[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-clickhouse-chdb-sql-en":3,"guides-for-clickhouse-chdb-sql":457,"similar-k17c4ydtqa4by58w512pxnpgan86n7a4-en":458},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":248,"isFallback":238,"parentExtension":252,"providers":306,"relations":310,"repo":311,"tags":454,"workflow":455},1778683910609.9011,"k17c4ydtqa4by58w512pxnpgan86n7a4",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"In-process ClickHouse SQL engine for Python — run ClickHouse SQL queries directly on local files, remote databases, and cloud storage without a server. Use when the user wants to write SQL queries against Parquet/CSV/ JSON files, use ClickHouse table functions (mysql(), s3(), postgresql(), iceberg(), deltaLake() etc.), build stateful analytical pipelines with Session, use parametrized queries, window functions, or other advanced ClickHouse SQL features. Also use when the user explicitly mentions chdb.query(), ClickHouse SQL syntax, or wants cross-source SQL joins. Do NOT use for pandas-style DataFrame operations — use chdb-datastore instead.",{"claudeCode":12},"clickhouse/agent-skills","chdb-sql","https://github.com/clickhouse/agent-skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":229,"workflow":246},1778684035570.2466,"kn71361498g0q6fmdm8qczjy3586mqaq","en",{"checks":20,"evaluatedAt":193,"extensionSummary":194,"features":195,"nonGoals":203,"promptVersionExtension":207,"promptVersionScoring":208,"purpose":209,"rationale":210,"score":211,"summary":212,"tags":213,"targetMarket":222,"tier":223,"useCases":224},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,99,103,107,110,114,118,122,125,128,131,134,137,140,144,148,151,154,158,161,164,167,170,174,177,180,183,186,190],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly identifies the problem of running ClickHouse SQL queries directly on various data sources without a server and specifies user intents like querying files, using table functions, and building analytical pipelines.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill provides significant value over a simple prompt by offering a dedicated in-process SQL engine for ClickHouse, enabling complex queries and cross-source joins directly within Python without external server setup.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill bundle appears complete, supporting the stated use cases of running ClickHouse SQL queries on various data sources and providing necessary APIs for different interaction patterns.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The extension focuses solely on providing an in-process ClickHouse SQL engine for Python, clearly defining its scope and avoiding unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description accurately reflects the skill's capabilities, clearly outlines its purpose, provides specific use cases, and explicitly states non-goals, making it easy to understand and use.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill utilizes a clear API (`chdb.query`, `Session`, `dbapi.connect`) that abstracts away underlying SQL execution, preventing direct arbitrary command execution.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","The API reference details all parameters for `chdb.query`, `Session`, and `dbapi.connect`, including output formats and parametrization, with examples provided.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","The core interfaces (`chdb.query`, `Session`, `dbapi.connect`) are descriptive and align with the domain of SQL querying.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","The API parameters are well-defined and structured (SQL query, output format, path, params), and the output is presented in various structured formats (CSV, DataFrame, JSON, etc.), minimizing extraneous data.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is licensed under the Apache-2.0 license, which is a permissive open-source license.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The repository has recent commits within the last 3 months, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The `pip install chdb` instruction and the presence of a lockfile (based on trust signals) suggest appropriate dependency management.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The skill does not appear to handle or echo secrets; connection details for external databases are passed as parameters, not hardcoded or logged.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The skill executes SQL queries through a defined API (`chdb.query`, `Session`), which sanitizes and executes SQL, mitigating direct command injection risks.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The skill relies on the `chdb` Python package and does not appear to fetch or execute external code or data at runtime.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The skill operates within Python and interacts with data files or databases via defined APIs, without attempting to write to arbitrary file paths or execute shell commands outside its scope.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","No detached process spawns or deny-retry loops were observed in the provided source code snippets.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The skill's core functionality is to query data, not exfiltrate it. Credentials for external databases are passed as parameters and are not documented as being submitted to third parties.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The bundled content and descriptions are free of hidden text tricks or invisible Unicode characters.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The skill's Python code is readable and does not employ obfuscation techniques like base64 encoding or runtime script fetching.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The skill primarily operates on data paths provided by the user or within a defined session context, without making rigid assumptions about project file structure.",{"category":95,"check":96,"severity":97,"summary":98},"Trust","Issues Attention","info","Open issues: 2, Closed issues: 0. The maintainers have not closed any issues in the last 90 days, and there are currently 2 open issues.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The skill has a declared version ('4.1') in the frontmatter, indicating clear versioning.",{"category":104,"check":105,"severity":24,"summary":106},"Execution","Validation","The API (`chdb.query`) handles SQL and parameters, implying internal validation. Output is returned in structured formats.",{"category":65,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","The skill is primarily analytical. While creating tables in a session is possible, destructive operations are not inherently unguarded and typical SQL DDL/DML would require explicit user intent.",{"category":111,"check":112,"severity":24,"summary":113},"Code Execution","Error Handling","The underlying `chdb` library likely handles errors robustly, and the Python API provides structured outputs or raises exceptions, allowing for meaningful error reporting.",{"category":111,"check":115,"severity":116,"summary":117},"Logging","not_applicable","This skill is primarily analytical and does not perform destructive actions or outbound calls that necessitate local audit logging.",{"category":119,"check":120,"severity":24,"summary":121},"Compliance","GDPR","The skill operates on user-provided data sources. It does not inherently process personal data unless the input data contains it, and it does not submit data to third parties.",{"category":119,"check":123,"severity":24,"summary":124},"Target market","The extension operates on local files, databases, and cloud storage and is not bound by specific geographic or legal jurisdictions.",{"category":91,"check":126,"severity":24,"summary":127},"Runtime stability","The skill relies on the Python `chdb` package and standard Python execution, making it portable across compatible operating systems.",{"category":44,"check":129,"severity":24,"summary":130},"README","The README file exists, is well-structured, and clearly states the extension's purpose and installation instructions.",{"category":33,"check":132,"severity":24,"summary":133},"Tool surface size","The extension primarily exposes SQL query capabilities through a few well-defined API entry points (`chdb.query`, `Session`), keeping the surface size manageable.",{"category":40,"check":135,"severity":24,"summary":136},"Overlapping near-synonym tools","The skill exposes distinct interfaces for different interaction patterns (`query`, `Session`, `dbapi`), avoiding redundant or overlapping tools.",{"category":44,"check":138,"severity":24,"summary":139},"Phantom features","All advertised features, such as querying different file types and data sources, are directly implemented through the `chdb` library and its APIs.",{"category":141,"check":142,"severity":24,"summary":143},"Install","Installation instruction","The README provides clear installation instructions (`npx skills add`) and an invocation example in the `SKILL.md` frontmatter and `examples.md`.",{"category":145,"check":146,"severity":24,"summary":147},"Errors","Actionable error messages","The provided troubleshooting section in `examples.md` and the general structure of API errors offer guidance on what failed and potential fixes.",{"category":104,"check":149,"severity":24,"summary":150},"Pinned dependencies","The extension lists `pip install chdb` and mentions Python 3.9+, implying dependency management. Trust signals indicate a lockfile is present.",{"category":33,"check":152,"severity":116,"summary":153},"Dry-run preview","The primary function of the skill is data analysis and querying, which is inherently read-only and does not involve state-changing operations requiring a dry-run mode.",{"category":155,"check":156,"severity":24,"summary":157},"Protocol","Idempotent retry & timeouts","The underlying `chdb` library handles query execution, which is generally idempotent for select statements. Timeouts are managed by the Python environment and underlying libraries.",{"category":119,"check":159,"severity":24,"summary":160},"Telemetry opt-in","The skill does not appear to emit telemetry. Any telemetry would likely be managed by the core `chdb` library or the agent framework, not directly by this skill.",{"category":40,"check":162,"severity":24,"summary":163},"Precise Purpose","The description precisely names the artifact (ClickHouse SQL engine), the user intent (run SQL queries), and provides clear use cases and non-goals.",{"category":40,"check":165,"severity":24,"summary":166},"Concise Frontmatter","The frontmatter is concise, self-contained, and effectively summarizes the core capability and trigger phrases within the recommended character limit.",{"category":44,"check":168,"severity":24,"summary":169},"Concise Body","The SKILL.md body is concise and effectively uses external markdown files for deeper material like API references and examples.",{"category":171,"check":172,"severity":24,"summary":173},"Context","Progressive Disclosure","Detailed information like API references, table functions, and SQL functions are appropriately delegated to separate markdown files, linked from the main SKILL.md.",{"category":171,"check":175,"severity":116,"summary":176},"Forked exploration","This skill is not focused on deep exploration or code review; its purpose is direct data querying, so `context: fork` is not applicable.",{"category":22,"check":178,"severity":24,"summary":179},"Usage examples","The `examples/examples.md` file provides a comprehensive set of runnable, end-to-end examples demonstrating various functionalities, including file querying, joins, sessions, and UDFs.",{"category":22,"check":181,"severity":24,"summary":182},"Edge cases","The `examples/examples.md` includes a section on common errors and fixes, addressing issues like file not found, incorrect function names, and connection problems with suggested recovery steps.",{"category":111,"check":184,"severity":116,"summary":185},"Tool Fallback","The skill relies on the core `chdb` Python package and does not have external tool dependencies that would require a fallback mechanism.",{"category":187,"check":188,"severity":24,"summary":189},"Safety","Halt on unexpected state","The provided examples and API structure suggest that invalid inputs or states would result in errors or exceptions rather than proceeding with unexpected consequences.",{"category":91,"check":191,"severity":24,"summary":192},"Cross-skill coupling","The skill is self-contained and focuses on SQL querying via `chdb`; it does not appear to implicitly rely on other skills and cross-references are not evident.",1778684035463,"This skill provides an in-process ClickHouse SQL engine for Python, allowing users to execute SQL queries directly on local files (Parquet, CSV, JSON), remote databases (MySQL, PostgreSQL), and cloud storage (S3, GCS, Azure Blob) without needing a separate ClickHouse server. It supports advanced ClickHouse features like table functions, parametrized queries, and window functions, and can ingest Python data structures as tables.",[196,197,198,199,200,201,202],"Run ClickHouse SQL queries in-process","Query local files (Parquet, CSV, JSON)","Connect to remote databases (MySQL, PostgreSQL)","Access cloud storage (S3, GCS, Azure Blob)","Use advanced ClickHouse SQL features (table functions, window functions, parametrized queries)","Integrate Python data structures (dicts, DataFrames) as SQL tables","Build stateful analytical pipelines with Session API",[204,205,206],"Performing pandas-style DataFrame operations (use `chdb-datastore` instead).","Running a standalone ClickHouse server.","Acting as a general-purpose database client for all SQL dialects.","3.0.0","4.4.0","To enable users to leverage the power of ClickHouse SQL directly within their Python environment for efficient data querying and analysis across various data sources.","Excellent documentation and functionality, with clear examples and comprehensive API references. No critical or warning findings.",98,"A high-quality skill for running ClickHouse SQL queries in-process via Python.",[214,215,216,217,218,219,220,221],"sql","clickhouse","query","python","data-analysis","parquet","csv","json","global","verified",[225,226,227,228],"Querying data from Parquet, CSV, or JSON files using SQL.","Joining data from different sources (e.g., MySQL and S3) with SQL.","Building multi-step analytical pipelines with persistent sessions.","Leveraging ClickHouse's rich SQL dialect within a Python script.",{"codeQuality":230,"collectedAt":232,"documentation":233,"maintenance":236,"security":243,"testCoverage":245},{"hasLockfile":231},true,1778684011129,{"descriptionLength":234,"readmeSize":235},649,6756,{"closedIssues90d":8,"forks":237,"hasChangelog":238,"manifestVersion":239,"openIssues90d":240,"pushedAt":241,"stars":242},25,false,"4.1",2,1778669462000,425,{"hasNpmPackage":238,"license":244,"smitheryVerified":238},"Apache-2.0",{"hasCi":231,"hasTests":238},{"updatedAt":247},1778684035570,{"basePath":249,"githubOwner":215,"githubRepo":250,"locale":18,"slug":13,"type":251},"skills/chdb-sql","agent-skills","skill",{"_creationTime":253,"_id":254,"community":255,"display":256,"identity":260,"parentExtension":263,"providers":292,"relations":301,"tags":302,"workflow":303},1778683910609.9004,"k171w0wat3qnkfpas7mn7yqtb986mfgf",{"reviewCount":8},{"description":257,"installMethods":258,"name":259,"sourceUrl":14},"28 best practice rules for ClickHouse schema design, query optimization, and data ingestion — prioritized by impact",{"claudeCode":259},"clickhouse-best-practices",{"basePath":261,"githubOwner":215,"githubRepo":250,"locale":18,"slug":250,"type":262},"","plugin",{"_creationTime":264,"_id":265,"community":266,"display":267,"identity":271,"providers":273,"relations":285,"tags":287,"workflow":288},1778683910609.9001,"k1790kh9nnyedb58t0bhb9k83s86mcna",{"reviewCount":8},{"description":268,"installMethods":269,"name":270,"sourceUrl":14},"Official ClickHouse best practices for Claude Code",{"claudeCode":12},"clickhouse-agent-skills",{"basePath":261,"githubOwner":215,"githubRepo":250,"locale":18,"slug":250,"type":272},"marketplace",{"evaluate":274,"extract":280},{"promptVersionExtension":275,"promptVersionScoring":208,"score":276,"tags":277,"targetMarket":222,"tier":223},"3.1.0",95,[215,278,214,218,279],"database","developer-tools",{"commitSha":281,"marketplace":282,"plugin":283},"HEAD",{"name":270,"pluginCount":240},{"mcpCount":8,"provider":284,"skillCount":8},"classify",{"repoId":286},"kd7723v6kvsmj7pd0jntz17bkn86ne4f",[215,218,278,279,214],{"evaluatedAt":289,"extractAt":290,"updatedAt":291},1778683929817,1778683910609,1778684301942,{"evaluate":293,"extract":298},{"promptVersionExtension":207,"promptVersionScoring":208,"score":294,"tags":295,"targetMarket":222,"tier":223},97,[215,278,214,217,296,297],"devops","analytics",{"commitSha":281,"license":244,"plugin":299},{"mcpCount":8,"provider":284,"skillCount":300},6,{"parentExtensionId":265,"repoId":286},[297,215,278,296,217,214],{"evaluatedAt":304,"extractAt":290,"updatedAt":305},1778683955196,1778684302148,{"evaluate":307,"extract":309},{"promptVersionExtension":207,"promptVersionScoring":208,"score":211,"tags":308,"targetMarket":222,"tier":223},[214,215,216,217,218,219,220,221],{"commitSha":281},{"parentExtensionId":254,"repoId":286},{"_creationTime":312,"_id":286,"identity":313,"providers":314,"workflow":450},1778683905800.361,{"githubOwner":215,"githubRepo":250,"sourceUrl":14},{"classify":315,"discover":442,"github":445},{"commitSha":281,"extensions":316},[317,330,351,361,379,392,409,418,426,434],{"basePath":261,"description":268,"displayName":270,"installMethods":318,"rationale":319,"selectedPaths":320,"source":329,"sourceLanguage":18,"type":272},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[321,324,326],{"path":322,"priority":323},".claude-plugin/marketplace.json","mandatory",{"path":325,"priority":323},"README.md",{"path":327,"priority":328},"LICENSE","high","rule",{"basePath":261,"description":257,"displayName":259,"installMethods":331,"license":244,"rationale":332,"selectedPaths":333,"source":329,"sourceLanguage":18,"type":262},{"claudeCode":259},"plugin manifest at .claude-plugin/plugin.json",[334,336,337,338,341,343,345,347,349],{"path":335,"priority":323},".claude-plugin/plugin.json",{"path":325,"priority":323},{"path":327,"priority":328},{"path":339,"priority":340},"skills/chdb-datastore/SKILL.md","medium",{"path":342,"priority":340},"skills/chdb-sql/SKILL.md",{"path":344,"priority":340},"skills/clickhouse-architecture-advisor/SKILL.md",{"path":346,"priority":340},"skills/clickhouse-best-practices/SKILL.md",{"path":348,"priority":340},"skills/clickhousectl-cloud-deploy/SKILL.md",{"path":350,"priority":340},"skills/clickhousectl-local-dev/SKILL.md",{"basePath":352,"description":353,"displayName":354,"installMethods":355,"rationale":356,"selectedPaths":357,"source":329,"sourceLanguage":18,"type":262},"skills/clickhouse-architecture-advisor","Workload-aware architecture decision skill for ClickHouse — ingestion strategies, partitioning, enrichment, upsert patterns, and pre-aggregation with explicit official/derived/field provenance","clickhouse-architecture-advisor",{"claudeCode":354},"inline plugin source from marketplace.json at skills/clickhouse-architecture-advisor",[358,359],{"path":325,"priority":323},{"path":360,"priority":328},"SKILL.md",{"basePath":362,"description":363,"displayName":364,"installMethods":365,"rationale":366,"selectedPaths":367,"source":329,"sourceLanguage":18,"type":251},"skills/chdb-datastore","Drop-in pandas replacement with ClickHouse performance. Use `import chdb.datastore as pd` (or `from datastore import DataStore`) and write standard pandas code — same API, 10-100x faster on large datasets. Supports 16+ data sources (MySQL, PostgreSQL, S3, MongoDB, ClickHouse, Iceberg, Delta Lake, etc.) and 10+ file formats (Parquet, CSV, JSON, Arrow, ORC, etc.) with cross-source joins. Use this skill when the user wants to analyze data with pandas-style syntax, speed up slow pandas code, query remote databases or cloud storage as DataFrames, or join data across different sources — even if they don't explicitly mention chdb or DataStore. Do NOT use for raw SQL queries, ClickHouse server administration, or non-Python languages.","chdb-datastore",{"claudeCode":12},"SKILL.md frontmatter at skills/chdb-datastore/SKILL.md",[368,369,370,373,375,377],{"path":360,"priority":323},{"path":325,"priority":328},{"path":371,"priority":372},"examples/examples.md","low",{"path":374,"priority":340},"references/api-reference.md",{"path":376,"priority":340},"references/connectors.md",{"path":378,"priority":372},"scripts/verify_install.py",{"basePath":249,"description":10,"displayName":13,"installMethods":380,"rationale":381,"selectedPaths":382,"source":329,"sourceLanguage":18,"type":251},{"claudeCode":12},"SKILL.md frontmatter at skills/chdb-sql/SKILL.md",[383,384,385,386,387,389,391],{"path":360,"priority":323},{"path":325,"priority":328},{"path":371,"priority":372},{"path":374,"priority":340},{"path":388,"priority":340},"references/sql-functions.md",{"path":390,"priority":340},"references/table-functions.md",{"path":378,"priority":372},{"basePath":352,"description":393,"displayName":354,"installMethods":394,"rationale":395,"selectedPaths":396,"source":329,"sourceLanguage":18,"type":251},"MUST USE when designing ClickHouse architectures, selecting between ingestion or modeling patterns, or translating best practices into workload-specific system designs. Complements clickhouse-best-practices with decision frameworks and explicit provenance labels.",{"claudeCode":12},"SKILL.md frontmatter at skills/clickhouse-architecture-advisor/SKILL.md",[397,398,399,401,403,405,407],{"path":360,"priority":323},{"path":325,"priority":328},{"path":400,"priority":340},"AGENTS.md",{"path":402,"priority":372},"examples/README.md",{"path":404,"priority":372},"examples/finserv-market-surveillance.md",{"path":406,"priority":372},"examples/observability-high-throughput.md",{"path":408,"priority":372},"examples/siem-security-analytics.md",{"basePath":410,"description":411,"displayName":259,"installMethods":412,"rationale":413,"selectedPaths":414,"source":329,"sourceLanguage":18,"type":251},"skills/clickhouse-best-practices","MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 31 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.",{"claudeCode":12},"SKILL.md frontmatter at skills/clickhouse-best-practices/SKILL.md",[415,416,417],{"path":360,"priority":323},{"path":325,"priority":328},{"path":400,"priority":340},{"basePath":419,"description":420,"displayName":421,"installMethods":422,"rationale":423,"selectedPaths":424,"source":329,"sourceLanguage":18,"type":251},"skills/clickhouse-client-js/clickhouse-js-node-troubleshooting","Troubleshoot and resolve common issues with the ClickHouse Node.js client (@clickhouse/client). Use this skill whenever a user reports errors, unexpected behavior, or configuration questions involving the Node.js client specifically — including socket hang-up errors, Keep-Alive problems, stream handling issues, data type mismatches, read-only user restrictions, proxy/TLS setup problems, or long-running query timeouts. Trigger even when the user hasn't precisely named the issue; vague symptoms like \"my inserts keep failing\" or \"connection drops randomly\" in a Node.js context are strong signals to use this skill. Do NOT use for browser/Web client issues.\n","clickhouse-js-node-troubleshooting",{"claudeCode":12},"SKILL.md frontmatter at skills/clickhouse-client-js/clickhouse-js-node-troubleshooting/SKILL.md",[425],{"path":360,"priority":323},{"basePath":427,"description":428,"displayName":429,"installMethods":430,"rationale":431,"selectedPaths":432,"source":329,"sourceLanguage":18,"type":251},"skills/clickhousectl-cloud-deploy","Use when a user wants to deploy ClickHouse to the cloud, go to production, use ClickHouse Cloud, host a managed ClickHouse service, or migrate from a local ClickHouse setup to ClickHouse Cloud.","clickhousectl-cloud-deploy",{"claudeCode":12},"SKILL.md frontmatter at skills/clickhousectl-cloud-deploy/SKILL.md",[433],{"path":360,"priority":323},{"basePath":435,"description":436,"displayName":437,"installMethods":438,"rationale":439,"selectedPaths":440,"source":329,"sourceLanguage":18,"type":251},"skills/clickhousectl-local-dev","Use when a user wants to build an application with ClickHouse, set up a local ClickHouse development environment, install ClickHouse, create a local server, create tables, or start developing with ClickHouse. Covers the full flow from zero to a working local ClickHouse setup.","clickhousectl-local-dev",{"claudeCode":12},"SKILL.md frontmatter at skills/clickhousectl-local-dev/SKILL.md",[441],{"path":360,"priority":323},{"sources":443},[444],"manual",{"closedIssues90d":8,"description":446,"forks":237,"homepage":447,"license":244,"openIssues90d":240,"pushedAt":241,"readmeSize":235,"stars":242,"topics":448},"The official Agent Skills for ClickHouse and ClickHouse Cloud","https://clickhouse.ai",[449,215],"agents",{"classifiedAt":451,"discoverAt":452,"extractAt":453,"githubAt":453,"updatedAt":451},1778683910082,1778683905800,1778683908184,[215,220,218,221,219,217,216,214],{"evaluatedAt":247,"extractAt":290,"updatedAt":456},1778684302501,[],[459,488,516,544,572,596],{"_creationTime":460,"_id":461,"community":462,"display":463,"identity":469,"providers":473,"relations":481,"tags":484,"workflow":485},1778695548458.3613,"k17dx6tyy2yb3z5pp1vgmg46ad86nm18",{"reviewCount":8},{"description":464,"installMethods":465,"name":467,"sourceUrl":468},"Fit cognitive drift-diffusion models (Ratcliff DDM) to reaction time and accuracy data with parameter estimation (drift rate, boundary separation, non-decision time), model comparison, and parameter recovery validation. Use when modeling binary decision-making with reaction time data, estimating cognitive parameters from experimental data, comparing sequential sampling model variants, or decomposing speed-accuracy tradeoff effects into latent cognitive components.\n",{"claudeCode":466},"pjt222/agent-almanac","fit-drift-diffusion-model","https://github.com/pjt222/agent-almanac",{"basePath":470,"githubOwner":471,"githubRepo":472,"locale":18,"slug":467,"type":251},"skills/fit-drift-diffusion-model","pjt222","agent-almanac",{"evaluate":474,"extract":480},{"promptVersionExtension":207,"promptVersionScoring":208,"score":475,"tags":476,"targetMarket":222,"tier":223},100,[477,478,479,217,218],"cognitive-science","modeling","statistics",{"commitSha":281},{"parentExtensionId":482,"repoId":483},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[477,218,478,217,479],{"evaluatedAt":486,"extractAt":487,"updatedAt":486},1778698191612,1778695548458,{"_creationTime":489,"_id":490,"community":491,"display":492,"identity":498,"providers":502,"relations":509,"tags":511,"workflow":512},1778683522639.4817,"k17a9cav35ya4h38sccx3r3d5d86mr2y",{"reviewCount":8},{"description":493,"installMethods":494,"name":496,"sourceUrl":497},"Guide for querying databases through DBHub MCP server. Use this skill whenever you need to explore database schemas, inspect tables, or run SQL queries via DBHub's MCP tools (search_objects, execute_sql). Activates on any database query task, schema exploration, data retrieval, or SQL execution through MCP — even if the user just says \"check the database\" or \"find me some data.\" This skill ensures you follow the correct explore-first workflow instead of guessing table structures.",{"claudeCode":495},"bytebase/dbhub","DBHub Database Query Guide","https://github.com/bytebase/dbhub",{"basePath":499,"githubOwner":500,"githubRepo":501,"locale":18,"slug":501,"type":251},"skills/dbhub","bytebase","dbhub",{"evaluate":503,"extract":507},{"promptVersionExtension":207,"promptVersionScoring":208,"score":475,"tags":504,"targetMarket":222,"tier":223},[278,214,216,505,506,500],"schema","mcp",{"commitSha":281,"license":508},"MIT",{"repoId":510},"kd75gz890g3h6zj0xf3qtbrdjd86mpw3",[500,278,506,216,505,214],{"evaluatedAt":513,"extractAt":514,"updatedAt":515},1778683601748,1778683522639,1778683734542,{"_creationTime":517,"_id":518,"community":519,"display":520,"identity":526,"providers":530,"relations":538,"tags":540,"workflow":541},1778682862751.9475,"k177bn4hpsv2417q7fvbdtwav586ny65",{"reviewCount":8},{"description":521,"installMethods":522,"name":524,"sourceUrl":525},"Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL migration, DDL operations, query plan explainability, and SQL compatibility validation. Triggers on phrases like: DSQL, Aurora DSQL, create DSQL table, DSQL schema, migrate to DSQL, distributed SQL database, serverless PostgreSQL-compatible database, DSQL query plan, DSQL EXPLAIN ANALYZE, why is my DSQL query slow.",{"claudeCode":523},"awslabs/mcp","dsql","https://github.com/awslabs/mcp",{"basePath":527,"githubOwner":528,"githubRepo":506,"locale":18,"slug":529,"type":251},"src/aurora-dsql-mcp-server/skills/dsql-skill","awslabs","dsql-skill",{"evaluate":531,"extract":537},{"promptVersionExtension":207,"promptVersionScoring":208,"score":475,"tags":532,"targetMarket":222,"tier":223},[278,214,533,534,524,535,505,216,536],"aws","aurora","migration","performance",{"commitSha":281},{"repoId":539},"kd71cq56hfddetnwspw92kb09x86mbzy",[534,533,278,524,535,536,216,505,214],{"evaluatedAt":542,"extractAt":543,"updatedAt":542},1778682978663,1778682862752,{"_creationTime":545,"_id":546,"community":547,"display":548,"identity":554,"providers":559,"relations":565,"tags":568,"workflow":569},1778696833339.6248,"k1704jzrc3jb9sv90n1mpz61hn86n2pp",{"reviewCount":8},{"description":549,"installMethods":550,"name":552,"sourceUrl":553},"Execute read-only SQL queries against multiple MySQL databases. Use when: (1) querying MySQL databases, (2) exploring database schemas/tables, (3) running SELECT queries for data analysis, (4) checking database contents. Supports multiple database connections with descriptions for intelligent auto-selection. Blocks all write operations (INSERT, UPDATE, DELETE, DROP, etc.) for safety.",{"claudeCode":551},"sanjay3290/ai-skills","MySQL Read-Only Query Skill","https://github.com/sanjay3290/ai-skills",{"basePath":555,"githubOwner":556,"githubRepo":557,"locale":18,"slug":558,"type":251},"skills/mysql","sanjay3290","ai-skills","mysql",{"evaluate":560,"extract":564},{"promptVersionExtension":207,"promptVersionScoring":208,"score":561,"tags":562,"targetMarket":222,"tier":223},99,[214,558,278,216,563],"read-only",{"commitSha":281,"license":244},{"parentExtensionId":566,"repoId":567},"k17es37z10n1sw6t2m3f0vsydx86mnje","kd71np0fyqg23qg8w2hcfw0h0h86nkn0",[278,558,216,563,214],{"evaluatedAt":570,"extractAt":571,"updatedAt":570},1778697138135,1778696833339,{"_creationTime":573,"_id":574,"community":575,"display":576,"identity":580,"providers":582,"relations":592,"tags":593,"workflow":594},1778695548458.3975,"k17ejn0j9x7ebtqhjz56mw3fbs86mn1z",{"reviewCount":8},{"description":577,"installMethods":578,"name":579,"sourceUrl":468},"Serialize and deserialize data across common formats including JSON, XML, YAML, Protocol Buffers, MessagePack, and Apache Arrow/Parquet. Covers format selection criteria, encoding/decoding patterns, performance trade-offs, and interoperability considerations. Use when choosing a wire format for API communication, persisting structured data to disk, exchanging data between systems written in different languages, optimizing transfer size or parsing speed, or migrating from one serialization format to another.\n",{"claudeCode":466},"serialize-data-formats",{"basePath":581,"githubOwner":471,"githubRepo":472,"locale":18,"slug":579,"type":251},"skills/serialize-data-formats",{"evaluate":583,"extract":591},{"promptVersionExtension":207,"promptVersionScoring":208,"score":294,"tags":584,"targetMarket":222,"tier":223},[585,586,221,587,588,589,219,590,536],"serialization","data-formats","xml","yaml","protobuf","arrow",{"commitSha":281},{"parentExtensionId":482,"repoId":483},[590,586,221,219,536,589,585,587,588],{"evaluatedAt":595,"extractAt":487,"updatedAt":595},1778701236156,{"_creationTime":597,"_id":598,"community":599,"display":600,"identity":603,"providers":604,"relations":612,"tags":613,"workflow":614},1778683910609.9016,"k17cwmsnj5cbb1s2zvz5waqwvx86n75w",{"reviewCount":8},{"description":411,"installMethods":601,"name":602,"sourceUrl":14},{"claudeCode":12},"ClickHouse Best Practices",{"basePath":410,"githubOwner":215,"githubRepo":250,"locale":18,"slug":259,"type":251},{"evaluate":605,"extract":611},{"promptVersionExtension":207,"promptVersionScoring":208,"score":606,"tags":607,"targetMarket":222,"tier":610},88,[215,278,608,505,216,536,609],"optimization","data-ingestion","community",{"commitSha":281,"license":244},{"parentExtensionId":254,"repoId":286},[215,609,278,608,536,216,505],{"evaluatedAt":615,"extractAt":290,"updatedAt":616},1778684090643,1778684302987]