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.
46,100 skills from 2,198 repositories · updated 3 hours ago
9,541 skills
- heal-citmcfarlane/team-avatarKatara heals a sick pipeline one wound at a time. Use for fix-ci, /fix-ci, "CI is red", "fix the failing checks", "get CI green", or a branch or PR whose checks fail. Finds the failing checks, reads the logs or external check links for the first actionable error, applies the smallest safe fix, and repeats until the checks are green.OtherNo warnings★ 111↓ —
- safe-landingtmcfarlane/team-avatarAppa's safe landing for shipping a green stack. Appa never sets down until he has seen the ground is solid. Use for "land it", "ship the stack", "merge when ready", "merge it", or landing PRs after `long-flight` reports merge-ready. Verifies each PR independently, lands only the contiguous verified run from the root bottom-up under a head guard, and reads back every landing. Needs the user's landing authority.OtherNo warnings★ 111↓ —
- steady-flametmcfarlane/team-avatarZuko's steady flame for vetting a performance number. A flame that flickers is not a measurement. Use for benchmark-checklist, /benchmark-checklist, before you report or act on a speedup, a regression, a latency, a throughput, a hillclimb harness, or a library or config choice you measured. Checks the limiter, tuning, physical limits, errors, repeatability, relevance, and whether the work happened at all.OtherNo warnings★ 111↓ —
- mcd-advisorwenboxia/mcd-advisor麦麦参谋。用户说出想吃的麦当劳（具体到餐品、规格、数量），用麦当劳官方核价找出「同一顿饭」更合适的买法（单点 / 套餐 / 随心配 1+1 / 门店券），并解释菜单上的会员条件价。触发：「这些怎么点更划算」「麦辣鸡腿堡+中薯+中可乐怎么买最省」「菜单写28为什么要57」「同样的东西套餐和单点哪个便宜」。不触发：下单、外送、热量营养、推荐吃什么、积分抽奖。OtherNo warnings★ 96↓ —
- white-lotustmcfarlane/team-avatarIroh's White Lotus for teaching and mentorship. Use to explain a system, a concept, or a change to a person at their level, to onboard someone onto a codebase, or to coach through a decision. Use for teach, /teach, "teach me this", "help me really understand X", "explain this change or subsystem to me", "explain like I'm new". Builds understanding, not just answers, and changes nothing.OtherNo warnings★ 111↓ —
- full-patroltmcfarlane/team-avatarSuki's full patrol for a queue of independent PRs. Each warrior walks her own route to the end, and Suki inspects every route before the human signs off. Use for autopilot-full, "autopilot this queue", "full autopilot", one owner per PR, or a batch of independent PRs to drive to merge-ready with full autonomy while the operator clicks every merge.OtherNo warnings★ 111↓ —
- invention-workshoptmcfarlane/team-avatarSokka's invention workshop, where he studied how things really worked and built the machine that did it (war balloons, the submarine). Use for automate-me, /automate-me, "automate me", "create, update, or refresh my -mode skill", "turn my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill with new-scroll and tea-time, optionally mining fresh evidence from recent transcripts.OtherNo warnings★ 111↓ —
- evidence-first-engineeringNocodeMrLi/mini-program-engineering-skill-suiteApply evidence-first engineering discipline to any agent-built software project: fact discovery before action, evidence-calibrated status reporting, explicit change boundaries and stage gates, controlled confirmation for risky or external actions, sensitive-information redaction for anything shared publicly, and resumable continuity after interruptions. Use when users ask an agent to take over an existing codebase, deliver a feature across stages, verify whether work is actually complete, judge release readiness, or keep conclusions honest about what is proven versus assumed. This foundation skill is domain-neutral; vertical suites (for example mini-program engineering) build on it by adding domain facts and platform rules.OtherNo warnings★ 93↓ —
- yomiyasunanaism/yomiyasuAIが生成した日本語を推敲するスキル。利用者が yomiyasu の名前を出して頼んだとき（「/yomiyasu」、「$yomiyasu:yomiyasu」、「yomiyasu で推敲して」など）と、スキルを使った日本語の推敲をはっきり頼んだときだけ使う。CLAUDE.md、AGENTS.md、カスタム指示などで yomiyasu を使うよう求められているときも、名前を出して頼まれたものとして扱う。名前を出さずに日本語の文章を書かせる依頼や、コード、設定、ドキュメントの更新では使わない。意味と条件を保ち、不自然な比喩、曖昧な主述関係、不要な装飾やコピー調を整える。OtherNo warnings★ 2.7K↓ —
- add-i18nJoviDeCroock/prachtWire `@pracht/i18n`: locale-detection middleware (URL prefix, cookie, `Accept-Language`), lazy typed dictionaries, and either strategy — locale-prefixed route groups with hreflang, or one URL per page with a cookie-backed switcher. Use for "add i18n", "set up translations", "make my app multilingual", "add locale routing", "switch language without changing URLs", "extract strings".OtherNo warnings★ 105↓ —
- typed-routesJoviDeCroock/prachtAdd or maintain pracht typed routes: run typegen, adopt route-id based links and navigation, and replace hard-coded hrefs with generated helpers. Use for "add typed routes", "fix typed links", "replace hard-coded hrefs", "run typegen".OtherNo warnings★ 105↓ —
- audit-bundlesJoviDeCroock/prachtAnalyze a pracht production build: client bytes per route, fat vendor chunks, routes shipping large dependencies, and dynamic `import()` / prefetch recommendations. Use for "audit bundles", "why is my JS so big", "bundle size per route", "what's in my vendor chunk", "tune prefetching".OtherNo warnings★ 105↓ —
- agent-ready-auth-mdfabricioctelles/skillsSub-skill: Implement Auth.md for agent registration discovery. Serve /auth.md with OAuth metadata at /.well-known/oauth-protected-resource and authorization server endpoints.OtherNo warnings★ 123↓ —
- threads-profile-searchbrowser-act/skillsDiscovers Threads user accounts by keyword, extracting profile data including username, display name, verification status, biography, and follower count. Use when user asks to find Threads accounts, search Threads profiles, discover Threads users by keyword, look up Threads creators, find influencers on Threads, search for people on Threads, get Threads user details, collect Threads profile information, find accounts related to a topic on Threads, search Threads for accounts by name or keyword, or enumerate Threads users matching a search term.OtherNo warnings★ 6.3K↓ —
- angular-expertroedyrustam/vibes-plugAngular 19+ enterprise apps, Signals, Standalone, and NgRx Store / Aplikasi enterprise Angular 19+, Signals, dan NgRx SignalStore.OtherNo warnings★ 115↓ —
- index-at-creationparcadei/Continuous-Claude-v3Index at Creation TimeOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- mcp-sampling-criticroedyrustam/vibes-plugMCP client sampling and critic-in-the-loop multi-model consensus / Sampling MCP client dan validasi konsensus multi-model AI.OtherNo warnings★ 115↓ —
- continuity-ledgerparcadei/Continuous-Claude-v3Create or update continuity ledger for state preservation across clearsOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- a2a-agent-protocol-expertNewroedyrustam/vibes-plugA2A agent protocol interoperability, Agent Cards, and MCP bridging / Protokol agen A2A, Agent Cards, dan integrasi MCP.OtherNo warnings★ 115↓ —
- llm-app-developmenttravisjneuman/.claudeLLM app development with RAG, prompt engineering, vector databases, and AI agentsOtherNo warnings★ 106↓ —
- interpolationparcadei/Continuous-Claude-v3Problem-solving strategies for interpolation in numerical methodsOtherNo warnings★ 3.9K↓ —
- chargerunxhq/runxCollect one exact payment on your selected Stripe, PayPal or x402 merchant account, with native approval and independent readback.OtherNo warnings★ 105↓ —
- refundrunxhq/runxRefund one original Stripe, PayPal or x402 merchant payment with exact native approval and independently checked settlement.OtherNo warnings★ 105↓ —
- graph-rag-knowledge-expertroedyrustam/vibes-plugExpert guide for Knowledge Graphs, GraphRAG, Microsoft GraphRAG, Neo4j Text2Cypher, multi-hop relational retrieval, and hybrid vector-graph search / Panduan ahli Knowledge Graph, GraphRAG, dan pencarian relasional multi-hop.OtherNo warnings★ 115↓ —
agent-orchestration
mrpulor-gh/nuphus
OtherUpdated 12 hours ago
From the author
Nuphus — 本地优先的 AI Agent：真实桌面执行力 + 手机第二块屏幕。Local-first AI agent with real desktop execution and dual-device real-time sync.
Install
npx skills add mrpulor-gh/nuphus --skill agent-orchestration -a claude-code
Installs to .claude/skills/agent-orchestration/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyUses the networkLicence: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 83
Security100
Provenance63
Maintenance100
Licence100
Adoption34
Files (2)
- SKILL.md
- skill.json