Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
add-strategy
Create a new trading strategy for the ai-trader backtesting framework. Handles file creation, registration, docstrings, and backtest scaffolding.
whchien/ai-trader 591
-
reverse-engineering
Use the bundled r2mcp MCP server for binary analysis, disassembly, and reverse-engineering tasks.
radareorg/radare2-mcp 201
-
release-dbt-mcp
Release a new version of dbt-mcp to PyPi
dbt-labs/dbt-mcp 534
-
rag-rlm
Computational analysis of the knowledge base via code execution in a sandboxed Python interpreter. Use for questions requiring counting, aggregation, statistics, data traversal, comparison across documents, or any task best answered by writing Python code. Examples: "how many pages?", "compare table 3 across documents", "calculate average word count", "extract all email addresses".
ggozad/haiku.rag 510
-
rag
Search, retrieve and analyze documents using RAG (Retrieval Augmented Generation).
ggozad/haiku.rag 510
-
biomcp
Search and retrieve biomedical data - genes, variants, clinical trials, articles, drugs, diseases, pathways, proteins, adverse events, pharmacogenomics, and phenotype-disease matching. Use for gene function, variant pathogenicity, trials, drug safety, pathway context, disease workups, and literature evidence.
genomoncology/biomcp 488
-
webclaw
Web extraction engine with antibot bypass. Scrape, crawl, extract, summarize, search, map, diff, monitor, research, and analyze any URL — including Cloudflare-protected sites. Use when you need reliable web content, the built-in web_fetch fails, or you need structured data extraction from web pages.
0xMassi/webclaw 478
-
docfork-docs
Retrieves up-to-date documentation for any third-party library, framework, or API where training data may be outdated or incomplete. Use when the user asks about library usage, API references, configuration, or code generation involving specific packages. Prefer over training data when accuracy or recency matters.
docfork/docfork 460
-
docfork-docs
Retrieves up-to-date documentation for any third-party library, framework, or API where training data may be outdated or incomplete. Use when the user asks about library usage, API references, configuration, or code generation involving specific packages. Prefer over training data when accuracy or recency matters.
docfork/docfork 460
-
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring, refactoring guidance, code review. Requires roam-code installed (`pip install roam-code`) and an indexed project (`roam init`).
Cranot/roam-code 449
-
git-dvc-versioning
Manage ML experiment versioning using Git + DVC + xetrack + DuckDB. Use this skill when the user wants to: version experiments with git tags and DVC, run sequential or parallel ML experiments with reproducibility, merge or rebase experiment results (SQLite databases, parquet data, models), set up DVC remotes and cache (including S3), manage model candidates and promotion, use git worktrees for parallel code/data experiments, track experiment metadata in SQLite with xetrack, retrieve models or data from past experiments, explore or compare historical experiments, or find what data was used. Triggers on: "version experiment", "tag experiment", "DVC setup", "merge results", "rebase data", "git worktree experiment", "parallel experiments", "model promotion", "candidates", "experiment tracking", "reproducibility", "dvc pipeline", "merge database", "data versioning", "retrieve model", "get model", "find experiment", "explore experiment", "compare experiments", "what data was used", "inspect results", "restore experiment", "recover model", "browse experiments", "download model", "historical model".
xdssio/xetrack 7
-
benchmark
xdssio/xetrack 7
-
xetrack
API reference and usage patterns for xetrack — lightweight experiment tracking with SQLite/DuckDB. Use when writing code that uses xetrack, when unsure about Tracker or Reader API, when using the xt CLI, when working with caching/diskcache, or when tracking ML experiments. Triggers on "xetrack", "Tracker", "Reader", "tracker.track", "tracker.log", "xt cli", "xetrack cache", "experiment tracking", "track function", "track metrics".
xdssio/xetrack 7
-
release
nwiizo/tfmcp 361
-
commit
Prepare code for review by running quality checks, creating conventional commits, and opening pull requests. Use when the user wants to commit changes, create a PR, prepare for code review, or asks to commit their work.
decocms/studio 357
-
review-plan
Spawn parallel subagents to criticize implementation plans from multiple perspectives (duplication, correctness, security, performance, testing, architecture, scope), then improve the plan based on feedback. Use when reviewing a plan before implementation or when stress-testing a plan for gaps.
decocms/studio 357
-
review-pr
Analyze the git diff between the current branch and main from multiple perspectives (duplication, correctness, security, performance, testing, architecture, scope) using parallel subagents, then produce a remediation plan for issues found. Use when reviewing branch changes before merge, after implementation, or when the user asks to critique or review current code changes.
decocms/studio 357
-
add-mcp-tools
Guide for adding new MCP tools with consistent patterns for schemas, tool definitions, registry updates, and Better Auth integration
decocms/studio 357
-
respond-to-pr-review
Use when PR review comments need to be processed and responded to, when the user says "respond to review", "handle PR comments", "address review feedback", or after receiving code review on a pull request
decocms/studio 357
-
azure-devops-rest-api
Guide for working with Azure DevOps REST APIs and OpenAPI specifications. Use this skill when implementing new Azure DevOps API integrations, exploring API capabilities, understanding request/response formats, or referencing the official OpenAPI specifications from the vsts-rest-api-specs repository.
Tiberriver256/mcp-server-azure-devops 357
-
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Tiberriver256/mcp-server-azure-devops 357
-
hookdeck-cli-release
Guides maintainers through Hookdeck CLI releases (stable GA, beta from main, beta from feature branches) and user-centric GitHub release notes. Validates proposed versions against SemVer from the actual change set (e.g. breaking changes require a major bump). Use when cutting a release, publishing a tag, drafting release notes, choosing vMAJOR.MINOR.PATCH, GoReleaser, npm publish, pre-releases, following the release checklist, or `gh release create`.
hookdeck/hookdeck-cli 353
-
add_mcp_feature
Instructions for adding new features (tools, prompts, etc.) to the dart_mcp_server package.
dart-lang/ai 248
-
Update dart_mcp_server README.md file
Instructions for updating the README.md file in the `dart_mcp_server` package.
dart-lang/ai 248