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.
45,604 skills from 2,205 repositories · updated 15 hours ago
5,657 skills
- py-lintGoldziher/ai-rulezLint and format Python with pinned tool versions.EngineeringNo warnings★ 163↓ —
- nw-pdr-review-criterianWave-ai/nWaveEvidence quality validation and decision gate criteria for product discovery reviewsEngineeringNo warnings★ 622↓ —Also in 1 other repo
- incident-response-patternsvibeeval/vibecosystemIncident severity classification, runbook templates, root cause analysis, and post-incident reviewEngineeringNo warnings★ 540↓ —
- tidy-branchesGoldziher/ai-rulezCleans up stale git branches. Use when the repository has many merged branches.EngineeringNo warnings★ 163↓ —
- dimensional-analysistrailofbits/skillsAudits code for unit and decimal-scaling bugs and annotates it with dimensional comments recording the units of each value. Use when someone asks to audit or review code for unit confusion, decimals or scaling mismatches, WAD/RAY scale errors, or the wrong token's decimals; to annotate units in a codebase; or to perform a dimensional analysis of a DeFi protocol, offchain code, or other arithmetic-heavy codebase. Catches formulas that combine values carrying different units or scales.EngineeringNo warnings★ 7.8K↓ —
- scikit-learnforyourhealth111-pixel/Vibe-SkillsMachine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.EngineeringNo warnings★ 3.8K↓ —
- zeroize-audittrailofbits/skillsDetects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C/C++/Rust code handling secrets, keys, passwords, or other sensitive data.EngineeringNo warnings★ 7.8K↓ —
- lcx-contribute-bug-fixcode-yeongyu/oh-my-openagentContribute a verified bug fix for LazyCodex, lazycodex-ai, omo-codex, bundled Codex skills, or upstream Codex CLI bugs. Opens a fork PR only for upstream openai/codex; LazyCodex-owned defects become a verified-fix issue on code-yeongyu/lazycodex (never a PR — that repo is a generated distribution mirror). Use when the user asks to fix a bug, contribute a bug fix, contribute to fix bug, open a PR for a bug, or debug and PR a LazyCodex/Codex defect.EngineeringNo warnings★ 70.3K↓ —
- nw-por-review-criterianWave-ai/nWaveReview dimensions and bug patterns for journey artifact reviewsEngineeringNo warnings★ 622↓ —Also in 1 other repo
- diagramming-codetrailofbits/skillsGenerates Mermaid diagrams from Trailmark code graphs. Produces call graphs, class hierarchies, module dependency maps, containment diagrams, complexity heatmaps, and attack surface data flow visualizations. Use when visualizing code architecture, drawing call graphs, generating class diagrams, creating dependency maps, producing complexity heatmaps, or visualizing data flow and attack surface paths as Mermaid diagrams.EngineeringNo warnings★ 7.8K↓ —
- clerk-tanstack-patternsclerk/skillsTanStack React Start auth patterns with @clerk/tanstack-react-start - createServerFn, beforeLoad guards, loaders, Vite plugin, server middleware. Triggers on: TanStack auth, createServerFn clerk, beforeLoad protection, TanStack Start middleware.OfficialEngineeringNo warnings★ 89↓ —
- sentryforyourhealth111-pixel/Vibe-SkillsUse when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.EngineeringNo warnings★ 3.8K↓ —Also in 1 other repo
- clerk-react-patternsclerk/skillsReact SPA auth patterns with @clerk/react for Vite/CRA - ClerkProvider setup, useAuth/useUser/useClerk hooks, React Router protected routes, custom sign-in flows. Triggers on: Vite Clerk setup, React Router auth, useAuth hook, protected route, custom sign-in form React.OfficialEngineeringNo warnings★ 89↓ —
- clerk-nuxt-patternsclerk/skillsNuxt 3 auth patterns with @clerk/nuxt - middleware, composables, server API routes, SSR. Triggers on: Nuxt auth, useAuth composable, clerkMiddleware Nuxt, server API Clerk, Nuxt route protection.OfficialEngineeringNo warnings★ 89↓ —
- cost-optimization-patternsvibeeval/vibecosystemCloud cost optimization, token/API cost tracking, build time optimization, and FinOps patternsEngineeringNo warnings★ 540↓ —
- bili-clikukemc/bili-cliOperate a Bilibili (B站/哔哩哔哩) account through the `bili` CLI — watch and understand videos (subtitles, AI summary, frames, speech-to-text), browse recommendations/trending/hot search, read the notification inbox, reply to comments with real @mentions, send private messages, post dynamics, upload videos with the AI-content declaration. Use when the user mentions Bilibili, B站, 哔哩哔哩, BV/av IDs, b23.tv or bilibili.com links, UP主, 弹幕, 评论区, 私信, 动态, 投稿, or asks you to run, monitor or post on their Bilibili account.EngineeringNo warnings★ 211↓ —
- nw-dor-validationnWave-ai/nWaveDefinition of Ready checklist criteria, antipattern detection patterns, UAT quality rules, and domain language enforcement for product owner reviewEngineeringNo warnings★ 622↓ —Also in 1 other repo
- session-analysis-patternsvibeeval/vibecosystemClaude Code session analysis, tool call patterns, efficiency metrics, and anti-pattern detectionEngineeringNo warnings★ 540↓ —
- springboot-verificationvibeeval/vibecosystemAI software team for Claude Code - 138 agents, 295 skills, 73 hooks. Self-learning, multi-agent swarm, autonomous skill evolution.EngineeringNo warnings★ 540↓ —
- external-skills-catalogvibeeval/vibecosystemCurated catalog of 60+ external Claude Code skills across 8 categories with quality rankings, install instructions, and fallback strategiesEngineeringNo warnings★ 540↓ —
- clerk-react-router-patternsclerk/skillsReact Router v7/v8 patterns with Clerk — rootAuthLoader, getAuth in loaders, clerkMiddleware, protected routes, SSR user data, org switching. Triggers on: react-router auth, rootAuthLoader, getAuth loader, react-router protected route, loader authentication, SSR auth react-router, useNavigate may be used only in the context of a Router.OfficialEngineeringNo warnings★ 89↓ —
- api-versioning-patternsvibeeval/vibecosystemAPI versioning strategies, breaking change detection, deprecation lifecycle, and migration guidesEngineeringNo warnings★ 540↓ —
- java-coding-standardsvibeeval/vibecosystemAI software team for Claude Code - 138 agents, 295 skills, 73 hooks. Self-learning, multi-agent swarm, autonomous skill evolution.EngineeringNo warnings★ 540↓ —
- diff-review-strategyvibeeval/vibecosystemPR size-based review depth, performance review checklist, architecture conformance checks, and framework-specific review patterns.EngineeringNo warnings★ 540↓ —