"rationale":1761,"selectedPaths":1762,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/matlab","MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.","matlab",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/matlab/SKILL.md",[1763,1764,1766,1768,1770,1772,1774,1776,1778],{"path":287,"priority":288},{"path":1765,"priority":291},"references/data-import-export.md",{"path":1767,"priority":291},"references/executing-scripts.md",{"path":1769,"priority":291},"references/graphics-visualization.md",{"path":1771,"priority":291},"references/mathematics.md",{"path":1773,"priority":291},"references/matrices-arrays.md",{"path":1775,"priority":291},"references/octave-compatibility.md",{"path":1777,"priority":291},"references/programming.md",{"path":1779,"priority":291},"references/python-integration.md",{"basePath":1781,"description":1782,"displayName":1783,"installMethods":1784,"rationale":1785,"selectedPaths":1786,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/matplotlib","Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization.","matplotlib",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/matplotlib/SKILL.md",[1787,1788,1789,1791,1793,1795,1797],{"path":287,"priority":288},{"path":898,"priority":291},{"path":1790,"priority":291},"references/common_issues.md",{"path":1792,"priority":291},"references/plot_types.md",{"path":1794,"priority":291},"references/styling_guide.md",{"path":1796,"priority":357},"scripts/plot_template.py",{"path":1798,"priority":357},"scripts/style_configurator.py",{"basePath":1800,"description":1801,"displayName":1802,"installMethods":1803,"rationale":1804,"selectedPaths":1805,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/medchem","Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.","medchem",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/medchem/SKILL.md",[1806,1807,1809,1811],{"path":287,"priority":288},{"path":1808,"priority":291},"references/api_guide.md",{"path":1810,"priority":291},"references/rules_catalog.md",{"path":1812,"priority":357},"scripts/filter_molecules.py",{"basePath":1814,"description":1815,"displayName":1816,"installMethods":1817,"rationale":1818,"selectedPaths":1819,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/modal","Cloud computing platform for running Python on GPUs and serverless infrastructure. Use when deploying AI/ML models, running GPU-accelerated workloads, serving web endpoints, scheduling batch jobs, or scaling Python code to the cloud. Use this skill whenever the user mentions Modal, serverless GPU compute, deploying ML models to the cloud, serving inference endpoints, running batch processing in the cloud, or needs to scale Python workloads beyond their local machine. Also use when the user wants to run code on H100s, A100s, or other cloud GPUs, or needs to create a web API for a model.","modal",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/modal/SKILL.md",[1820,1821,1822,1824,1826,1828,1830,1832,1834,1836,1838,1840,1842],{"path":287,"priority":288},{"path":898,"priority":291},{"path":1823,"priority":291},"references/examples.md",{"path":1825,"priority":291},"references/functions.md",{"path":1827,"priority":291},"references/getting-started.md",{"path":1829,"priority":291},"references/gpu.md",{"path":1831,"priority":291},"references/images.md",{"path":1833,"priority":291},"references/resources.md",{"path":1835,"priority":291},"references/scaling.md",{"path":1837,"priority":291},"references/scheduled-jobs.md",{"path":1839,"priority":291},"references/secrets.md",{"path":1841,"priority":291},"references/volumes.md",{"path":1843,"priority":291},"references/web-endpoints.md",{"basePath":1845,"description":1846,"displayName":1847,"installMethods":1848,"rationale":1849,"selectedPaths":1850,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/molecular-dynamics","Run and analyze molecular dynamics simulations with OpenMM and MDAnalysis. Set up protein/small molecule systems, define force fields, run energy minimization and production MD, analyze trajectories (RMSD, RMSF, contact maps, free energy surfaces). For structural biology, drug binding, and biophysics.","molecular-dynamics",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/molecular-dynamics/SKILL.md",[1851,1852],{"path":287,"priority":288},{"path":1853,"priority":291},"references/mdanalysis_analysis.md",{"basePath":1855,"description":1856,"displayName":1857,"installMethods":1858,"rationale":1859,"selectedPaths":1860,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/molfeat","Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.","molfeat",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/molfeat/SKILL.md",[1861,1862,1863,1865],{"path":287,"priority":288},{"path":898,"priority":291},{"path":1864,"priority":291},"references/available_featurizers.md",{"path":1823,"priority":291},{"basePath":1867,"description":1868,"displayName":1869,"installMethods":1870,"rationale":1871,"selectedPaths":1872,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/networkx","Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.","networkx",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/networkx/SKILL.md",[1873,1874,1875,1877,1879,1881],{"path":287,"priority":288},{"path":350,"priority":291},{"path":1876,"priority":291},"references/generators.md",{"path":1878,"priority":291},"references/graph-basics.md",{"path":1880,"priority":291},"references/io.md",{"path":1143,"priority":291},{"basePath":1883,"description":1884,"displayName":1885,"installMethods":1886,"rationale":1887,"selectedPaths":1888,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/neurokit2","Comprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. Use this skill when processing cardiovascular signals, brain activity, electrodermal responses, respiratory patterns, muscle activity, or eye movements. Applicable for heart rate variability analysis, event-related potentials, complexity measures, autonomic nervous system assessment, psychophysiology research, and multi-modal physiological signal integration.","neurokit2",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/neurokit2/SKILL.md",[1889,1890,1892,1894,1896,1898,1900,1902,1904,1906,1908,1910,1912],{"path":287,"priority":288},{"path":1891,"priority":291},"references/bio_module.md",{"path":1893,"priority":291},"references/complexity.md",{"path":1895,"priority":291},"references/ecg_cardiac.md",{"path":1897,"priority":291},"references/eda.md",{"path":1899,"priority":291},"references/eeg.md",{"path":1901,"priority":291},"references/emg.md",{"path":1903,"priority":291},"references/eog.md",{"path":1905,"priority":291},"references/epochs_events.md",{"path":1907,"priority":291},"references/hrv.md",{"path":1909,"priority":291},"references/ppg.md",{"path":1911,"priority":291},"references/rsp.md",{"path":1913,"priority":291},"references/signal_processing.md",{"basePath":1915,"description":1916,"displayName":1917,"installMethods":1918,"rationale":1919,"selectedPaths":1920,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/neuropixels-analysis","Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.","neuropixels-analysis",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/neuropixels-analysis/SKILL.md",[1921,1922,1924,1926,1928,1930,1932,1934,1936,1938,1939,1941,1943,1945,1947,1949,1951,1953],{"path":287,"priority":288},{"path":1923,"priority":357},"assets/analysis_template.py",{"path":1925,"priority":291},"references/AI_CURATION.md",{"path":1927,"priority":291},"references/ANALYSIS.md",{"path":1929,"priority":291},"references/AUTOMATED_CURATION.md",{"path":1931,"priority":291},"references/MOTION_CORRECTION.md",{"path":1933,"priority":291},"references/PREPROCESSING.md",{"path":1935,"priority":291},"references/QUALITY_METRICS.md",{"path":1937,"priority":291},"references/SPIKE_SORTING.md",{"path":898,"priority":291},{"path":1940,"priority":291},"references/plotting_guide.md",{"path":1942,"priority":291},"references/standard_workflow.md",{"path":1944,"priority":357},"scripts/compute_metrics.py",{"path":1946,"priority":357},"scripts/explore_recording.py",{"path":1948,"priority":357},"scripts/export_to_phy.py",{"path":1950,"priority":357},"scripts/neuropixels_pipeline.py",{"path":1952,"priority":357},"scripts/preprocess_recording.py",{"path":1954,"priority":357},"scripts/run_sorting.py",{"basePath":1956,"description":1957,"displayName":1958,"installMethods":1959,"rationale":1960,"selectedPaths":1961,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/omero-integration","Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.","omero-integration",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/omero-integration/SKILL.md",[1962,1963,1964,1966,1968,1970,1972,1974,1976],{"path":287,"priority":288},{"path":443,"priority":291},{"path":1965,"priority":291},"references/connection.md",{"path":1967,"priority":291},"references/data_access.md",{"path":1969,"priority":291},"references/image_processing.md",{"path":1971,"priority":291},"references/metadata.md",{"path":1973,"priority":291},"references/rois.md",{"path":1975,"priority":291},"references/scripts.md",{"path":373,"priority":291},{"basePath":1978,"description":1979,"displayName":1980,"installMethods":1981,"rationale":1982,"selectedPaths":1983,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/open-notebook","Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. Use when organizing research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating AI-powered notes and summaries, creating multi-speaker podcasts from research, chatting with documents using context-aware AI, searching across materials with full-text and vector search, or running custom content transformations. Supports 16+ AI providers including OpenAI, Anthropic, Google, Ollama, Groq, and Mistral with complete data privacy through self-hosting.","open-notebook",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/open-notebook/SKILL.md",[1984,1985,1986,1988,1989,1990,1992,1994,1996],{"path":287,"priority":288},{"path":898,"priority":291},{"path":1987,"priority":291},"references/architecture.md",{"path":982,"priority":291},{"path":1823,"priority":291},{"path":1991,"priority":357},"scripts/chat_interaction.py",{"path":1993,"priority":357},"scripts/notebook_management.py",{"path":1995,"priority":357},"scripts/source_ingestion.py",{"path":1997,"priority":357},"scripts/test_open_notebook_skill.py",{"basePath":1999,"description":2000,"displayName":2001,"installMethods":2002,"rationale":2003,"selectedPaths":2004,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/opentrons-integration","Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2 features. Best for production Opentrons protocols, official API compatibility. For multi-vendor automation or broader equipment control use pylabrobot.","opentrons-integration",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/opentrons-integration/SKILL.md",[2005,2006,2007,2009,2011],{"path":287,"priority":288},{"path":898,"priority":291},{"path":2008,"priority":357},"scripts/basic_protocol_template.py",{"path":2010,"priority":357},"scripts/pcr_setup_template.py",{"path":2012,"priority":357},"scripts/serial_dilution_template.py",{"basePath":2014,"description":2015,"displayName":2016,"installMethods":2017,"rationale":2018,"selectedPaths":2019,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/optimize-for-gpu","GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, KvikIO, cuCIM, cuxfilter, cuVS, cuSpatial, and RAFT. Use whenever the user mentions GPU/CUDA/NVIDIA acceleration, or wants to speed up NumPy, pandas, scikit-learn, scikit-image, NetworkX, GeoPandas, or Faiss workloads. Covers physics simulation, differentiable rendering, mesh ray casting, particle systems (DEM/SPH/fluids), vector/similarity search, GPUDirect Storage file IO, interactive dashboards, geospatial analysis, medical imaging, and sparse eigensolvers. Also use when you see CPU-bound Python code (loops, large arrays, ML pipelines, graph analytics, image processing) that would benefit from GPU acceleration, even if not explicitly requested.","optimize-for-gpu",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/optimize-for-gpu/SKILL.md",[2020,2021,2023,2025,2027,2029,2031,2033,2035,2037,2039,2041,2043],{"path":287,"priority":288},{"path":2022,"priority":291},"references/cucim.md",{"path":2024,"priority":291},"references/cudf.md",{"path":2026,"priority":291},"references/cugraph.md",{"path":2028,"priority":291},"references/cuml.md",{"path":2030,"priority":291},"references/cupy.md",{"path":2032,"priority":291},"references/cuspatial.md",{"path":2034,"priority":291},"references/cuvs.md",{"path":2036,"priority":291},"references/cuxfilter.md",{"path":2038,"priority":291},"references/kvikio.md",{"path":2040,"priority":291},"references/numba.md",{"path":2042,"priority":291},"references/raft.md",{"path":2044,"priority":291},"references/warp.md",{"basePath":2046,"description":2047,"displayName":2048,"installMethods":2049,"rationale":2050,"selectedPaths":2051,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/paper-lookup","Search 10 academic paper databases via REST APIs for research papers, preprints, and scholarly articles. Covers PubMed, PMC (full text), bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, Unpaywall. Use when searching for papers, citations, DOI/PMID lookups, abstracts, full text, open access, preprints, citation graphs, author search, or any scholarly literature query. Triggers on mentions of any supported database or requests like \"find papers on X\" or \"look up this DOI\".","paper-lookup",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/paper-lookup/SKILL.md",[2052,2053,2055,2057,2059,2061,2063,2065,2067,2069,2071],{"path":287,"priority":288},{"path":2054,"priority":291},"references/arxiv.md",{"path":2056,"priority":291},"references/biorxiv.md",{"path":2058,"priority":291},"references/core.md",{"path":2060,"priority":291},"references/crossref.md",{"path":2062,"priority":291},"references/medrxiv.md",{"path":2064,"priority":291},"references/openalex.md",{"path":2066,"priority":291},"references/pmc.md",{"path":2068,"priority":291},"references/pubmed.md",{"path":2070,"priority":291},"references/semantic-scholar.md",{"path":2072,"priority":291},"references/unpaywall.md",{"basePath":2074,"description":2075,"displayName":2076,"installMethods":2077,"rationale":2078,"selectedPaths":2079,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/paperzilla","Chat with your agent about projects, recommendations, and canonical papers in Paperzilla. Use when users ask for recent project recommendations, canonical paper details, markdown-based summaries, recommendation feedback, feed export, or Atom feed URLs.","paperzilla",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/paperzilla/SKILL.md",[2080],{"path":287,"priority":288},{"basePath":2082,"description":2083,"displayName":2084,"installMethods":2085,"rationale":2086,"selectedPaths":2087,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/parallel-web","All-in-one web toolkit powered by parallel-cli, with a strong emphasis on academic and scientific sources. Use this skill whenever the user needs to search the web, fetch/extract URL content, enrich data with web-sourced fields, or run deep research reports. Covers: web search (fast lookups, research, current info — prioritizing peer-reviewed papers, preprints, and scholarly databases), URL extraction (fetching pages, articles, academic PDFs), bulk data enrichment (adding fields to CSV/lists from the web), and deep research (exhaustive multi-source reports grounded in academic literature). Also handles setup, status checks, and result retrieval. Use this skill for ANY web-related task — even if the user doesn't mention 'parallel' or 'web' explicitly. If they want to look something up, fetch a page, enrich a dataset, investigate a topic, find academic papers, check citations, or review scientific literature, this is the skill to use.","parallel-web",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/parallel-web/SKILL.md",[2088,2089,2091,2093,2094],{"path":287,"priority":288},{"path":2090,"priority":291},"references/data-enrichment.md",{"path":2092,"priority":291},"references/deep-research.md",{"path":1158,"priority":291},{"path":1160,"priority":291},{"basePath":2096,"description":2097,"displayName":2098,"installMethods":2099,"rationale":2100,"selectedPaths":2101,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pathml","Full-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be simpler.","pathml",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pathml/SKILL.md",[2102,2103,2105,2107,2109,2111,2113],{"path":287,"priority":288},{"path":2104,"priority":291},"references/data_management.md",{"path":2106,"priority":291},"references/graphs.md",{"path":2108,"priority":291},"references/image_loading.md",{"path":2110,"priority":291},"references/machine_learning.md",{"path":2112,"priority":291},"references/multiparametric.md",{"path":2114,"priority":291},"references/preprocessing.md",{"basePath":2116,"description":2117,"displayName":2118,"installMethods":2119,"rationale":2120,"selectedPaths":2121,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pdf","Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.","pdf",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pdf/SKILL.md",[2122,2123,2124,2126,2128,2130,2132,2134,2136,2138,2140,2142],{"path":287,"priority":288},{"path":998,"priority":999},{"path":2125,"priority":291},"forms.md",{"path":2127,"priority":291},"reference.md",{"path":2129,"priority":357},"scripts/check_bounding_boxes.py",{"path":2131,"priority":357},"scripts/check_fillable_fields.py",{"path":2133,"priority":357},"scripts/convert_pdf_to_images.py",{"path":2135,"priority":357},"scripts/create_validation_image.py",{"path":2137,"priority":357},"scripts/extract_form_field_info.py",{"path":2139,"priority":357},"scripts/extract_form_structure.py",{"path":2141,"priority":357},"scripts/fill_fillable_fields.py",{"path":2143,"priority":357},"scripts/fill_pdf_form_with_annotations.py",{"basePath":2145,"description":2146,"displayName":2147,"installMethods":2148,"rationale":2149,"selectedPaths":2150,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/peer-review","Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation.","peer-review",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/peer-review/SKILL.md",[2151,2152,2153,2155,2156],{"path":287,"priority":288},{"path":1790,"priority":291},{"path":2154,"priority":291},"references/reporting_standards.md",{"path":539,"priority":357},{"path":541,"priority":357},{"basePath":2158,"description":2159,"displayName":2160,"installMethods":2161,"rationale":2162,"selectedPaths":2163,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pennylane","Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch/JAX/TensorFlow. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.","pennylane",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pennylane/SKILL.md",[2164,2165,2166,2168,2170,2172,2174,2176],{"path":287,"priority":288},{"path":1207,"priority":291},{"path":2167,"priority":291},"references/devices_backends.md",{"path":2169,"priority":291},"references/getting_started.md",{"path":2171,"priority":291},"references/optimization.md",{"path":2173,"priority":291},"references/quantum_chemistry.md",{"path":2175,"priority":291},"references/quantum_circuits.md",{"path":2177,"priority":291},"references/quantum_ml.md",{"basePath":2179,"description":2180,"displayName":2181,"installMethods":2182,"rationale":2183,"selectedPaths":2184,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/phylogenetics","Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.","phylogenetics",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/phylogenetics/SKILL.md",[2185,2186,2188],{"path":287,"priority":288},{"path":2187,"priority":291},"references/iqtree_inference.md",{"path":2189,"priority":357},"scripts/phylogenetic_analysis.py",{"basePath":2191,"description":2192,"displayName":2193,"installMethods":2194,"rationale":2195,"selectedPaths":2196,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/polars","Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.","polars",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/polars/SKILL.md",[2197,2198,2199,2201,2203,2205,2207],{"path":287,"priority":288},{"path":332,"priority":291},{"path":2200,"priority":291},"references/core_concepts.md",{"path":2202,"priority":291},"references/io_guide.md",{"path":2204,"priority":291},"references/operations.md",{"path":2206,"priority":291},"references/pandas_migration.md",{"path":322,"priority":291},{"basePath":2209,"description":2210,"displayName":2211,"installMethods":2212,"rationale":2213,"selectedPaths":2214,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/polars-bio","High-performance genomic interval operations and bioinformatics file I/O on Polars DataFrames. Overlap, nearest, merge, coverage, complement, subtract for BED/VCF/BAM/GFF intervals. Streaming, cloud-native, faster bioframe alternative.","polars-bio",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/polars-bio/SKILL.md",[2215,2216,2218,2219,2221,2223,2225],{"path":287,"priority":288},{"path":2217,"priority":291},"references/bioframe_migration.md",{"path":982,"priority":291},{"path":2220,"priority":291},"references/file_io.md",{"path":2222,"priority":291},"references/interval_operations.md",{"path":2224,"priority":291},"references/pileup_operations.md",{"path":2226,"priority":291},"references/sql_processing.md",{"basePath":2228,"description":2229,"displayName":2230,"installMethods":2231,"rationale":2232,"selectedPaths":2233,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pptx","Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.","pptx",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pptx/SKILL.md",[2234,2235,2236,2238,2240,2241,2243,2245,2246,2247,2248,2249,2250,2251,2252,2253,2254,2255,2256,2257,2258,2259,2260,2261,2262,2263,2264,2265,2266,2267,2268,2269,2270,2271,2272,2273,2274,2275,2276,2277,2278,2279,2280,2281,2282,2283,2284,2285,2286,2287,2288,2289,2290,2291,2292,2293,2294,2295,2296],{"path":287,"priority":288},{"path":998,"priority":999},{"path":2237,"priority":291},"editing.md",{"path":2239,"priority":291},"pptxgenjs.md",{"path":1001,"priority":357},{"path":2242,"priority":357},"scripts/add_slide.py",{"path":2244,"priority":357},"scripts/clean.py",{"path":1007,"priority":357},{"path":1009,"priority":357},{"path":1011,"priority":357},{"path":1013,"priority":357},{"path":1015,"priority":357},{"path":1017,"priority":357},{"path":1019,"priority":357},{"path":1021,"priority":357},{"path":1023,"priority":357},{"path":1025,"priority":357},{"path":1027,"priority":357},{"path":1029,"priority":357},{"path":1031,"priority":357},{"path":1033,"priority":357},{"path":1035,"priority":357},{"path":1037,"priority":357},{"path":1039,"priority":357},{"path":1041,"priority":357},{"path":1043,"priority":357},{"path":1045,"priority":357},{"path":1047,"priority":357},{"path":1049,"priority":357},{"path":1051,"priority":357},{"path":1053,"priority":357},{"path":1055,"priority":357},{"path":1057,"priority":357},{"path":1059,"priority":357},{"path":1061,"priority":357},{"path":1063,"priority":357},{"path":1065,"priority":357},{"path":1067,"priority":357},{"path":1069,"priority":357},{"path":1071,"priority":357},{"path":1073,"priority":357},{"path":1075,"priority":357},{"path":1077,"priority":357},{"path":1079,"priority":357},{"path":1081,"priority":357},{"path":1083,"priority":357},{"path":1085,"priority":357},{"path":1087,"priority":357},{"path":1089,"priority":357},{"path":1091,"priority":357},{"path":1093,"priority":357},{"path":1095,"priority":357},{"path":1097,"priority":357},{"path":1099,"priority":357},{"path":1101,"priority":357},{"path":1103,"priority":357},{"path":1105,"priority":357},{"path":1107,"priority":357},{"path":2297,"priority":357},"scripts/thumbnail.py",{"basePath":2299,"description":2300,"displayName":2301,"installMethods":2302,"rationale":2303,"selectedPaths":2304,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pptx-posters","Create research posters using HTML/CSS that can be exported to PDF or PPTX. Use this skill ONLY when the user explicitly requests PowerPoint/PPTX poster format. For standard research posters, use latex-posters instead. This skill provides modern web-based poster design with responsive layouts and easy visual integration.","pptx-posters",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pptx-posters/SKILL.md",[2305,2306,2308,2309,2310,2311,2312,2313],{"path":287,"priority":288},{"path":2307,"priority":357},"assets/poster_html_template.html",{"path":1581,"priority":357},{"path":1588,"priority":291},{"path":1590,"priority":291},{"path":1592,"priority":291},{"path":539,"priority":357},{"path":541,"priority":357},{"basePath":2315,"description":2316,"displayName":2317,"installMethods":2318,"rationale":2319,"selectedPaths":2320,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/primekg","Query the Precision Medicine Knowledge Graph (PrimeKG) for multiscale biological data including genes, drugs, diseases, phenotypes, and more.","primekg",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/primekg/SKILL.md",[2321,2322],{"path":287,"priority":288},{"path":2323,"priority":357},"scripts/query_primekg.py",{"basePath":2325,"description":2326,"displayName":2327,"installMethods":2328,"rationale":2329,"selectedPaths":2330,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/protocolsio-integration","Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.","protocolsio-integration",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/protocolsio-integration/SKILL.md",[2331,2332,2334,2335,2337,2339,2341],{"path":287,"priority":288},{"path":2333,"priority":291},"references/additional_features.md",{"path":423,"priority":291},{"path":2336,"priority":291},"references/discussions.md",{"path":2338,"priority":291},"references/file_manager.md",{"path":2340,"priority":291},"references/protocols_api.md",{"path":2342,"priority":291},"references/workspaces.md",{"basePath":2344,"description":2345,"displayName":2346,"installMethods":2347,"rationale":2348,"selectedPaths":2349,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pufferlib","High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.","pufferlib",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pufferlib/SKILL.md",[2350,2351,2353,2355,2357,2359,2361,2363],{"path":287,"priority":288},{"path":2352,"priority":291},"references/environments.md",{"path":2354,"priority":291},"references/integration.md",{"path":2356,"priority":291},"references/policies.md",{"path":2358,"priority":291},"references/training.md",{"path":2360,"priority":291},"references/vectorization.md",{"path":2362,"priority":357},"scripts/env_template.py",{"path":2364,"priority":357},"scripts/train_template.py",{"basePath":2366,"description":2367,"displayName":2368,"installMethods":2369,"rationale":2370,"selectedPaths":2371,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pydeseq2","Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.","pydeseq2",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pydeseq2/SKILL.md",[2372,2373,2374,2376],{"path":287,"priority":288},{"path":898,"priority":291},{"path":2375,"priority":291},"references/workflow_guide.md",{"path":2377,"priority":357},"scripts/run_deseq2_analysis.py",{"basePath":2379,"description":2380,"displayName":2381,"installMethods":2382,"rationale":2383,"selectedPaths":2384,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pydicom","Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.","pydicom",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pydicom/SKILL.md",[2385,2386,2388,2390,2392,2394],{"path":287,"priority":288},{"path":2387,"priority":291},"references/common_tags.md",{"path":2389,"priority":291},"references/transfer_syntaxes.md",{"path":2391,"priority":357},"scripts/anonymize_dicom.py",{"path":2393,"priority":357},"scripts/dicom_to_image.py",{"path":535,"priority":357},{"basePath":2396,"description":2397,"displayName":2398,"installMethods":2399,"rationale":2400,"selectedPaths":2401,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pyhealth","Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer, RETAIN, GAMENet, SafeDrug, MICRON, StageNet, AdaCare, CNN/RNN/MLP), training with the PyHealth Trainer, computing clinical metrics, and using medical code utilities (ICD/ATC/NDC/RxNorm lookup and cross-mapping). Use this skill whenever the user mentions PyHealth, MIMIC, eICU, OMOP, EHR modeling, clinical prediction, drug recommendation, sleep staging, medical code mapping, ICD/ATC codes, or any healthcare ML pipeline that fits the dataset → task → model → trainer → metrics pattern, even if \"PyHealth\" isn't named explicitly.","pyhealth",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pyhealth/SKILL.md",[2402,2403,2405,2407,2408,2409,2411,2413],{"path":287,"priority":288},{"path":2404,"priority":357},"assets/starter_pipeline.py",{"path":2406,"priority":291},"references/datasets.md",{"path":1823,"priority":291},{"path":1209,"priority":291},{"path":2410,"priority":291},"references/medcode.md",{"path":2412,"priority":291},"references/models.md",{"path":2414,"priority":291},"references/tasks.md",{"basePath":2416,"description":2417,"displayName":2418,"installMethods":2419,"rationale":2420,"selectedPaths":2421,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pylabrobot","Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API, opentrons-integration may be simpler.","pylabrobot",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pylabrobot/SKILL.md",[2422,2423,2425,2427,2429,2431,2432],{"path":287,"priority":288},{"path":2424,"priority":291},"references/analytical-equipment.md",{"path":2426,"priority":291},"references/hardware-backends.md",{"path":2428,"priority":291},"references/liquid-handling.md",{"path":2430,"priority":291},"references/material-handling.md",{"path":1833,"priority":291},{"path":1143,"priority":291},{"basePath":2434,"description":2435,"displayName":2436,"installMethods":2437,"rationale":2438,"selectedPaths":2439,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pymatgen","Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science.","pymatgen",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pymatgen/SKILL.md",[2440,2441,2443,2445,2447,2449,2451,2453,2455],{"path":287,"priority":288},{"path":2442,"priority":291},"references/analysis_modules.md",{"path":2444,"priority":291},"references/core_classes.md",{"path":2446,"priority":291},"references/io_formats.md",{"path":2448,"priority":291},"references/materials_project_api.md",{"path":2450,"priority":291},"references/transformations_workflows.md",{"path":2452,"priority":357},"scripts/phase_diagram_generator.py",{"path":2454,"priority":357},"scripts/structure_analyzer.py",{"path":2456,"priority":357},"scripts/structure_converter.py",{"basePath":2458,"description":2459,"displayName":2460,"installMethods":2461,"rationale":2462,"selectedPaths":2463,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pymc","Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.","pymc",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pymc/SKILL.md",[2464,2465,2467,2469,2471,2473,2474,2476],{"path":287,"priority":288},{"path":2466,"priority":357},"assets/hierarchical_model_template.py",{"path":2468,"priority":357},"assets/linear_regression_template.py",{"path":2470,"priority":291},"references/distributions.md",{"path":2472,"priority":291},"references/sampling_inference.md",{"path":674,"priority":291},{"path":2475,"priority":357},"scripts/model_comparison.py",{"path":2477,"priority":357},"scripts/model_diagnostics.py",{"basePath":2479,"description":2480,"displayName":2481,"installMethods":2482,"rationale":2483,"selectedPaths":2484,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pymoo","Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.","pymoo",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pymoo/SKILL.md",[2485,2486,2487,2489,2491,2493,2494,2496,2498,2500,2502],{"path":287,"priority":288},{"path":350,"priority":291},{"path":2488,"priority":291},"references/constraints_mcdm.md",{"path":2490,"priority":291},"references/operators.md",{"path":2492,"priority":291},"references/problems.md",{"path":1143,"priority":291},{"path":2495,"priority":357},"scripts/custom_problem_example.py",{"path":2497,"priority":357},"scripts/decision_making_example.py",{"path":2499,"priority":357},"scripts/many_objective_example.py",{"path":2501,"priority":357},"scripts/multi_objective_example.py",{"path":2503,"priority":357},"scripts/single_objective_example.py",{"basePath":2505,"description":2506,"displayName":2507,"installMethods":2508,"rationale":2509,"selectedPaths":2510,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pyopenms","Complete mass spectrometry analysis platform. Use for proteomics workflows feature detection, peptide identification, protein quantification, and complex LC-MS/MS pipelines. Supports extensive file formats and algorithms. Best for proteomics, comprehensive MS data processing. For simple spectral comparison and metabolite ID use matchms.","pyopenms",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pyopenms/SKILL.md",[2511,2512,2514,2516,2517,2519,2521],{"path":287,"priority":288},{"path":2513,"priority":291},"references/data_structures.md",{"path":2515,"priority":291},"references/feature_detection.md",{"path":2220,"priority":291},{"path":2518,"priority":291},"references/identification.md",{"path":2520,"priority":291},"references/metabolomics.md",{"path":1913,"priority":291},{"basePath":2523,"description":2524,"displayName":2525,"installMethods":2526,"rationale":2527,"selectedPaths":2528,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pysam","Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.","pysam",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pysam/SKILL.md",[2529,2530,2532,2534,2536],{"path":287,"priority":288},{"path":2531,"priority":291},"references/alignment_files.md",{"path":2533,"priority":291},"references/common_workflows.md",{"path":2535,"priority":291},"references/sequence_files.md",{"path":2537,"priority":291},"references/variant_files.md",{"basePath":2539,"description":2540,"displayName":2541,"installMethods":2542,"rationale":2543,"selectedPaths":2544,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pytdc","Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.","pytdc",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pytdc/SKILL.md",[2545,2546,2547,2549,2550,2552,2554],{"path":287,"priority":288},{"path":2406,"priority":291},{"path":2548,"priority":291},"references/oracles.md",{"path":1245,"priority":291},{"path":2551,"priority":357},"scripts/benchmark_evaluation.py",{"path":2553,"priority":357},"scripts/load_and_split_data.py",{"path":2555,"priority":357},"scripts/molecular_generation.py",{"basePath":2557,"description":2558,"displayName":2559,"installMethods":2560,"rationale":2561,"selectedPaths":2562,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pytorch-lightning","Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.","pytorch-lightning",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pytorch-lightning/SKILL.md",[2563,2564,2565,2567,2569,2571,2573,2575,2577,2579,2581],{"path":287,"priority":288},{"path":332,"priority":291},{"path":2566,"priority":291},"references/callbacks.md",{"path":2568,"priority":291},"references/data_module.md",{"path":2570,"priority":291},"references/distributed_training.md",{"path":2572,"priority":291},"references/lightning_module.md",{"path":2574,"priority":291},"references/logging.md",{"path":2576,"priority":291},"references/trainer.md",{"path":2578,"priority":357},"scripts/quick_trainer_setup.py",{"path":2580,"priority":357},"scripts/template_datamodule.py",{"path":2582,"priority":357},"scripts/template_lightning_module.py",{"basePath":2584,"description":2585,"displayName":2586,"installMethods":2587,"rationale":2588,"selectedPaths":2589,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/pyzotero","Interact with Zotero reference management libraries using the pyzotero Python client. Retrieve, create, update, and delete items, collections, tags, and attachments via the Zotero Web API v3. Use this skill when working with Zotero libraries programmatically, managing bibliographic references, exporting citations, searching library contents, uploading PDF attachments, or building research automation workflows that integrate with Zotero.","pyzotero",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/pyzotero/SKILL.md",[2590,2591,2592,2593,2595,2597,2599,2601,2603,2605,2607,2609,2611,2613],{"path":287,"priority":288},{"path":423,"priority":291},{"path":1365,"priority":291},{"path":2594,"priority":291},"references/collections.md",{"path":2596,"priority":291},"references/error-handling.md",{"path":2598,"priority":291},"references/exports.md",{"path":2600,"priority":291},"references/files-attachments.md",{"path":2602,"priority":291},"references/full-text.md",{"path":2604,"priority":291},"references/pagination.md",{"path":2606,"priority":291},"references/read-api.md",{"path":2608,"priority":291},"references/saved-searches.md",{"path":2610,"priority":291},"references/search-params.md",{"path":2612,"priority":291},"references/tags.md",{"path":2614,"priority":291},"references/write-api.md",{"basePath":260,"description":10,"displayName":222,"installMethods":2616,"rationale":2617,"selectedPaths":2618,"source":292,"sourceLanguage":18,"type":263},{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/qiskit/SKILL.md",[2619,2620,2621,2623,2625,2627,2629,2631,2633],{"path":287,"priority":288},{"path":350,"priority":291},{"path":2622,"priority":291},"references/backends.md",{"path":2624,"priority":291},"references/circuits.md",{"path":2626,"priority":291},"references/patterns.md",{"path":2628,"priority":291},"references/primitives.md",{"path":2630,"priority":291},"references/setup.md",{"path":2632,"priority":291},"references/transpilation.md",{"path":1143,"priority":291},{"basePath":2635,"description":2636,"displayName":2637,"installMethods":2638,"rationale":2639,"selectedPaths":2640,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/qutip","Quantum physics simulation library for open quantum systems. Use when studying master equations, Lindblad dynamics, decoherence, quantum optics, or cavity QED. Best for physics research, open system dynamics, and educational simulations. NOT for circuit-based quantum computing—use qiskit, cirq, or pennylane for quantum algorithms and hardware execution.","qutip",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/qutip/SKILL.md",[2641,2642,2643,2645,2646,2648],{"path":287,"priority":288},{"path":443,"priority":291},{"path":2644,"priority":291},"references/analysis.md",{"path":2200,"priority":291},{"path":2647,"priority":291},"references/time_evolution.md",{"path":1143,"priority":291},{"basePath":2650,"description":2651,"displayName":2652,"installMethods":2653,"rationale":2654,"selectedPaths":2655,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/rdkit","Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.","rdkit",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/rdkit/SKILL.md",[2656,2657,2658,2660,2662,2664,2666],{"path":287,"priority":288},{"path":898,"priority":291},{"path":2659,"priority":291},"references/descriptors_reference.md",{"path":2661,"priority":291},"references/smarts_patterns.md",{"path":2663,"priority":357},"scripts/molecular_properties.py",{"path":2665,"priority":357},"scripts/similarity_search.py",{"path":2667,"priority":357},"scripts/substructure_filter.py",{"basePath":2669,"description":2670,"displayName":2671,"installMethods":2672,"rationale":2673,"selectedPaths":2674,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/research-grants","Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.","research-grants",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/research-grants/SKILL.md",[2675,2676,2678,2680,2682,2683,2685,2687,2689,2691,2693,2695,2697,2698],{"path":287,"priority":288},{"path":2677,"priority":357},"assets/budget_justification_template.md",{"path":2679,"priority":357},"assets/nih_specific_aims_template.md",{"path":2681,"priority":357},"assets/nsf_project_summary_template.md",{"path":571,"priority":291},{"path":2684,"priority":291},"references/broader_impacts.md",{"path":2686,"priority":291},"references/darpa_guidelines.md",{"path":2688,"priority":291},"references/doe_guidelines.md",{"path":2690,"priority":291},"references/nih_guidelines.md",{"path":2692,"priority":291},"references/nsf_guidelines.md",{"path":2694,"priority":291},"references/nstc_guidelines.md",{"path":2696,"priority":291},"references/specific_aims_guide.md",{"path":539,"priority":357},{"path":541,"priority":357},{"basePath":2700,"description":2701,"displayName":2702,"installMethods":2703,"rationale":2704,"selectedPaths":2705,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/research-lookup","Look up current research information using parallel-cli search (primary, fast web search), the Parallel Chat API (deep research), or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information. Note: query text is transmitted to api.parallel.ai (PARALLEL_API_KEY) and, for academic searches, to openrouter.ai (OPENROUTER_API_KEY).","research-lookup",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/research-lookup/SKILL.md",[2706,2707,2708,2709,2710],{"path":287,"priority":288},{"path":1255,"priority":999},{"path":539,"priority":357},{"path":541,"priority":357},{"path":2711,"priority":357},"scripts/research_lookup.py",{"basePath":2713,"description":2714,"displayName":2715,"installMethods":2716,"rationale":2717,"selectedPaths":2718,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/rowan","Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use for pKa and macropKa prediction, conformer and tautomer ensembles, docking and analogue docking, protein-ligand cofolding, MSA generation, molecular dynamics, permeability, descriptor workflows, and related small-molecule or protein modeling tasks. Ideal for programmatic batch screening, multi-step chemistry pipelines, and workflows that would otherwise require maintaining local HPC/GPU infrastructure.","rowan",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/rowan/SKILL.md",[2719],{"path":287,"priority":288},{"basePath":2721,"description":2722,"displayName":2723,"installMethods":2724,"rationale":2725,"selectedPaths":2726,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/scanpy","Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use anndata.","scanpy",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/scanpy/SKILL.md",[2727,2728,2729,2730,2731,2732],{"path":287,"priority":288},{"path":1923,"priority":357},{"path":898,"priority":291},{"path":1940,"priority":291},{"path":1942,"priority":291},{"path":2733,"priority":357},"scripts/qc_analysis.py",{"basePath":2735,"description":2736,"displayName":2737,"installMethods":2738,"rationale":2739,"selectedPaths":2740,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/scholar-evaluation","Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and writing with quantitative scoring and actionable feedback.","scholar-evaluation",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/scholar-evaluation/SKILL.md",[2741,2742,2744,2746,2747],{"path":287,"priority":288},{"path":2743,"priority":291},"references/evaluation_framework.md",{"path":2745,"priority":357},"scripts/calculate_scores.py",{"path":539,"priority":357},{"path":541,"priority":357},{"basePath":2749,"description":2750,"displayName":2751,"installMethods":2752,"rationale":2753,"selectedPaths":2754,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/scientific-brainstorming","Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.","scientific-brainstorming",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/scientific-brainstorming/SKILL.md",[2755,2756],{"path":287,"priority":288},{"path":2757,"priority":291},"references/brainstorming_methods.md",{"basePath":2759,"description":2760,"displayName":2761,"installMethods":2762,"rationale":2763,"selectedPaths":2764,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/scientific-critical-thinking","Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review.","scientific-critical-thinking",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/scientific-critical-thinking/SKILL.md",[2765,2766,2768,2770,2772,2774,2776,2778,2779],{"path":287,"priority":288},{"path":2767,"priority":291},"references/common_biases.md",{"path":2769,"priority":291},"references/evidence_hierarchy.md",{"path":2771,"priority":291},"references/experimental_design.md",{"path":2773,"priority":291},"references/logical_fallacies.md",{"path":2775,"priority":291},"references/scientific_method.md",{"path":2777,"priority":291},"references/statistical_pitfalls.md",{"path":539,"priority":357},{"path":541,"priority":357},{"basePath":2781,"description":2782,"displayName":2783,"installMethods":2784,"rationale":2785,"selectedPaths":2786,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/scientific-schematics","Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.","scientific-schematics",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/scientific-schematics/SKILL.md",[2787,2788,2790,2791,2792,2794,2795],{"path":287,"priority":288},{"path":2789,"priority":291},"references/QUICK_REFERENCE.md",{"path":571,"priority":291},{"path":332,"priority":291},{"path":2793,"priority":357},"scripts/example_usage.sh",{"path":539,"priority":357},{"path":541,"priority":357},{"basePath":2797,"description":2798,"displayName":2799,"installMethods":2800,"rationale":2801,"selectedPaths":2802,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/scientific-slides","Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.","scientific-slides",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/scientific-slides/SKILL.md",[2803,2804,2806,2808,2810,2812,2814,2816,2818,2820,2822,2824,2826,2827,2828,2830,2832,2834,2836],{"path":287,"priority":288},{"path":2805,"priority":357},"assets/beamer_template_conference.tex",{"path":2807,"priority":357},"assets/beamer_template_defense.tex",{"path":2809,"priority":357},"assets/beamer_template_seminar.tex",{"path":2811,"priority":357},"assets/powerpoint_design_guide.md",{"path":2813,"priority":357},"assets/timing_guidelines.md",{"path":2815,"priority":291},"references/beamer_guide.md",{"path":2817,"priority":291},"references/data_visualization_slides.md",{"path":2819,"priority":291},"references/presentation_structure.md",{"path":2821,"priority":291},"references/slide_design_principles.md",{"path":2823,"priority":291},"references/talk_types_guide.md",{"path":2825,"priority":291},"references/visual_review_workflow.md",{"path":539,"priority":357},{"path":541,"priority":357},{"path":2829,"priority":357},"scripts/generate_slide_image.py",{"path":2831,"priority":357},"scripts/generate_slide_image_ai.py",{"path":2833,"priority":357},"scripts/pdf_to_images.py",{"path":2835,"priority":357},"scripts/slides_to_pdf.py",{"path":2837,"priority":357},"scripts/validate_presentation.py",{"basePath":2839,"description":2840,"displayName":2841,"installMethods":2842,"rationale":2843,"selectedPaths":2844,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/scientific-visualization","Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.","scientific-visualization",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/scientific-visualization/SKILL.md",[2845,2846,2848,2850,2852,2854,2855,2857,2859,2861,2863],{"path":287,"priority":288},{"path":2847,"priority":357},"assets/color_palettes.py",{"path":2849,"priority":357},"assets/nature.mplstyle",{"path":2851,"priority":357},"assets/presentation.mplstyle",{"path":2853,"priority":357},"assets/publication.mplstyle",{"path":1482,"priority":291},{"path":2856,"priority":291},"references/journal_requirements.md",{"path":2858,"priority":291},"references/matplotlib_examples.md",{"path":2860,"priority":291},"references/publication_guidelines.md",{"path":2862,"priority":357},"scripts/figure_export.py",{"path":2864,"priority":357},"scripts/style_presets.py",{"basePath":2866,"description":2867,"displayName":2868,"installMethods":2869,"rationale":2870,"selectedPaths":2871,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/scientific-writing","Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.","scientific-writing",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/scientific-writing/SKILL.md",[2872,2873,2875,2877,2879,2880,2882,2884,2886,2888,2890,2891,2892],{"path":287,"priority":288},{"path":2874,"priority":357},"assets/REPORT_FORMATTING_GUIDE.md",{"path":2876,"priority":357},"assets/scientific_report.sty",{"path":2878,"priority":357},"assets/scientific_report_template.tex",{"path":1608,"priority":291},{"path":2881,"priority":291},"references/figures_tables.md",{"path":2883,"priority":291},"references/imrad_structure.md",{"path":2885,"priority":291},"references/professional_report_formatting.md",{"path":2887,"priority":291},"references/reporting_guidelines.md",{"path":2889,"priority":291},"references/writing_principles.md",{"path":1227,"priority":357},{"path":539,"priority":357},{"path":541,"priority":357},{"basePath":2894,"description":2895,"displayName":2896,"installMethods":2897,"rationale":2898,"selectedPaths":2899,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/scikit-bio","Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.","scikit-bio",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/scikit-bio/SKILL.md",[2900,2901],{"path":287,"priority":288},{"path":898,"priority":291},{"basePath":2903,"description":2904,"displayName":2905,"installMethods":2906,"rationale":2907,"selectedPaths":2908,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/scikit-learn","Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.","scikit-learn",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/scikit-learn/SKILL.md",[2909,2910,2912,2914,2915,2917,2919,2921,2923],{"path":287,"priority":288},{"path":2911,"priority":291},"references/model_evaluation.md",{"path":2913,"priority":291},"references/pipelines_and_composition.md",{"path":2114,"priority":291},{"path":2916,"priority":291},"references/quick_reference.md",{"path":2918,"priority":291},"references/supervised_learning.md",{"path":2920,"priority":291},"references/unsupervised_learning.md",{"path":2922,"priority":357},"scripts/classification_pipeline.py",{"path":2924,"priority":357},"scripts/clustering_analysis.py",{"basePath":2926,"description":2927,"displayName":2928,"installMethods":2929,"rationale":2930,"selectedPaths":2931,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/scikit-survival","Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-event analysis, fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, handling competing risks, or implementing any survival analysis workflow with the scikit-survival library.","scikit-survival",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/scikit-survival/SKILL.md",[2932,2933,2935,2937,2939,2941,2943],{"path":287,"priority":288},{"path":2934,"priority":291},"references/competing-risks.md",{"path":2936,"priority":291},"references/cox-models.md",{"path":2938,"priority":291},"references/data-handling.md",{"path":2940,"priority":291},"references/ensemble-models.md",{"path":2942,"priority":291},"references/evaluation-metrics.md",{"path":2944,"priority":291},"references/svm-models.md",{"basePath":2946,"description":2947,"displayName":2948,"installMethods":2949,"rationale":2950,"selectedPaths":2951,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/scvelo","RNA velocity analysis with scVelo. Estimate cell state transitions from unspliced/spliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data. Complements Scanpy/scVI-tools for trajectory inference.","scvelo",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/scvelo/SKILL.md",[2952,2953,2955],{"path":287,"priority":288},{"path":2954,"priority":291},"references/velocity_models.md",{"path":2956,"priority":357},"scripts/rna_velocity_workflow.py",{"basePath":2958,"description":2959,"displayName":2960,"installMethods":2961,"rationale":2962,"selectedPaths":2963,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/scvi-tools","Deep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI). Best for advanced modeling, batch effects, multimodal data. For standard analysis pipelines use scanpy.","scvi-tools",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/scvi-tools/SKILL.md",[2964,2965,2967,2969,2971,2973,2975,2977,2979],{"path":287,"priority":288},{"path":2966,"priority":291},"references/differential-expression.md",{"path":2968,"priority":291},"references/models-atac-seq.md",{"path":2970,"priority":291},"references/models-multimodal.md",{"path":2972,"priority":291},"references/models-scrna-seq.md",{"path":2974,"priority":291},"references/models-spatial.md",{"path":2976,"priority":291},"references/models-specialized.md",{"path":2978,"priority":291},"references/theoretical-foundations.md",{"path":674,"priority":291},{"basePath":2981,"description":2982,"displayName":2983,"installMethods":2984,"rationale":2985,"selectedPaths":2986,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/seaborn","Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualization.","seaborn",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/seaborn/SKILL.md",[2987,2988,2989,2991],{"path":287,"priority":288},{"path":1823,"priority":291},{"path":2990,"priority":291},"references/function_reference.md",{"path":2992,"priority":291},"references/objects_interface.md",{"basePath":2994,"description":2995,"displayName":2996,"installMethods":2997,"rationale":2998,"selectedPaths":2999,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/shap","Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.","shap",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/shap/SKILL.md",[3000,3001,3003,3005,3007],{"path":287,"priority":288},{"path":3002,"priority":291},"references/explainers.md",{"path":3004,"priority":291},"references/plots.md",{"path":3006,"priority":291},"references/theory.md",{"path":674,"priority":291},{"basePath":3009,"description":3010,"displayName":3011,"installMethods":3012,"rationale":3013,"selectedPaths":3014,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/simpy","Process-based discrete-event simulation framework in Python. Use this skill when building simulations of systems with processes, queues, resources, and time-based events such as manufacturing systems, service operations, network traffic, logistics, or any system where entities interact with shared resources over time.","simpy",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/simpy/SKILL.md",[3015,3016,3018,3020,3022,3024,3025,3027],{"path":287,"priority":288},{"path":3017,"priority":291},"references/events.md",{"path":3019,"priority":291},"references/monitoring.md",{"path":3021,"priority":291},"references/process-interaction.md",{"path":3023,"priority":291},"references/real-time.md",{"path":1833,"priority":291},{"path":3026,"priority":357},"scripts/basic_simulation_template.py",{"path":3028,"priority":357},"scripts/resource_monitor.py",{"basePath":3030,"description":3031,"displayName":3032,"installMethods":3033,"rationale":3034,"selectedPaths":3035,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/stable-baselines3","Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.","stable-baselines3",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/stable-baselines3/SKILL.md",[3036,3037,3038,3039,3041,3043,3045,3047],{"path":287,"priority":288},{"path":350,"priority":291},{"path":2566,"priority":291},{"path":3040,"priority":291},"references/custom_environments.md",{"path":3042,"priority":291},"references/vectorized_envs.md",{"path":3044,"priority":357},"scripts/custom_env_template.py",{"path":3046,"priority":357},"scripts/evaluate_agent.py",{"path":3048,"priority":357},"scripts/train_rl_agent.py",{"basePath":3050,"description":3051,"displayName":3052,"installMethods":3053,"rationale":3054,"selectedPaths":3055,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/statistical-analysis","Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for your data, assumption checking, power analysis, and APA-formatted results. Best for academic research reporting, test selection guidance. For implementing specific models programmatically use statsmodels.","statistical-analysis",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/statistical-analysis/SKILL.md",[3056,3057,3059,3061,3063,3064,3066],{"path":287,"priority":288},{"path":3058,"priority":291},"references/assumptions_and_diagnostics.md",{"path":3060,"priority":291},"references/bayesian_statistics.md",{"path":3062,"priority":291},"references/effect_sizes_and_power.md",{"path":2154,"priority":291},{"path":3065,"priority":291},"references/test_selection_guide.md",{"path":3067,"priority":357},"scripts/assumption_checks.py",{"basePath":3069,"description":3070,"displayName":3071,"installMethods":3072,"rationale":3073,"selectedPaths":3074,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/statsmodels","Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.","statsmodels",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/statsmodels/SKILL.md",[3075,3076,3078,3080,3082,3084],{"path":287,"priority":288},{"path":3077,"priority":291},"references/discrete_choice.md",{"path":3079,"priority":291},"references/glm.md",{"path":3081,"priority":291},"references/linear_models.md",{"path":3083,"priority":291},"references/stats_diagnostics.md",{"path":3085,"priority":291},"references/time_series.md",{"basePath":3087,"description":3088,"displayName":3089,"installMethods":3090,"rationale":3091,"selectedPaths":3092,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/sympy","Use this skill when working with symbolic mathematics in Python. This skill should be used for symbolic computation tasks including solving equations algebraically, performing calculus operations (derivatives, integrals, limits), manipulating algebraic expressions, working with matrices symbolically, physics calculations, number theory problems, geometry computations, and generating executable code from mathematical expressions. Apply this skill when the user needs exact symbolic results rather than numerical approximations, or when working with mathematical formulas that contain variables and parameters.","sympy",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/sympy/SKILL.md",[3093,3094,3096,3098,3100,3102],{"path":287,"priority":288},{"path":3095,"priority":291},"references/advanced-topics.md",{"path":3097,"priority":291},"references/code-generation-printing.md",{"path":3099,"priority":291},"references/core-capabilities.md",{"path":3101,"priority":291},"references/matrices-linear-algebra.md",{"path":3103,"priority":291},"references/physics-mechanics.md",{"basePath":3105,"description":3106,"displayName":3107,"installMethods":3108,"rationale":3109,"selectedPaths":3110,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/tiledbvcf","Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF/BCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.","tiledbvcf",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/tiledbvcf/SKILL.md",[3111],{"path":287,"priority":288},{"basePath":3113,"description":3114,"displayName":3115,"installMethods":3116,"rationale":3117,"selectedPaths":3118,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/timesfm-forecasting","Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.","timesfm-forecasting",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/timesfm-forecasting/SKILL.md",[3119,3120,3122,3124,3126,3128,3130,3132,3134,3136,3138,3140,3142,3144,3146,3148,3150,3152,3154,3156,3158,3160,3162,3163,3165,3167,3169],{"path":287,"priority":288},{"path":3121,"priority":357},"examples/anomaly-detection/detect_anomalies.py",{"path":3123,"priority":357},"examples/anomaly-detection/output/anomaly_detection.json",{"path":3125,"priority":357},"examples/anomaly-detection/output/anomaly_detection.png",{"path":3127,"priority":357},"examples/covariates-forecasting/demo_covariates.py",{"path":3129,"priority":357},"examples/covariates-forecasting/output/covariates_data.png",{"path":3131,"priority":357},"examples/covariates-forecasting/output/covariates_metadata.json",{"path":3133,"priority":357},"examples/covariates-forecasting/output/sales_with_covariates.csv",{"path":3135,"priority":357},"examples/global-temperature/README.md",{"path":3137,"priority":357},"examples/global-temperature/generate_animation_data.py",{"path":3139,"priority":357},"examples/global-temperature/generate_gif.py",{"path":3141,"priority":357},"examples/global-temperature/generate_html.py",{"path":3143,"priority":357},"examples/global-temperature/output/animation_data.json",{"path":3145,"priority":357},"examples/global-temperature/output/forecast_animation.gif",{"path":3147,"priority":357},"examples/global-temperature/output/forecast_output.csv",{"path":3149,"priority":357},"examples/global-temperature/output/forecast_output.json",{"path":3151,"priority":357},"examples/global-temperature/output/forecast_visualization.png",{"path":3153,"priority":357},"examples/global-temperature/output/interactive_forecast.html",{"path":3155,"priority":357},"examples/global-temperature/run_example.sh",{"path":3157,"priority":357},"examples/global-temperature/run_forecast.py",{"path":3159,"priority":357},"examples/global-temperature/temperature_anomaly.csv",{"path":3161,"priority":357},"examples/global-temperature/visualize_forecast.py",{"path":898,"priority":291},{"path":3164,"priority":291},"references/data_preparation.md",{"path":3166,"priority":291},"references/system_requirements.md",{"path":3168,"priority":357},"scripts/check_system.py",{"path":3170,"priority":357},"scripts/forecast_csv.py",{"basePath":3172,"description":3173,"displayName":3174,"installMethods":3175,"rationale":3176,"selectedPaths":3177,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/torch-geometric","Guide for building Graph Neural Networks with PyTorch Geometric (PyG). Use this skill whenever the user asks about graph neural networks, GNNs, node classification, link prediction, graph classification, message passing networks, heterogeneous graphs, neighbor sampling, or any task involving torch_geometric / PyG. Also trigger when you see imports from torch_geometric, or the user mentions graph convolutions (GCN, GAT, GraphSAGE, GIN), graph data structures, or working with relational/network data. Even if the user just says 'graph learning' or 'geometric deep learning', use this skill.","torch-geometric",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/torch-geometric/SKILL.md",[3178,3179,3181,3183,3185,3187,3189],{"path":287,"priority":288},{"path":3180,"priority":291},"references/custom_datasets.md",{"path":3182,"priority":291},"references/explainability.md",{"path":3184,"priority":291},"references/heterogeneous.md",{"path":3186,"priority":291},"references/link_prediction.md",{"path":3188,"priority":291},"references/message_passing.md",{"path":1835,"priority":291},{"basePath":3191,"description":3192,"displayName":3193,"installMethods":3194,"rationale":3195,"selectedPaths":3196,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/torchdrug","PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem; for benchmark datasets use pytdc.","torchdrug",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/torchdrug/SKILL.md",[3197,3198,3199,3200,3202,3204,3206,3208,3210],{"path":287,"priority":288},{"path":2200,"priority":291},{"path":2406,"priority":291},{"path":3201,"priority":291},"references/knowledge_graphs.md",{"path":3203,"priority":291},"references/models_architectures.md",{"path":3205,"priority":291},"references/molecular_generation.md",{"path":3207,"priority":291},"references/molecular_property_prediction.md",{"path":3209,"priority":291},"references/protein_modeling.md",{"path":3211,"priority":291},"references/retrosynthesis.md",{"basePath":3213,"description":3214,"displayName":3215,"installMethods":3216,"rationale":3217,"selectedPaths":3218,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/transformers","This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.","transformers",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/transformers/SKILL.md",[3219,3220,3222,3223,3225,3226],{"path":287,"priority":288},{"path":3221,"priority":291},"references/generation.md",{"path":2412,"priority":291},{"path":3224,"priority":291},"references/pipelines.md",{"path":1375,"priority":291},{"path":2358,"priority":291},{"basePath":3228,"description":3229,"displayName":3230,"installMethods":3231,"rationale":3232,"selectedPaths":3233,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/treatment-plans","Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.","treatment-plans",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/treatment-plans/SKILL.md",[3234,3235,3237,3239,3241,3243,3245,3247,3249,3251,3252,3254,3255,3257,3259,3260,3262,3264,3266,3267,3268,3270,3272],{"path":287,"priority":288},{"path":3236,"priority":357},"assets/STYLING_QUICK_REFERENCE.md",{"path":3238,"priority":357},"assets/chronic_disease_management_plan.tex",{"path":3240,"priority":357},"assets/general_medical_treatment_plan.tex",{"path":3242,"priority":357},"assets/medical_treatment_plan.sty",{"path":3244,"priority":357},"assets/mental_health_treatment_plan.tex",{"path":3246,"priority":357},"assets/one_page_treatment_plan.tex",{"path":3248,"priority":357},"assets/pain_management_plan.tex",{"path":3250,"priority":357},"assets/perioperative_care_plan.tex",{"path":623,"priority":357},{"path":3253,"priority":357},"assets/rehabilitation_treatment_plan.tex",{"path":571,"priority":291},{"path":3256,"priority":291},"references/goal_setting_frameworks.md",{"path":3258,"priority":291},"references/intervention_guidelines.md",{"path":644,"priority":291},{"path":3261,"priority":291},"references/specialty_specific_guidelines.md",{"path":3263,"priority":291},"references/treatment_plan_standards.md",{"path":3265,"priority":357},"scripts/check_completeness.py",{"path":539,"priority":357},{"path":541,"priority":357},{"path":3269,"priority":357},"scripts/generate_template.py",{"path":3271,"priority":357},"scripts/timeline_generator.py",{"path":3273,"priority":357},"scripts/validate_treatment_plan.py",{"basePath":3275,"description":3276,"displayName":3277,"installMethods":3278,"rationale":3279,"selectedPaths":3280,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/umap-learn","UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.","umap-learn",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/umap-learn/SKILL.md",[3281,3282],{"path":287,"priority":288},{"path":898,"priority":291},{"basePath":3284,"description":3285,"displayName":3286,"installMethods":3287,"rationale":3288,"selectedPaths":3289,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/usfiscaldata","Query the U.S. Treasury Fiscal Data API for federal financial data including national debt, government spending, revenue, interest rates, exchange rates, and savings bonds. Access 54 datasets and 182 data tables with no API key required. Use when working with U.S. federal fiscal data, national debt tracking (Debt to the Penny), Daily Treasury Statements, Monthly Treasury Statements, Treasury securities auctions, interest rates on Treasury securities, foreign exchange rates, savings bonds, or any U.S. government financial statistics.","usfiscaldata",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/usfiscaldata/SKILL.md",[3290,3291,3293,3295,3297,3299,3301,3302,3303],{"path":287,"priority":288},{"path":3292,"priority":291},"references/api-basics.md",{"path":3294,"priority":291},"references/datasets-debt.md",{"path":3296,"priority":291},"references/datasets-fiscal.md",{"path":3298,"priority":291},"references/datasets-interest-rates.md",{"path":3300,"priority":291},"references/datasets-securities.md",{"path":1823,"priority":291},{"path":1213,"priority":291},{"path":3304,"priority":291},"references/response-format.md",{"basePath":3306,"description":3307,"displayName":3308,"installMethods":3309,"rationale":3310,"selectedPaths":3311,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/vaex","Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.","vaex",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/vaex/SKILL.md",[3312,3313,3315,3317,3318,3319,3321],{"path":287,"priority":288},{"path":3314,"priority":291},"references/core_dataframes.md",{"path":3316,"priority":291},"references/data_processing.md",{"path":338,"priority":291},{"path":2110,"priority":291},{"path":3320,"priority":291},"references/performance.md",{"path":1143,"priority":291},{"basePath":3323,"description":3324,"displayName":3325,"installMethods":3326,"rationale":3327,"selectedPaths":3328,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/venue-templates","Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.","venue-templates",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/venue-templates/SKILL.md",[3329,3330,3332,3334,3336,3338,3340,3342,3344,3346,3348,3350,3352,3354,3356,3358,3360,3362,3364,3366,3368,3370,3372,3374,3375,3376,3378],{"path":287,"priority":288},{"path":3331,"priority":357},"assets/examples/cell_summary_example.md",{"path":3333,"priority":357},"assets/examples/medical_structured_abstract.md",{"path":3335,"priority":357},"assets/examples/nature_abstract_examples.md",{"path":3337,"priority":357},"assets/examples/neurips_introduction_example.md",{"path":3339,"priority":357},"assets/grants/nih_specific_aims.tex",{"path":3341,"priority":357},"assets/grants/nsf_proposal_template.tex",{"path":3343,"priority":357},"assets/journals/nature_article.tex",{"path":3345,"priority":357},"assets/journals/neurips_article.tex",{"path":3347,"priority":357},"assets/journals/plos_one.tex",{"path":3349,"priority":357},"assets/posters/beamerposter_academic.tex",{"path":3351,"priority":291},"references/cell_press_style.md",{"path":3353,"priority":291},"references/conferences_formatting.md",{"path":3355,"priority":291},"references/cs_conference_style.md",{"path":3357,"priority":291},"references/grants_requirements.md",{"path":3359,"priority":291},"references/journals_formatting.md",{"path":3361,"priority":291},"references/medical_journal_styles.md",{"path":3363,"priority":291},"references/ml_conference_style.md",{"path":3365,"priority":291},"references/nature_science_style.md",{"path":3367,"priority":291},"references/posters_guidelines.md",{"path":3369,"priority":291},"references/reviewer_expectations.md",{"path":3371,"priority":291},"references/venue_writing_styles.md",{"path":3373,"priority":357},"scripts/customize_template.py",{"path":539,"priority":357},{"path":541,"priority":357},{"path":3377,"priority":357},"scripts/query_template.py",{"path":3379,"priority":357},"scripts/validate_format.py",{"basePath":3381,"description":3382,"displayName":3383,"installMethods":3384,"rationale":3385,"selectedPaths":3386,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/what-if-oracle","Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like \"what if...\", \"what would happen if...\", \"what are the possibilities\", \"explore scenarios\", \"scenario analysis\", \"possibility space\", \"what could go wrong\", \"best case / worst case\", \"risk analysis\", \"contingency planning\", \"strategic options\", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.","what-if-oracle",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/what-if-oracle/SKILL.md",[3387,3388],{"path":287,"priority":288},{"path":3389,"priority":291},"references/scenario-templates.md",{"basePath":3391,"description":3392,"displayName":3393,"installMethods":3394,"rationale":3395,"selectedPaths":3396,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/xlsx","Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.","xlsx",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/xlsx/SKILL.md",[3397,3398,3399,3400,3401,3402,3403,3404,3405,3406,3407,3408,3409,3410,3411,3412,3413,3414,3415,3416,3417,3418,3419,3420,3421,3422,3423,3424,3425,3426,3427,3428,3429,3430,3431,3432,3433,3434,3435,3436,3437,3438,3439,3440,3441,3442,3443,3444,3445,3446,3447,3448,3449,3450],{"path":287,"priority":288},{"path":998,"priority":999},{"path":1007,"priority":357},{"path":1009,"priority":357},{"path":1011,"priority":357},{"path":1013,"priority":357},{"path":1015,"priority":357},{"path":1017,"priority":357},{"path":1019,"priority":357},{"path":1021,"priority":357},{"path":1023,"priority":357},{"path":1025,"priority":357},{"path":1027,"priority":357},{"path":1029,"priority":357},{"path":1031,"priority":357},{"path":1033,"priority":357},{"path":1035,"priority":357},{"path":1037,"priority":357},{"path":1039,"priority":357},{"path":1041,"priority":357},{"path":1043,"priority":357},{"path":1045,"priority":357},{"path":1047,"priority":357},{"path":1049,"priority":357},{"path":1051,"priority":357},{"path":1053,"priority":357},{"path":1055,"priority":357},{"path":1057,"priority":357},{"path":1059,"priority":357},{"path":1061,"priority":357},{"path":1063,"priority":357},{"path":1065,"priority":357},{"path":1067,"priority":357},{"path":1069,"priority":357},{"path":1071,"priority":357},{"path":1073,"priority":357},{"path":1075,"priority":357},{"path":1077,"priority":357},{"path":1079,"priority":357},{"path":1081,"priority":357},{"path":1083,"priority":357},{"path":1085,"priority":357},{"path":1087,"priority":357},{"path":1089,"priority":357},{"path":1091,"priority":357},{"path":1093,"priority":357},{"path":1095,"priority":357},{"path":1097,"priority":357},{"path":1099,"priority":357},{"path":1101,"priority":357},{"path":1103,"priority":357},{"path":1105,"priority":357},{"path":1107,"priority":357},{"path":3451,"priority":357},"scripts/recalc.py",{"basePath":3453,"description":3454,"displayName":3455,"installMethods":3456,"rationale":3457,"selectedPaths":3458,"source":292,"sourceLanguage":18,"type":263},"scientific-skills/zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.","zarr-python",{"claudeCode":12},"SKILL.md frontmatter at scientific-skills/zarr-python/SKILL.md",[3459,3460],{"path":287,"priority":288},{"path":898,"priority":291},{"sources":3462},[3463],"manual",{"closedIssues90d":8,"description":3465,"forks":249,"homepage":3466,"license":255,"openIssues90d":8,"pushedAt":252,"readmeSize":246,"stars":253,"topics":3467},"A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.","https://k-dense.ai",[3468,3469,3470,3471,3472,3473,3474,3475,3476,3477,3478,3479,3480,3481,3482,2841,3483],"ai-scientist","bioinformatics","chemoinformatics","claude","claude-skills","claudecode","clinical-research","computational-biology","data-analysis","drug-discovery","genomics","materials-science","metabolomics","proteomics","scientific-computing","agent-skills",{"classifiedAt":3485,"discoverAt":3486,"extractAt":3487,"githubAt":3487,"updatedAt":3485},1778691799051,1778691790211,1778691796670,[225,223,224,222,221,226],{"evaluatedAt":258,"extractAt":3490,"updatedAt":258},1778691799740,[],[3493,3510,3537,3557,3574,3605],{"_creationTime":3494,"_id":3495,"community":3496,"display":3497,"identity":3499,"providers":3500,"relations":3506,"tags":3507,"workflow":3508},1778691799740.4697,"k17fd9k52qh0ew0frj32e1jab986mebd",{"reviewCount":8},{"description":492,"installMethods":3498,"name":493,"sourceUrl":14},{"claudeCode":12},{"basePath":491,"githubOwner":261,"githubRepo":262,"locale":18,"slug":493,"type":263},{"evaluate":3501,"extract":3505},{"promptVersionExtension":214,"promptVersionScoring":215,"score":3502,"tags":3503,"targetMarket":227,"tier":228},98,[221,493,3504,226,225],"google-ai",{"commitSha":269},{"repoId":272},[225,493,3504,221,226],{"evaluatedAt":3509,"extractAt":3490,"updatedAt":3509},1778692112906,{"_creationTime":3511,"_id":3512,"community":3513,"display":3514,"identity":3520,"providers":3525,"relations":3531,"tags":3533,"workflow":3534},1778675145461.872,"k1781ky6fcd8hgbsnh1x18qjzx86mqqv",{"reviewCount":8},{"description":3515,"installMethods":3516,"name":3518,"sourceUrl":3519},"Part of the AlterLab Academic Skills suite. Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.",{"claudeCode":3517},"AlterLab-IEU/AlterLab-Academic-Skills","Cirq - Quantum Computing with Python","https://github.com/AlterLab-IEU/AlterLab-Academic-Skills",{"basePath":3521,"githubOwner":3522,"githubRepo":3523,"locale":18,"slug":3524,"type":263},"skills/domain-specific/alterlab-cirq","AlterLab-IEU","AlterLab-Academic-Skills","alterlab-cirq",{"evaluate":3526,"extract":3530},{"promptVersionExtension":214,"promptVersionScoring":215,"score":3502,"tags":3527,"targetMarket":227,"tier":228},[221,493,3528,225,226,3529],"google-quantum-ai","noise-modeling",{"commitSha":269,"license":270},{"repoId":3532},"kd7fqvj70pvyn4r3q9kctpnd7d86mfqd",[225,493,3528,3529,221,226],{"evaluatedAt":3535,"extractAt":3536,"updatedAt":3535},1778678194572,1778675145461,{"_creationTime":3538,"_id":3539,"community":3540,"display":3541,"identity":3545,"providers":3547,"relations":3553,"tags":3554,"workflow":3555},1778675145461.8748,"k173e8xqsfkjjbf4v3pqr0xs1d86n9aa",{"reviewCount":8},{"description":3542,"installMethods":3543,"name":3544,"sourceUrl":3519},"Part of the AlterLab Academic Skills suite. IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools. Best for IBM hardware execution, quantum error mitigation, and enterprise quantum computing. For Google hardware use cirq; for gradient-based quantum ML use pennylane; for open quantum system simulations use qutip.",{"claudeCode":3517},"alterlab-qiskit",{"basePath":3546,"githubOwner":3522,"githubRepo":3523,"locale":18,"slug":3544,"type":263},"skills/domain-specific/alterlab-qiskit",{"evaluate":3548,"extract":3552},{"promptVersionExtension":214,"promptVersionScoring":215,"score":3549,"tags":3550,"targetMarket":227,"tier":228},95,[221,222,223,224,3551],"research",{"commitSha":269},{"repoId":3532},[223,224,222,221,3551],{"evaluatedAt":3556,"extractAt":3536,"updatedAt":3556},1778678515896,{"_creationTime":3558,"_id":3559,"community":3560,"display":3561,"identity":3563,"providers":3564,"relations":3570,"tags":3571,"workflow":3572},1778691799740.4912,"k17etggmf4x0zmxk39h969809d86naj3",{"reviewCount":8},{"description":2636,"installMethods":3562,"name":2637,"sourceUrl":14},{"claudeCode":12},{"basePath":2635,"githubOwner":261,"githubRepo":262,"locale":18,"slug":2637,"type":263},{"evaluate":3565,"extract":3569},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":3566,"targetMarket":227,"tier":228},[3567,221,226,3568,224],"physics","open-systems",{"commitSha":269},{"repoId":272},[3568,3567,224,221,226],{"evaluatedAt":3573,"extractAt":3490,"updatedAt":3573},1778694022295,{"_creationTime":3575,"_id":3576,"community":3577,"display":3578,"identity":3584,"providers":3588,"relations":3598,"tags":3601,"workflow":3602},1778699018122.8064,"k178yxvt3g9djb8ph907q3tv1186n8ex",{"reviewCount":8},{"description":3579,"installMethods":3580,"name":3582,"sourceUrl":3583},"Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.",{"claudeCode":3581},"wshobson/agents","embedding-strategies","https://github.com/wshobson/agents",{"basePath":3585,"githubOwner":3586,"githubRepo":3587,"locale":18,"slug":3582,"type":263},"plugins/llm-application-dev/skills/embedding-strategies","wshobson","agents",{"evaluate":3589,"extract":3597},{"promptVersionExtension":214,"promptVersionScoring":215,"score":3590,"tags":3591,"targetMarket":227,"tier":228},100,[3592,3593,3594,3595,3596,224],"embeddings","rag","semantic-search","vector-databases","llm-applications",{"commitSha":269},{"parentExtensionId":3599,"repoId":3600},"k1719fyk9jrke6aq23wbyf8ej586n3af","kd74de64zj0axtg5b8t7eqqe2x86nske",[3592,3596,224,3593,3594,3595],{"evaluatedAt":3603,"extractAt":3604,"updatedAt":3603},1778701750946,1778699018122,{"_creationTime":3606,"_id":3607,"community":3608,"display":3609,"identity":3615,"providers":3620,"relations":3630,"tags":3634,"workflow":3635},1778699887554.4724,"k171fhjffw07a0a511s1v1hqsh86m9gz",{"reviewCount":8},{"description":3610,"installMethods":3611,"name":3613,"sourceUrl":3614},"AWS Cloud Development Kit (CDK) 专家，用于使用 TypeScript/Python 构建云基础设施。在创建 CDK 堆栈、定义 CDK 构造、实现基础设施即代码，或当用户提及 CDK、CloudFormation、IaC、cdk synth、cdk deploy，或希望以编程方式定义 AWS 基础设施时使用。涵盖 CDK 应用结构、构造模式、堆栈组合和部署工作流。",{"claudeCode":3612},"zxkane/aws-skills","aws-cdk-development","https://github.com/zxkane/aws-skills",{"basePath":3616,"githubOwner":3617,"githubRepo":3618,"locale":3619,"slug":3613,"type":263},"plugins/aws-cdk/skills/aws-cdk-development","zxkane","aws-skills","zh-CN",{"evaluate":3621,"extract":3629},{"promptVersionExtension":214,"promptVersionScoring":215,"score":3590,"tags":3622,"targetMarket":227,"tier":228},[3623,3624,3625,224,3626,3627,3628],"aws","cdk","typescript","iac","cloudformation","infrastructure",{"commitSha":269},{"parentExtensionId":3631,"repoId":3632,"translatedFrom":3633},"k177paz2fgaa1r1kfhgb2esr1n86my7m","kd7708aervxaq6vqq9tdf93s2586mcqy","k174bzyyax9v1t5bm0m98bfqyh86m8v8",[3623,3624,3627,3626,3628,224,3625],{"evaluatedAt":3636,"extractAt":3637,"updatedAt":3638},1778699774404,1778699647844,1778699887554]