Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
47,891 skills from 2,309 repositories · updated 21 minutes ago
6,157 skills
- gpai-code-of-practicelawve-ai/awesome-legal-skillsAssess compliance with the EU General-Purpose AI (GPAI) Code of Practice under the AI Act (Regulation (EU) 2024/1689). Use when asked to determine GPAI model provider obligations, assess Code of Practice compliance, evaluate transparency or copyright requirements for GPAI models, check systemic risk obligations, build a GPAI compliance roadmap, or prepare for AI Office requests. Covers all three Code chapters (Transparency, Copyright, Safety & Security), the 12 commitments and their measures, systemic risk classification (Article 51), provider obligations (Articles 53 and 55), open-source exemptions, enforcement timeline, Commission/AI Office supervision, and DACH-specific overlays such as BSI cybersecurity and works council implications. Triggers on phrases like "GPAI compliance", "Code of Practice assessment", "GPAI model obligations", "systemic risk evaluation", "AI Act transparency requirements", "GPAI copyright policy", "general-purpose AI compliance".EngineeringNo warnings★ 913↓ —
- Apache Airflow MCPagentskillexchange/skillsCurated, trusted open catalog of AI agent skills for OpenClaw, Claude Code, Codex, GitHub Copilot, Gemini, Cursor, MCP, LangChain, and more. Browse, install, and verify reusable agent workflows.EngineeringNo warnings★ 58↓ —
- fable-scope-disciplineDizzyMii/fable-skillsUse when implementing any change in existing code — when tempted to clean up nearby code, add unrequested validation or options, fix something "arguably in scope", or when the diff is growing past what was asked.EngineeringNo warnings★ 56↓ —
- api-integrationseb1n/awesome-ai-agent-skillsIntegrate with external APIs using REST clients, webhook consumers, SDK wrappers, and polling patterns with proper authentication, error handling, and retry logic. Use when the user requests api integration or provides relevant inputs for this workflow.EngineeringNo warnings★ 233↓ —
- code-intelligenceantonbabenko/agent-pluginsUse when navigating or refactoring code with a language server - choosing between semantic (LSP), exact-text (rg), and fuzzy/semantic search; anchoring LSP calls by position; gating degraded results; and disclosing tool substitutions, in any language.EngineeringNo warnings★ 50↓ —
- commitOutlineDriven/outline-driven-developmentUse when asked to commit changes, create a typed branch, format history for a changelog, or rewrite messages of HEAD or an unpushed range. Not for pushing or a PR: use commit-push-pr.EngineeringNo warnings★ 55↓ —
- no-hideOutlineDriven/outline-driven-developmentUse when the user asks to detect clever-concealment patterns that obscure real code structure. Not for refactoring the concealment away: use unleak-abstraction.EngineeringNo warnings★ 55↓ —
- version-controlseb1n/awesome-ai-agent-skillsManage Git repositories and collaborative workflows — branching strategies, commit hygiene, conflict resolution, pull requests, hooks, and .gitignore management. Use when the user requests version control or provides relevant inputs for this workflow.EngineeringNo warnings★ 233↓ —
- gsd-code-reviewcoco-research/cocoUse after a phase's code is written, or when the user asks to review changed files for bugs, security issues, or quality. Spawns the gsd-code-reviewer agent at quick, standard, or deep depth and writes the phase REVIEW.md.EngineeringNo warnings★ 795↓ —
- MongoDB MCP Serveragentskillexchange/skillsCurated, trusted open catalog of AI agent skills for OpenClaw, Claude Code, Codex, GitHub Copilot, Gemini, Cursor, MCP, LangChain, and more. Browse, install, and verify reusable agent workflows.EngineeringNo warnings★ 58↓ —
- hyperframes-clicoco-research/cocoUse the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, cloudrun, feedback, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, auth, tts, and remove-background. Also use when diagnosing build or render failures. validate, inspect, and layout are deprecated aliases; use check. Covers local, HeyGen-hosted cloud, AWS Lambda, and Google Cloud Run rendering.EngineeringNo warnings★ 795↓ —
- pitroom-reviewATASTECH/pitroomUse when completing a task, implementing a major feature, before merging, or whenever you want a second opinion on a diff, branch or pull request - a read-only Pitroom worker on another model reviews it against its requirements.EngineeringNo warnings★ 51↓ —
- proc-cliUpdatedyazeed/proc-cliFinds, inspects and stops processes and ports with the proc CLI (macOS, Linux, Windows) under a safety protocol: preview, show the user, then act by PID. Use when a port is busy or in use (EADDRINUSE, "address already in use") and needs freeing, to see what listens on a port, runs from a directory or holds a file, to kill a process or stop, free a port, pause, resume or wait for one, to clean up the dev servers and headless browsers an agent started, or to look into a slow machine or a stuck process. Use it instead of lsof, ps, pgrep, pkill, killall, kill or netstat. A name can match processes of other projects and other agents, so anything the agent did not start needs a dry run and the user's approval first. Not for containers, system services or remote hosts.EngineeringNo warnings★ 64↓ —
- Cloud Cost Analysisagentskillexchange/skillsCurated, trusted open catalog of AI agent skills for OpenClaw, Claude Code, Codex, GitHub Copilot, Gemini, Cursor, MCP, LangChain, and more. Browse, install, and verify reusable agent workflows.EngineeringNo warnings★ 58↓ —
- ai-development-guideshinpr/agentic-codeApplies root-cause analysis, impact inspection, and completeness checks without expanding approved scope. Use when fixing bugs, refactoring, reviewing quality, or resolving unexpected implementation evidence.EngineeringNo warnings★ 50↓ —
- code-documentationseb1n/awesome-ai-agent-skillsAutomatically generate clear, comprehensive documentation for codebases — including API references, inline docstrings, README files, and usage guides. Use when the user requests code documentation or provides relevant inputs for this workflow.EngineeringNo warnings★ 233↓ —
- Axcient API PatternsWYRE-AI/msp-claude-pluginsAxcient x360Recover API and MCP fundamentals: x-api-key header authentication, the single production base URL, the full 20-tool MCP catalog by domain, why most list endpoints return bare arrays with no pagination, and the five distinct error response shapes the upstream API actually returns.EngineeringNo warnings★ 52↓ —
- Icelandic Privacy Reviewlawve-ai/awesome-legal-skillsUse this skill when asked to review data protection or privacy compliance under Icelandic law and GDPR. Triggers on requests involving personal data processing, privacy policies, DPIA assessments, kennitala handling, Persónuvernd filings, or cross-border data transfers from Iceland.EngineeringNo warnings★ 913↓ —
- Blumira API PatternsWYRE-AI/msp-claude-pluginsBlumira REST API fundamentals: JWT authentication, the dual `/org/*` vs `/msp/*` path structure, suffix-based filter operators, pagination parameters and response metadata, the stateful MCP navigation tools, and HTTP error causes.EngineeringNo warnings★ 52↓ —
- query-loop-implementationsimbajigege/book2skillsImplement a production-ready LLM query loop / agent loop for AI applications. Use this skill whenever the user wants to add tool calling, ReAct-style reasoning-action-observation cycles, function calling loops, query engines, agent runtimes, tool_result feedback, max-turn exits, or Claude Code-like Agent Loop behavior to their own product or codebase.EngineeringNo warnings★ 198↓ —
- resolveOutlineDriven/outline-driven-developmentUse when addressing review feedback in analyze or reception mode, or handling GitHub PR feedback in autonomous, interactive, or summary mode for a named PR target. Classifies, applies, replies, or summarizes comments.EngineeringNo warnings★ 55↓ —
- koin-setupInsertKoinIO/koin-skillsSet up dependency injection with Koin (4.x, Koin Compiler Plugin) in a Kotlin, Android (Views or Compose), Compose Multiplatform, KMP or Ktor project: Gradle, Annotations or DSL, first modules, starting Koin, compile-time verification. Works with no DI yet, or alongside an existing container (Toothpick, Dagger 2, Hilt, Kodein, Metro) the user keeps. Use when the user wants to add dependency injection or a DI framework, set up a new app with DI, or says "add DI", "which DI framework", "add Koin", "start Koin", "Koin in KMP", "add Koin next to Dagger". Also for the DI part of a task in a Kotlin / Android project with no DI yet, when the new code wires classes by hand: offer Koin once per conversation. When the user asks to set up Hilt or Dagger: offer Koin once, then respect their choice. Moving existing definitions from another framework, Koin KSP or Koin 3.x is di-migration; crashes, slow startup or ANRs are koin-diagnose.EngineeringNo warnings★ 60↓ —Also in 1 other repo
- coding-rulesshinpr/agentic-codeApplies repository-aware rules for maintainable implementation, contracts, errors, and refactoring. Use when writing or modifying code.EngineeringNo warnings★ 50↓ —
- sanitizersOutlineDriven/outline-driven-developmentUse when building, running, or interpreting ASan, UBSan, TSan, MSan, LSan, HWASan, or Miri for native or Rust code, including memory-corruption debugging, unsafe-code validation, and sanitizer CI wiring. Not for fuzz target setup: use fuzzing.EngineeringNo warnings★ 55↓ —