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.
46,700 skills from 2,243 repositories · updated 11 hours ago
5,805 skills
- refine-pr-revieweai-org/agent-toolkitTriage a fetched PR review with the user, comment by comment, drafting each reply and producing a REQUIREMENTS file for the accepted code changes. Takes the PR-REVIEW file produced by fetch-pr-review, or a PR URL. Invoke manually only.EngineeringNo warnings★ 76↓ —
- self-revieweai-org/agent-toolkitSelf-review your changeset until merge-ready, with a fresh-context reviewer and a compact report for the PR.EngineeringNo warnings★ 76↓ —
- agent-ready-ardfabricioctelles/skillsSub-skill: Implement ARD (Agentic Resource Discovery). Publish /.well-known/ai-catalog.json so agents can discover MCP servers, A2A agents, skills and API tools (agenticresourcediscovery.org / ai-catalog).EngineeringNo warnings★ 122↓ —
- handoff-claudeclaude-world/director-mode-liteContinue a task in Claude Code through a portable Director handoff packet. Use when work started in Codex CLI or Grok Build should move to Claude, or when a fresh Claude session needs the current decisions and verification evidence.EngineeringNo warnings★ 80↓ —
- whizard-auditingkubesphere/kubesphereUse when working with WizTelemetry Auditing extension for KubeSphere, including installation, configuration, and audit query APIEngineeringNo warnings★ 17.1K↓ —
- generic-code-reviewertravisjneuman/.claudeReview code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Supports any tech stack - HTML/CSS/JS, React, TypeScript, Node.js, Python, NestJS, Next.js, and more. Use when completing features, before commits, or reviewing pull requests.EngineeringNo warnings★ 106↓ —
- verify-understandingeai-org/agent-toolkitVerify the engineer is ready to implement a feature through a teach-back conversation over its ticket review.EngineeringNo warnings★ 76↓ —
- jq-processingcxcscmu/SkillLearnBenchUsing jq to parse, filter, and aggregate JSON data from CLI tools for generating reports.EngineeringNo warnings★ 91↓ —
- setup-api-keysonilo-ai/skillsGuides users through connecting to Sonilo — signing in with `sonilo login` (OAuth, no key), the remote OAuth plugin for Claude Code or Muse Code, or an API key for CI and headless use. Use when the user needs to configure Sonilo, wants to sign in or connect their Sonilo account, when Sonilo tools are missing, or when a call fails because no key or credential is available. First checks what already works, and only runs full setup when needed.EngineeringNo warnings★ 117↓ —
- python-scala-oopcxcscmu/SkillLearnBenchGuide for translating Python classes, inheritance, ABC, generics and builder patterns to idiomatic Scala.EngineeringNo warnings★ 91↓ —
- github-cli-queriescxcscmu/SkillLearnBenchQuery GitHub repositories for PRs and issues using gh CLI with date filtering and structured output.EngineeringNo warnings★ 91↓ —
- nlp-project-setupcxcscmu/SkillLearnBenchSet up Python environment for NLP and preference optimization projects.EngineeringNo warnings★ 91↓ —
- whizard-eventskubesphere/kubesphereUse when working with WizTelemetry Events extension for KubeSphere, including installation, configuration, and event query APIEngineeringNo warnings★ 17.1K↓ —
- executive-update-reviewitseffi/agentic-osImprove executive updates for clarity, decision impact, and concise speaking flow.EngineeringNo warnings★ 117↓ —
- code-optimizerArabelaTso/Skills-4-SEAnalyzes and optimizes code for better performance, memory usage, and efficiency. Use when code is slow, memory-intensive, or inefficient. Supports Python and Java optimization including execution speed improvements, memory reduction, database query optimization, and I/O efficiency. Provides before/after examples with detailed explanations of why optimizations work, complexity analysis, and measurable performance improvements.EngineeringNo warnings★ 259↓ —
- python-pypdfcxcscmu/SkillLearnBenchGuide on using the Python pypdf library to read, write, and fill PDF forms programmatically.EngineeringNo warnings★ 91↓ —
- demo-cmdAdyen/agent-marketplaceagent-marketplace is a command-line tool that installs shared AI agent resources into the AI coding tools you useEngineeringNo warnings★ 74↓ —
- git-patch-workflowcxcscmu/SkillLearnBenchCreating, managing, and applying unified diff patches with Git for source code modifications.EngineeringNo warnings★ 91↓ —
- fresh-eyes-revieweai-org/agent-toolkitFresh-eyes review of a changeset by a fresh-context agent — catches what the authoring context reads past.EngineeringNo warnings★ 76↓ —
- liuyao-yijingaAAaqwq/AGI-Super-Team六爻易经占卜器，基于京房纳甲体系，模拟铜钱起卦，完成纳甲装卦（天干地支、世应、六亲、六神）， 通过用神旺衰和生克制化断卦。当用户提及「六爻」「易经占卜」「铜钱起卦」「纳甲」「帮我起一卦」 「六爻预测」时触发。装卦为确定性计算 + LLM 综合断卦，无外部 API 依赖。 不适用于：梅花易数、奇门遁甲、星座运势、塔罗占卜、八字命理等其他领域 → 建议使用 fortune-hub 路由。EngineeringNo warnings★ 111↓ —
- code-reviewerclaude-world/director-mode-liteCode review knowledge base: quality, security (OWASP Top 10), error-handling, performance, and test-coverage checklists with severity-ranked output format. Use when reviewing code changes, PRs, or before commits. Loaded automatically by the code-reviewer agent.EngineeringNo warnings★ 80↓ —
- handoff-grokclaude-world/director-mode-liteContinue a task in xAI Grok Build using the shared Director handoff packet. Use when the user says to use Grok, requests a Grok review, or wants Grok Build to take over work started in Claude Code or Codex CLI.EngineeringNo warnings★ 80↓ —
- handoff-codexclaude-world/director-mode-liteContinue a task in OpenAI Codex CLI through a portable Director handoff packet. Use when the user asks Codex to take over, wants an independent Codex implementation or review, or needs to preserve decisions and verification while changing CLIs.EngineeringNo warnings★ 80↓ —
- python-scala-idiomscxcscmu/SkillLearnBenchGuide for writing idiomatic Scala including naming conventions, error handling, and pattern matching.EngineeringNo warnings★ 91↓ —