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.
47,938 skills from 2,309 repositories · updated 6 minutes ago
6,159 skills
- refactorarbiterForge/codeArbiterRestructure code without changing observable behavior: rename, extract, inline, move, deduplicate, or replace an internal implementation with an equivalent one. Prove parity through unchanged pre-existing tests. Not for new behavior, bug fixes, explanation-only questions, or committing finished work.EngineeringNo warnings★ 149↓ —
- refactorarbiterForge/codeArbiterRestructure code without changing observable behavior: rename, extract, inline, move, deduplicate, or replace an internal implementation with an equivalent one. Prove parity through unchanged pre-existing tests. Not for new behavior, bug fixes, explanation-only questions, or committing finished work.EngineeringNo warnings★ 149↓ —
- debugarbiterForge/codeArbiterInvestigate an unexplained defect or unexpected behavior without changing application code. Use for root-cause diagnosis and an evidence-backed handoff, including a bounded unresolved result. Not for implementing a known fix, new features, or explanation-only questions.EngineeringNo warnings★ 149↓ —
- refactorarbiterForge/codeArbiterRestructure code without changing observable behavior: rename, extract, inline, move, deduplicate, or replace an internal implementation with an equivalent one. Prove parity through unchanged pre-existing tests. Not for new behavior, bug fixes, explanation-only questions, or committing finished work.EngineeringNo warnings★ 149↓ —
- refactorarbiterForge/codeArbiterRestructure code without changing observable behavior: rename, extract, inline, move, deduplicate, or replace an internal implementation with an equivalent one. Prove parity through unchanged pre-existing tests. Not for new behavior, bug fixes, explanation-only questions, or committing finished work.EngineeringNo warnings★ 149↓ —
- dispatching-parallel-agentsarbiterForge/codeArbiterThe parallel fan-out primitive. Routed to by any skill or command that splits work across independent units and dispatches an agent per unit — subagent-driven-development, /sprint, parallel /review. It owns the dispatch/collect/funnel discipline: bound concurrency, isolate units, collect every result, dedupe overlap, and funnel through finding-triage then the read-only verdict-aggregator. Raw agent output is never consumed before the funnel runs; an agent that errors records its unit as incomplete without corrupting the batch.EngineeringNo warnings★ 149↓ —
- swebench-solverskillberry-ai/cap-evolveUse when fixing a bug in an open-source repository given a GitHub issue description. Analyzes the problem, locates the relevant code, and produces a minimal unified diff patch.EngineeringNo warnings★ 66↓ —
- Rust Crates.io Exploreragentskillexchange/skillsSearches the crates.io REST API for Rust crate metadata, version diffs, and feature flag documentation. Integrates with docs.rs API for inline rustdoc retrieval and lib.rs category browsing.EngineeringNo warnings★ 58↓ —
- SonarQube PR Gateagentskillexchange/skillsIntegrates SonarQube quality gates into pull request workflows via the SonarQube Web API /api/qualitygates/project_status. Blocks merges when code smells, duplications, or coverage thresholds fail and posts inline annotations using the GitHub Checks API.EngineeringNo warnings★ 58↓ —
- CycloneDX SBOM Generatoragentskillexchange/skillsGenerates Software Bill of Materials in CycloneDX format using cdxgen and Syft. Scans npm, pip, and Go modules for known CVEs via OSV.dev API integration.EngineeringNo warnings★ 58↓ —
- debugarbiterForge/codeArbiterInvestigate an unexplained defect or unexpected behavior without changing application code. Use for root-cause diagnosis and an evidence-backed handoff, including a bounded unresolved result. Not for implementing a known fix, new features, or explanation-only questions.EngineeringNo warnings★ 149↓ —
- ca-debugarbiterForge/codeArbiterInvestigate an unexplained defect or unexpected behavior without changing application code. Use for root-cause diagnosis and an evidence-backed handoff, including a bounded unresolved result. Not for implementing a known fix, new features, or explanation-only questions.EngineeringNo warnings★ 149↓ —
- ca-spikearbiterForge/codeArbiterExploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or /ca-feature.EngineeringNo warnings★ 149↓ —
- karpathy-guidelinescoco-research/cocoPointer to the upstream skill for behavioural guidelines that reduce common LLM coding mistakes, installed from upstream.EngineeringNo warnings★ 795↓ —
- debugarbiterForge/codeArbiterInvestigate an unexplained defect or unexpected behavior without changing application code. Use for root-cause diagnosis and an evidence-backed handoff, including a bounded unresolved result. Not for implementing a known fix, new features, or explanation-only questions.EngineeringNo warnings★ 149↓ —
- clerk-setupclerk/skillsSet up Clerk authentication in any project with the Clerk CLI and official framework quickstarts. Use when adding Clerk, initializing Clerk, scaffolding a new app with Clerk, or migrating an existing authentication system to Clerk.OfficialEngineeringReview first★ 89↓ —
- Datto BCDR API PatternsWYRE-AI/msp-claude-pluginsDatto BCDR (Backup Portal) REST API fundamentals: public/private key HMAC-SHA256 request signing, the /v1 endpoint surface, pagination, appliance/agent hierarchy, and screenshot verification retrieval.EngineeringNo warnings★ 52↓ —
- ca-refactorarbiterForge/codeArbiterRestructure code without changing observable behavior: rename, extract, inline, move, deduplicate, or replace an internal implementation with an equivalent one. Prove parity through unchanged pre-existing tests. Not for new behavior, bug fixes, explanation-only questions, or committing finished work.EngineeringNo warnings★ 149↓ —
- Mimecast API PatternsWYRE-AI/msp-claude-pluginsMimecast MCP fundamentals: the available tool catalog, OAuth 2.0 client-credentials authentication, regional API endpoints, pagination, rate limiting, and error handling.EngineeringNo warnings★ 52↓ —
- Datto RMM JobsWYRE-AI/msp-claude-pluginsDatto RMM job execution: quick jobs vs. scheduled vs. policy jobs, the job status lifecycle, component scripts and their variables, and stdout/stderr/exit-code result handling.EngineeringNo warnings★ 52↓ —
- commit-gatearbiterForge/codeArbiterCreate a verified local Git commit when committing changes is requested. Not for explaining commit history, drafting a message only, or postponing a commit. Applies every commit gate and never implies a push or PR.EngineeringNo warnings★ 149↓ —
- 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↓ —
- 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↓ —
- lov-translation-reviewlovstudio/skillsReview Chinese-to-English translations for accuracy, grammar, terminology, and consistency. Produces a structured review report with prioritized issues. Trigger when: user provides a Chinese document and its English translation for review/checking/proofreading, or mentions "翻译检查", "翻译审校", "translation review", "translation check", "proofread translation".EngineeringNo warnings★ 73↓ —