[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-lllllllama-minimal-run-and-audit-en":3,"guides-for-lllllllama-minimal-run-and-audit":502,"similar-k1718b6r9230y7ft3t8gkmsg2986my9z-en":503},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":245,"isFallback":230,"parentExtension":250,"providers":251,"relations":256,"repo":258,"tags":498,"workflow":499},1778692396032.778,"k1718b6r9230y7ft3t8gkmsg2986my9z",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Trusted-lane execution and reporting skill for README-first AI repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, or end-to-end orchestration by itself.",{"claudeCode":12},"lllllllama/ai-paper-reproduction-skill","minimal-run-and-audit","https://github.com/lllllllama/ai-paper-reproduction-skill",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":228,"workflow":243},1778692567369.054,"kn70jt2f7ctn61x11k41vyzvxs86n9at","en",{"checks":20,"evaluatedAt":195,"extensionSummary":196,"features":197,"nonGoals":203,"promptVersionExtension":209,"promptVersionScoring":210,"purpose":211,"rationale":212,"score":213,"summary":214,"tags":215,"targetMarket":221,"tier":222,"useCases":223},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,103,107,110,113,116,120,123,126,129,132,135,138,142,146,150,153,157,160,163,166,169,173,176,179,182,185,188,192],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of reproducing AI research artifacts from READMEs and names the target user (teams maintaining AI research workflows).",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill provides a specialized workflow for AI repo reproduction and evidence normalization, going beyond generic LLM capabilities by focusing on specific output formats and trusted execution lanes.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill bundle appears complete for its stated purpose of capturing and normalizing execution evidence, with documented scripts and a clear reporting policy.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill `minimal-run-and-audit` focuses specifically on capturing and normalizing evidence from documented commands, fitting within the broader AI research workflow without overlapping unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's purpose of trusted-lane execution and reporting for AI repo reproduction, including clear use cases and non-goals.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This skill appears to be a single-purpose entry point and does not expose multiple tools. The core logic is likely within the `run_command.py` script.",{"category":45,"check":46,"severity":24,"summary":47},"Documentation","Configuration & parameter reference","The skill's operational parameters (repo, command, timeout) are clearly defined via its argument parser in `run_command.py` and documented within the SKILL.md and README.",{"category":33,"check":49,"severity":24,"summary":50},"Tool naming","The primary entrypoint is well-named (`minimal-run-and-audit`) and its associated script (`run_command.py`) is descriptive of its function.",{"category":33,"check":52,"severity":24,"summary":53},"Minimal I/O surface","The `run_command.py` script captures specific execution details (return code, stdout, stderr, file changes) relevant to its purpose without excessive diagnostic dumps.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The repository is licensed under the MIT license, which is a permissive open-source license and clearly indicated in the LICENSE file.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The latest commit was on May 9, 2026, which is within the last 90 days, indicating active maintenance.",{"category":59,"check":63,"severity":42,"summary":64},"Dependency Management","The provided scripts appear to use standard Python libraries and git, with no explicit third-party dependencies that would require complex management.",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","The script `run_command.py` executes a provided command within a repository context and does not appear to handle or expose secrets.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The `run_command.py` script uses `shlex.split` to parse commands and subprocess to execute them, mitigating direct injection risks. Git commands are also handled safely.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The script executes local commands and git operations within the repository context and does not fetch external code or data at runtime.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The script operates within the provided repository path and its primary actions are executing commands and capturing git status, staying within expected boundaries.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","The Python script uses standard `subprocess.run` and does not appear to employ detached processes or retry loops around denied calls.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The script focuses on capturing local execution output and git status; it does not appear to read or submit confidential data to any third party.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled scripts and SKILL.md files appear to be free of hidden text tricks or obfuscation designed to mislead the model.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The Python script is plain, readable source code and does not involve obfuscation, base64 decoding, or runtime script fetching.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The script operates within a specified repository path and handles git status relative to that path, making no broad assumptions about user project structure.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","With 0 issues opened and 0 issues closed in the last 90 days, the maintainer engagement is not indicative of neglect.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","While there isn't a semver in the SKILL.md frontmatter or GitHub releases, the installation instructions reference a specific commit/tag implicitly via the repo URL, and there is a CHANGELOG.md.",{"category":104,"check":105,"severity":24,"summary":106},"Code Execution","Validation","The `run_command.py` script uses `shlex.split` for command parsing and `subprocess.run` for execution, with explicit timeouts, providing a basic level of input validation.",{"category":66,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","The script's main function is to execute a given command and report its output/status; it does not contain inherently destructive operations like `rm -rf`.",{"category":104,"check":111,"severity":24,"summary":112},"Error Handling","The `run_command.py` script explicitly handles `FileNotFoundError`, `subprocess.TimeoutExpired`, and non-zero return codes, providing structured output and logging.",{"category":104,"check":114,"severity":24,"summary":115},"Logging","The script captures stdout, stderr, and git status, which serves as an audit log of the executed command's outcome and file system changes.",{"category":117,"check":118,"severity":42,"summary":119},"Compliance","GDPR","The skill does not operate on personal data; it executes commands within a code repository and captures output and file status.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The skill operates on code repositories and standard command execution, with no regional or jurisdictional limitations detected; targetMarket is 'global'.",{"category":92,"check":124,"severity":24,"summary":125},"Runtime stability","The script uses standard Python 3 and subprocess, making it compatible with common POSIX environments and Windows PowerShell.",{"category":45,"check":127,"severity":24,"summary":128},"README","The README.md file is comprehensive, explaining the repository's purpose, installation, skills, and usage.",{"category":33,"check":130,"severity":42,"summary":131},"Tool surface size","This is a single-purpose skill, not a collection of multiple tools.",{"category":40,"check":133,"severity":42,"summary":134},"Overlapping near-synonym tools","This skill appears to be a single entry point and does not expose multiple distinct tools with overlapping functionality.",{"category":45,"check":136,"severity":24,"summary":137},"Phantom features","The described functionality for executing and reporting on commands is directly implemented in the `run_command.py` script and associated documentation.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","The README provides clear `npx skills add` instructions and copy-pasteable examples for installing and invoking the skill.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","Errors like command not found, timeouts, and non-zero exit codes are clearly reported with context and remediation hints like 'command failed before launch' or timeout durations.",{"category":147,"check":148,"severity":24,"summary":149},"Execution","Pinned dependencies","The Python script uses standard library features and `subprocess`, and the shebang `#!/usr/bin/env python3` indicates the interpreter, providing clarity on execution environment.",{"category":33,"check":151,"severity":42,"summary":152},"Dry-run preview","The skill's primary function is to execute a command and report its output, not to perform state-changing operations that would require a dry-run mode.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The script enforces a hard timeout and returns a structured error on expiry, and its core operation of running a command is inherently restartable.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The script captures local execution data and git status for audit purposes; there is no indication of outbound telemetry being sent.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The skill's purpose is precisely defined for executing documented commands and normalizing evidence, with clear boundaries against training or initial setup.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The SKILL.md frontmatter is concise, providing a clear summary of the skill's purpose and key usage scenarios.",{"category":45,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md body is reasonably concise, outlining principles and usage without excessive inline detail, relying on references for deeper material.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md references other markdown files like `agent-operating-principles.md` and `reporting-policy.md` for deeper information.",{"category":170,"check":174,"severity":42,"summary":175},"Forked exploration","This skill is not an exploration-heavy skill; it executes a specific command and reports on it, so `context: fork` is not applicable.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The README provides example prompts for trusted reproduction, which align with the functionality of `minimal-run-and-audit`.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The script handles command not found, timeouts, and non-zero exit codes, documenting these failure modes and recovery paths.",{"category":104,"check":183,"severity":42,"summary":184},"Tool Fallback","This skill does not appear to rely on external tools like an MCP server; it uses standard Python and subprocess.",{"category":92,"check":186,"severity":24,"summary":187},"Stack assumptions","The shebang `#!/usr/bin/env python3` and use of standard libraries indicate broad portability across POSIX-like systems and Windows PowerShell.",{"category":189,"check":190,"severity":24,"summary":191},"Safety","Halt on unexpected state","The script explicitly checks for errors like command not found or timeouts and reports them, halting execution and reporting the state.",{"category":92,"check":193,"severity":24,"summary":194},"Cross-skill coupling","The skill is self-contained and focuses on executing a command and reporting results, without implicit reliance on other skills.",1778692567260,"This skill executes specified commands within a given repository, captures their output (stdout, stderr), return codes, and file system changes (via git status), and normalizes this information into a structured JSON payload. It handles command not found errors, timeouts, and non-zero exit codes, providing auditable evidence for research reproduction.",[198,199,200,201,202],"Trusted execution lane for AI repo reproduction","Captures command output, errors, and file changes","Generates standardized `repro_outputs/` files","Handles execution timeouts and non-zero exit codes","Supports patch notes when repository files change",[204,205,206,207,208],"Initial repo scanning or intake","Generic environment setup","Paper lookup or target selection","End-to-end orchestration by itself","Training execution or state management","3.0.0","4.4.0","To provide a trusted and auditable way to execute and report on documented commands in AI research repositories, ensuring evidence is captured consistently for reproduction.","All checks passed, indicating a high-quality, well-documented, and secure skill.",100,"A robust skill for auditable execution and reporting of commands within AI research repositories.",[216,217,218,219,220],"reproduction","testing","reporting","code-execution","evidence-capture","global","verified",[224,225,226,227],"Verifying documented inference or evaluation commands","Capturing evidence from smoke tests","Normalizing execution results for auditability","Reporting on repository file changes after command execution",{"codeQuality":229,"collectedAt":231,"documentation":232,"maintenance":235,"security":240,"testCoverage":242},{"hasLockfile":230},false,1778692549002,{"descriptionLength":233,"readmeSize":234},477,22701,{"closedIssues90d":8,"forks":236,"hasChangelog":237,"openIssues90d":8,"pushedAt":238,"stars":239},4,true,1778347974000,75,{"hasNpmPackage":230,"license":241,"smitheryVerified":230},"MIT",{"hasCi":237,"hasTests":237},{"updatedAt":244},1778692567369,{"basePath":246,"githubOwner":247,"githubRepo":248,"locale":18,"slug":13,"type":249},"skills/minimal-run-and-audit","lllllllama","ai-paper-reproduction-skill","skill",null,{"evaluate":252,"extract":254},{"promptVersionExtension":209,"promptVersionScoring":210,"score":213,"tags":253,"targetMarket":221,"tier":222},[216,217,218,219,220],{"commitSha":255},"HEAD",{"repoId":257},"kd7629v5mqesxwwe9w7qtfgp7d86n6re",{"_creationTime":259,"_id":257,"identity":260,"providers":261,"workflow":494},1778692391648.3123,{"githubOwner":247,"githubRepo":248,"sourceUrl":14},{"classify":262,"discover":488,"github":491},{"commitSha":255,"extensions":263},[264,341,371,383,403,416,429,439,449,463,476],{"basePath":265,"description":266,"displayName":267,"installMethods":268,"rationale":269,"selectedPaths":270,"source":340,"sourceLanguage":18,"type":249},"skills/ai-research-explore","Explore-lane end-to-end orchestrator for the third research scenario: the researcher has already chosen the task family, dataset, benchmark, evaluation method, and provided SOTA references, and wants candidate-only exploration on top of `current_research` with auditable repo understanding, idea gating, and governed experiments written to `explore_outputs/`. Do not use for README-first trusted reproduction, open-ended direction finding, narrow code-only or run-only exploration, passive repo analysis, or implicit experimentation.","ai-research-explore",{"claudeCode":12},"SKILL.md frontmatter at skills/ai-research-explore/SKILL.md",[271,274,277,279,281,283,285,287,290,292,294,296,298,300,302,304,306,308,310,312,314,316,318,320,322,324,326,328,330,332,334,336,338],{"path":272,"priority":273},"SKILL.md","mandatory",{"path":275,"priority":276},"references/ai-research-explore-policy.md","medium",{"path":278,"priority":276},"references/idea-evaluation-framework.md",{"path":280,"priority":276},"references/research-campaign-spec.md",{"path":282,"priority":276},"references/smoke-validation-policy.md",{"path":284,"priority":276},"references/source-mapping-policy.md",{"path":286,"priority":276},"references/sources-naming-policy.md",{"path":288,"priority":289},"scripts/lookup/__init__.py","low",{"path":291,"priority":289},"scripts/lookup/cache_store.py",{"path":293,"priority":289},"scripts/lookup/inventory_writer.py",{"path":295,"priority":289},"scripts/lookup/normalizers.py",{"path":297,"priority":289},"scripts/lookup/providers/__init__.py",{"path":299,"priority":289},"scripts/lookup/providers/arxiv_provider.py",{"path":301,"priority":289},"scripts/lookup/providers/base.py",{"path":303,"priority":289},"scripts/lookup/providers/doi_provider.py",{"path":305,"priority":289},"scripts/lookup/providers/github_provider.py",{"path":307,"priority":289},"scripts/lookup/providers/optional_provider.py",{"path":309,"priority":289},"scripts/lookup/providers/url_provider.py",{"path":311,"priority":289},"scripts/lookup/record_schema.py",{"path":313,"priority":289},"scripts/lookup/repo_extractors.py",{"path":315,"priority":289},"scripts/lookup/source_support.py",{"path":317,"priority":289},"scripts/orchestrate_explore.py",{"path":319,"priority":289},"scripts/passes/__init__.py",{"path":321,"priority":289},"scripts/passes/atomic_idea_decomposition.py",{"path":323,"priority":289},"scripts/passes/candidate_idea_generation.py",{"path":325,"priority":289},"scripts/passes/execution_feasibility.py",{"path":327,"priority":289},"scripts/passes/idea_cards.py",{"path":329,"priority":289},"scripts/passes/idea_ranking.py",{"path":331,"priority":289},"scripts/passes/implementation_fidelity.py",{"path":333,"priority":289},"scripts/passes/improvement_bank.py",{"path":335,"priority":289},"scripts/passes/lookup_sources.py",{"path":337,"priority":289},"scripts/passes/source_mapping.py",{"path":339,"priority":289},"scripts/write_outputs.py","rule",{"basePath":342,"description":343,"displayName":344,"installMethods":345,"rationale":346,"selectedPaths":347,"source":340,"sourceLanguage":18,"type":249},"skills/ai-research-reproduction","Main orchestrator for README-first AI repo reproduction. Use when the user wants an end-to-end, minimal-trustworthy reproduction flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted training, optional repository analysis, and optional paper-gap resolution, enforces conservative patch rules, records evidence assumptions deviations and human decision points, and writes the standardized `repro_outputs/` bundle. Do not use for paper summary, generic environment setup, isolated repo scanning, standalone command execution, silent protocol changes, or broad research assistance outside repository-grounded reproduction.","ai-research-reproduction",{"claudeCode":12},"SKILL.md frontmatter at skills/ai-research-reproduction/SKILL.md",[348,349,351,353,355,357,359,361,363,365,367,369],{"path":272,"priority":273},{"path":350,"priority":289},"assets/COMMANDS.template.md",{"path":352,"priority":289},"assets/LOG.template.md",{"path":354,"priority":289},"assets/PATCHES.template.md",{"path":356,"priority":289},"assets/SUMMARY.template.md",{"path":358,"priority":289},"assets/status.template.json",{"path":360,"priority":276},"references/architecture.md",{"path":362,"priority":276},"references/language-policy.md",{"path":364,"priority":276},"references/output-spec.md",{"path":366,"priority":276},"references/patch-policy.md",{"path":368,"priority":276},"references/research-safety-principles.md",{"path":370,"priority":289},"scripts/orchestrate_repro.py",{"basePath":372,"description":373,"displayName":374,"installMethods":375,"rationale":376,"selectedPaths":377,"source":340,"sourceLanguage":18,"type":249},"skills/analyze-project","Trusted-lane analysis skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrypoints, review configs and insertion points, or flag suspicious implementation patterns without modifying code or running heavy jobs. Do not use for active command execution, broad refactoring, speculative code adaptation, or automatic bug fixing.","analyze-project",{"claudeCode":12},"SKILL.md frontmatter at skills/analyze-project/SKILL.md",[378,379,381],{"path":272,"priority":273},{"path":380,"priority":276},"references/analysis-policy.md",{"path":382,"priority":289},"scripts/analyze_project.py",{"basePath":384,"description":385,"displayName":386,"installMethods":387,"rationale":388,"selectedPaths":389,"source":340,"sourceLanguage":18,"type":249},"skills/env-and-assets-bootstrap","Environment and assets sub-skill for README-first AI repo reproduction. Use when the task is specifically to prepare a conservative conda-first environment, checkpoint and dataset path assumptions, cache location hints, and setup notes before any run on a README-documented repository. Do not use for repo scanning, full orchestration, paper interpretation, final run reporting, or generic environment setup that is not tied to a specific reproduction target.","env-and-assets-bootstrap",{"claudeCode":12},"SKILL.md frontmatter at skills/env-and-assets-bootstrap/SKILL.md",[390,391,393,395,397,399,401],{"path":272,"priority":273},{"path":392,"priority":276},"references/assets-policy.md",{"path":394,"priority":276},"references/env-policy.md",{"path":396,"priority":289},"scripts/bootstrap_env.py",{"path":398,"priority":289},"scripts/bootstrap_env.sh",{"path":400,"priority":289},"scripts/plan_setup.py",{"path":402,"priority":289},"scripts/prepare_assets.py",{"basePath":404,"description":405,"displayName":406,"installMethods":407,"rationale":408,"selectedPaths":409,"source":340,"sourceLanguage":18,"type":249},"skills/explore-code","Explore-lane code adaptation skill for deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated branch or worktree to transplant modules, adapt a backbone, add LoRA or adapter layers, replace a head, or stitch together low-risk migration ideas with summary-only records in `explore_outputs/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted baseline reproduction, conservative debugging, environment setup, or default repository analysis.","explore-code",{"claudeCode":12},"SKILL.md frontmatter at skills/explore-code/SKILL.md",[410,411,413,415],{"path":272,"priority":273},{"path":412,"priority":276},"references/explore-policy.md",{"path":414,"priority":289},"scripts/plan_code_changes.py",{"path":339,"priority":289},{"basePath":417,"description":418,"displayName":419,"installMethods":420,"rationale":421,"selectedPaths":422,"source":340,"sourceLanguage":18,"type":249},"skills/explore-run","Explore-lane experimental execution skill for deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning trials, with results summarized in `explore_outputs/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted baseline execution, conservative training verification, default routing, or implicit experimentation.","explore-run",{"claudeCode":12},"SKILL.md frontmatter at skills/explore-run/SKILL.md",[423,424,426,428],{"path":272,"priority":273},{"path":425,"priority":276},"references/execution-policy.md",{"path":427,"priority":289},"scripts/plan_variants.py",{"path":339,"priority":289},{"basePath":246,"description":10,"displayName":13,"installMethods":430,"rationale":431,"selectedPaths":432,"source":340,"sourceLanguage":18,"type":249},{"claudeCode":12},"SKILL.md frontmatter at skills/minimal-run-and-audit/SKILL.md",[433,434,436,438],{"path":272,"priority":273},{"path":435,"priority":276},"references/reporting-policy.md",{"path":437,"priority":289},"scripts/run_command.py",{"path":339,"priority":289},{"basePath":440,"description":441,"displayName":442,"installMethods":443,"rationale":444,"selectedPaths":445,"source":340,"sourceLanguage":18,"type":249},"skills/paper-context-resolver","Optional narrow helper skill for README-first AI repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.","paper-context-resolver",{"claudeCode":12},"SKILL.md frontmatter at skills/paper-context-resolver/SKILL.md",[446,447],{"path":272,"priority":273},{"path":448,"priority":276},"references/paper-assisted-reproduction.md",{"basePath":450,"description":451,"displayName":452,"installMethods":453,"rationale":454,"selectedPaths":455,"source":340,"sourceLanguage":18,"type":249},"skills/repo-intake-and-plan","Narrow helper skill for README-first AI repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.","repo-intake-and-plan",{"claudeCode":12},"SKILL.md frontmatter at skills/repo-intake-and-plan/SKILL.md",[456,457,459,461],{"path":272,"priority":273},{"path":458,"priority":276},"references/repo-scan-rules.md",{"path":460,"priority":289},"scripts/extract_commands.py",{"path":462,"priority":289},"scripts/scan_repo.py",{"basePath":464,"description":465,"displayName":466,"installMethods":467,"rationale":468,"selectedPaths":469,"source":340,"sourceLanguage":18,"type":249},"skills/run-train","Trusted-lane training execution skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup verification, short-run verification, full kickoff, or resume, with status, checkpoint, and metric capture written to standardized `train_outputs/`. Do not use for environment setup, exploratory sweeps, speculative idea implementation, or end-to-end orchestration.","run-train",{"claudeCode":12},"SKILL.md frontmatter at skills/run-train/SKILL.md",[470,471,473,475],{"path":272,"priority":273},{"path":472,"priority":276},"references/training-policy.md",{"path":474,"priority":289},"scripts/run_training.py",{"path":339,"priority":289},{"basePath":477,"description":478,"displayName":479,"installMethods":480,"rationale":481,"selectedPaths":482,"source":340,"sourceLanguage":18,"type":249},"skills/safe-debug","Trusted-lane debug skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training failure and wants conservative diagnosis before any patching. Do not use for broad refactoring, speculative adaptation, automatic exploratory patching, or general repository familiarization.","safe-debug",{"claudeCode":12},"SKILL.md frontmatter at skills/safe-debug/SKILL.md",[483,484,486],{"path":272,"priority":273},{"path":485,"priority":276},"references/debug-policy.md",{"path":487,"priority":289},"scripts/safe_debug.py",{"sources":489},[490],"manual",{"closedIssues90d":8,"description":492,"forks":236,"license":241,"openIssues90d":8,"pushedAt":238,"readmeSize":234,"stars":239,"topics":493},"",[],{"classifiedAt":495,"discoverAt":496,"extractAt":497,"githubAt":497,"updatedAt":495},1778692395631,1778692391648,1778692393876,[219,220,218,216,217],{"evaluatedAt":244,"extractAt":500,"updatedAt":501},1778692396032,1778692750344,[],[504,537,567,596,623,652],{"_creationTime":505,"_id":506,"community":507,"display":508,"identity":514,"providers":519,"relations":529,"tags":532,"workflow":533},1778693511416.3665,"k17fqs996gpd2bggec9k1qbbns86nh4g",{"reviewCount":8},{"description":509,"installMethods":510,"name":512,"sourceUrl":513},"Update context-mode from GitHub and fix hooks/settings.\nPulls latest, builds, installs, updates npm global, configures hooks.\nTrigger: /context-mode:ctx-upgrade\n",{"claudeCode":511},"mksglu/context-mode","Context Mode","https://github.com/mksglu/context-mode",{"basePath":515,"githubOwner":516,"githubRepo":517,"locale":18,"slug":518,"type":249},"skills/ctx-upgrade","mksglu","context-mode","ctx-upgrade",{"evaluate":520,"extract":527},{"promptVersionExtension":209,"promptVersionScoring":210,"score":213,"tags":521,"targetMarket":221,"tier":222},[522,523,219,524,525,526],"context-management","llm-ops","session-continuity","productivity","mcp",{"commitSha":255,"license":528},"NOASSERTION",{"parentExtensionId":530,"repoId":531},"k17ezy748es7sfnbnp9phht43h86m53y","kd764b2fctbqg4b8j8y6xvmkvs86m29m",[219,522,523,526,525,524],{"evaluatedAt":534,"extractAt":535,"updatedAt":536},1778693713738,1778693511416,1778693818462,{"_creationTime":538,"_id":539,"community":540,"display":541,"identity":547,"providers":552,"relations":561,"tags":563,"workflow":564},1778696691708.3035,"k17br1j5s86ae90zqeyd7zcg2586mkwr",{"reviewCount":8},{"description":542,"installMethods":543,"name":545,"sourceUrl":546},"Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms\n",{"claudeCode":544},"ruvnet/ruflo","Performance Analysis","https://github.com/ruvnet/ruflo",{"basePath":548,"githubOwner":549,"githubRepo":550,"locale":18,"slug":551,"type":249},".claude/skills/performance-analysis","ruvnet","ruflo","performance-analysis",{"evaluate":553,"extract":560},{"promptVersionExtension":209,"promptVersionScoring":210,"score":213,"tags":554,"targetMarket":221,"tier":222},[555,556,557,558,559,218],"performance","analysis","optimization","claude-flow","bottleneck-detection",{"commitSha":255,"license":241},{"repoId":562},"kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[556,559,558,557,555,218],{"evaluatedAt":565,"extractAt":566,"updatedAt":565},1778699217174,1778696691708,{"_creationTime":568,"_id":569,"community":570,"display":571,"identity":577,"providers":581,"relations":589,"tags":592,"workflow":593},1778698144006.2202,"k172517ana4f5vj79mb22xzwsx86mksv",{"reviewCount":8},{"description":572,"installMethods":573,"name":575,"sourceUrl":576},"Audit and consolidate HubSpot reporting dashboards. Identifies unused, duplicate, or outdated dashboards. Must be performed manually — no dashboard API is available.",{"claudeCode":574},"TomGranot/hubspot-admin-skills","cleanup-dashboards","https://github.com/TomGranot/hubspot-admin-skills",{"basePath":578,"githubOwner":579,"githubRepo":580,"locale":18,"slug":575,"type":249},"skills/cleanup-dashboards","TomGranot","hubspot-admin-skills",{"evaluate":582,"extract":588},{"promptVersionExtension":209,"promptVersionScoring":210,"score":213,"tags":583,"targetMarket":221,"tier":222},[584,585,586,218,587],"hubspot","crm","maintenance","cleanup",{"commitSha":255},{"parentExtensionId":590,"repoId":591},"k17c3p8t0thc73pbc8egtz31y986mwr0","kd75kpec7arn6z2wz641vfaj8n86nab6",[587,585,584,586,218],{"evaluatedAt":594,"extractAt":595,"updatedAt":594},1778698268281,1778698144006,{"_creationTime":597,"_id":598,"community":599,"display":600,"identity":606,"providers":610,"relations":616,"tags":619,"workflow":620},1778694480889.9524,"k17cem4hc58gq77dezte6rz8mx86nkpf",{"reviewCount":8},{"description":601,"installMethods":602,"name":604,"sourceUrl":605},"Display the current state of the FPF knowledge base",{"claudeCode":603},"NeoLabHQ/context-engineering-kit","status","https://github.com/NeoLabHQ/context-engineering-kit",{"basePath":607,"githubOwner":608,"githubRepo":609,"locale":18,"slug":604,"type":249},"plugins/fpf/skills/status","NeoLabHQ","context-engineering-kit",{"evaluate":611,"extract":615},{"promptVersionExtension":209,"promptVersionScoring":210,"score":213,"tags":612,"targetMarket":221,"tier":222},[613,604,218,614],"knowledge-base","fpf",{"commitSha":255},{"parentExtensionId":617,"repoId":618},"k170dd9j7raacsjs3ta67k8cw986m50s","kd7a3rj13ezgx1wgm0jfh08hsx86n0sz",[614,613,218,604],{"evaluatedAt":621,"extractAt":622,"updatedAt":621},1778695034738,1778694480890,{"_creationTime":624,"_id":625,"community":626,"display":627,"identity":633,"providers":637,"relations":645,"tags":648,"workflow":649},1778692726926.7627,"k17dhmskz6t7wpxvd9ygy7fvsh86n695",{"reviewCount":8},{"description":628,"installMethods":629,"name":631,"sourceUrl":632},"End-of-quarter strategic review in narrative style with a bets scorecard. Use when someone says \"quarter review\", \"strategic review\", \"what happened last quarter\", \"quarterly retro\", \"bets scorecard\", \"review our bets\", \"end of quarter report\".\n",{"claudeCode":630},"marfoerst/the-pragmatic-pm","pm-strategic-review","https://github.com/marfoerst/the-pragmatic-pm",{"basePath":634,"githubOwner":635,"githubRepo":636,"locale":18,"slug":631,"type":249},"skills/pm-strategic-review","marfoerst","the-pragmatic-pm",{"evaluate":638,"extract":644},{"promptVersionExtension":209,"promptVersionScoring":210,"score":213,"tags":639,"targetMarket":221,"tier":222},[640,641,218,642,643],"product-management","strategy","review","scorecard",{"commitSha":255},{"parentExtensionId":646,"repoId":647},"k17ehawghqbe3ff7rxmq9cq1xs86nm21","kd731k864fr1ezp8r85ecbhz9986mzz7",[640,218,642,643,641],{"evaluatedAt":650,"extractAt":651,"updatedAt":650},1778693621016,1778692726926,{"_creationTime":653,"_id":654,"community":655,"display":656,"identity":662,"providers":666,"relations":675,"tags":678,"workflow":679},1778692306427.1023,"k17f0vqhj9x3ee4773kq2m8fph86n5ct",{"reviewCount":8},{"description":657,"installMethods":658,"name":660,"sourceUrl":661},"Revenue and costs tracker. AWS spend via aws ce, credits tracker, project revenue stages. Shows burn rate, runway estimate, credits expiring.",{"claudeCode":659},"Lifecycle-Innovations-Limited/claude-ops","ops-revenue","https://github.com/Lifecycle-Innovations-Limited/claude-ops",{"basePath":663,"githubOwner":664,"githubRepo":665,"locale":18,"slug":660,"type":249},"claude-ops/skills/ops-revenue","Lifecycle-Innovations-Limited","claude-ops",{"evaluate":667,"extract":674},{"promptVersionExtension":209,"promptVersionScoring":210,"score":213,"tags":668,"targetMarket":221,"tier":222},[669,670,671,672,218,673],"finance","aws","cost-tracking","revenue","dashboard",{"commitSha":255},{"parentExtensionId":676,"repoId":677},"k17d0t6ns7y6t377pfprg128hd86nm89","kd7d52tcek2e34r805zs06b10d86n39v",[670,671,673,669,218,672],{"evaluatedAt":680,"extractAt":681,"updatedAt":680},1778692873720,1778692306427]