Skill-uri pentru agenți pe care le poți verifica înainte să le instalezi
Skill-uri SKILL.md publice din depozite GitHub cu peste 50 de stele și de la producători, scanate și evaluate. Instalează oricare dintre ele cu o singură comandă în Claude Code, Cursor, Codex, GitHub Copilot sau Gemini CLI.
44.590 de skill-uri din 2.116 depozite · actualizat acum 11 minute
9.610 skill-uri
- ln-96-error-handling-engineerlevnikolaevich/claude-code-skillsImplements safe error boundaries, cancellation and user recovery contracts; not telemetry pipelines or durable retry machinery.AlteleFără avertismente★ 583↓ —
- ln-98-mutation-reliability-engineerlevnikolaevich/claude-code-skillsImplements transactions, idempotency and interrupted-operation recovery; not schema migration or a mandatory background-job platform.AlteleFără avertismente★ 583↓ —
- ln-95-resource-authorization-engineerlevnikolaevich/claude-code-skillsImplements permissions and tenant or owner scoped resource access while preserving approved grants; not authentication or role redesign.AlteleFără avertismente★ 583↓ —
- health-checkbitwize-music-studio/claude-ai-music-skillsRuns plugin health checks (venv packages, skill registration, and album slug collisions). Use when the user asks to check plugin health, verify setup, or troubleshoot missing skills.AlteleFără avertismente★ 586↓ —
- thinking-cynefintjboudreaux/cc-thinking-skillsWhen the right response mode is unclear, classify the cause-effect domain first; decompose disorder.AlteleFără avertismente★ 1,7 K↓ —
- lyric-reviewerbitwize-music-studio/claude-ai-music-skillsReviews lyrics against a quality checklist before Suno generation. Use before generating tracks to catch rhyme, prosody, pronunciation, and structural issues.AlteleFără avertismente★ 586↓ —
- build-workspace-docsMoizIbnYousaf/ai-agent-skillsUse when regenerating README.md and WORK_AREAS.md in a managed library workspace. Always dry-run first to preview changes.AlteleFără avertismente★ 1,2 K↓ —
- migrate-skills-between-librariesMoizIbnYousaf/ai-agent-skillsUse when moving skills between library workspaces or upgrading from a personal library to a team library. Export from one workspace, import into another.AlteleFără avertismente★ 1,2 K↓ —
- ln-57-persistence-auditorlevnikolaevich/claude-code-skillsAudits queries, transactions, consistency and persistence resource lifetimes; read-only.AlteleFără avertismente★ 583↓ —
- ln-11-opportunity-evaluatorlevnikolaevich/claude-code-skillsEvaluates new product opportunities through demand, channels and economics before committing to build.AlteleFără avertismente★ 583↓ —
- ln-53-documentation-auditorlevnikolaevich/claude-code-skillsAudits documentation and comments for trust, coverage, consistency and freshness; read-only.AlteleFără avertismente★ 583↓ —
- audit-library-healthMoizIbnYousaf/ai-agent-skillsUse when checking the overall health of a skills library. Run doctor, validate, check for stale skills, and verify generated docs are in sync.AlteleFără avertismente★ 1,2 K↓ —
- ln-44-performance-optimizerlevnikolaevich/claude-code-skillsProfiles and improves a measured performance bottleneck; retains only verified improvements.AlteleFără avertismente★ 583↓ —
- ln-52-delivery-reviewerlevnikolaevich/claude-code-skillsReviews a completed change for acceptance, regressions and release risk; read-only, not a whole-codebase audit.AlteleFără avertismente★ 583↓ —
- abide-compilecoldteadotai/abideCompile a repository's instruction files (AGENTS.md, CLAUDE.md and friends) into an Abide rubric, then validate and calibrate it.AlteleFără avertismente★ 606↓ —
- ln-45-benchmark-comparatorlevnikolaevich/claude-code-skillsCompares tools or implementations through controlled benchmarks and independent correctness checks.AlteleFără avertismente★ 583↓ —
- ln-64-community-announcerlevnikolaevich/claude-code-skillsDrafts or publishes authorized, fact-checked GitHub Discussions announcements; does not create releases.AlteleFără avertismente★ 583↓ —
- storyzenstory-ai/oh-story-claudecode网络小说工具箱主入口。根据用户需求自动路由到对应 skill，并可启动本地 Dashboard。触发方式：/story、$story、/story dashboard、/网文、「我想写小说」「记住我的写作习惯」「打开工作台」「检查更新」。AlteleFără avertismente★ 8 K↓ —Apare și în 1 alt depozit
- update-installed-skillsMoizIbnYousaf/ai-agent-skillsUse when syncing or updating previously installed skills to their latest version. Always dry-run updates before applying, and check for breaking changes.AlteleFără avertismente★ 1,2 K↓ —
- story-deslopzenstory-ai/oh-story-claudecode网文去AI味。从表达、叙事用笔、故事因果三层诊断并修复文本，保留作者文风与已定剧情。触发方式：/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。AlteleFără avertismente★ 8 K↓ —Apare și în 1 alt depozit
- story-long-scanzenstory-ai/oh-story-claudecode长篇网文扫榜。分析起点、番茄、晋江、七猫等平台排行榜与新书数据，提炼市场趋势与热门题材。触发方式：/story-long-scan、/长篇扫榜、「长篇什么火」「起点排行」「扫七猫新书」。AlteleFără avertismente★ 8 K↓ —Apare și în 1 alt depozit
- create-release-checklistposit-dev/skillsCreate a release checklist and GitHub issue for an R package. Use when the user asks to "create a release checklist" or "start a release" for an R package.AlteleFără avertismente★ 547↓ —
- story-short-scanzenstory-ai/oh-story-claudecode短篇网文扫榜。分析知乎盐言、七猫、黑岩、点众等平台热门短篇数据，捕捉风口题材。触发方式：/story-short-scan、/短篇扫榜、「短篇什么火」「知乎故事排行」。AlteleFără avertismente★ 8 K↓ —Apare și în 1 alt depozit
- ln-72-product-outcome-evaluatorlevnikolaevich/claude-code-skillsEvaluates observed product outcomes against a prior hypothesis; does not run experiments or change user treatment.AlteleFără avertismente★ 583↓ —