Agent skills

Skills for codex

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
9,699 found
4,1774,224 · page 88 / 203
redis-memory-backendRedis backend for conversation state persistence and cachinga5c-aiwritesredux-toolkitRedux Toolkit patterns including slice creation, async thunks, RTK Query, state normalization, and DevTools integration.a5c-aiwritesrefactoring-assistantSuggest and guide application of refactoring patterns to improve code qualitya5c-aiwritesreference-media-analysisProvider-independent reference media analysis for generated-media production. Use when an agent must analyze reference images…calesthiorefine-critique-loopUse this plugin when the user has an existing Open Design artifact and wants targeted critique, patching, brand tightening…nexu-iorefinedCarefully curated, modern minimal style with elegant serif typography and understated, sophisticated palettes.bergsideRegister AllocationExpert skill for register allocation algorithms including graph coloring, linear scan, and spill code generationa5c-aiwritescommunity-registry-starterA small community registry starter plugin used to verify Open Design marketplace install flows.nexu-ioremixRemix patterns including loaders, actions, nested routing, progressive enhancement, and deployment strategies.a5c-aiwritesremote-configRemote configuration skill for feature flags.a5c-aiwritesremotion-best-practicesBest practices for Remotion - Video creation in Reactgooseworks-airemotion-video-compositionProvider-independent production workflow for assembling generated or sourced media into React/Remotion videos. Use when an agent…calesthioREPL DevelopmentExpert skill for building interactive REPLs with rich editing and evaluation featuresa5c-aiwritesreproduce-frontend-bugBuild a bounded, replayable browser or UI bug reproduction from GitHub Issues, Jira, Aone, user-provided exports, screenshots…QoderAIreq-to-executable-prompt將使用者的自然語言需求,轉換成「Codex 可直接執行」的工程指令 prompt。 輸出內容包含:背景、明確目標、可驗收條件、操作步驟、不可違反的限制、與交付格式。 適用於任何語言、任何 repo、任何專案階段。majiayu000request-debuggerHTTP request/response debugging and inspection toolsa5c-aiwritesrequesting-code-reviewUse when completing tasks, implementing major features, or before merging to verify work meets requirements.a5c-airequesting-code-reviewPrepare and request a code review after implementation or before merge by assembling scope, requirements, git range, and reviewer…foryourhealth111-pixelrequesting-code-reviewUse when requesting independent code review, after implementation slices, before merging high-risk work, or when verification…GanyuanRanrequesting-code-reviewUse when completing tasks, implementing major features, or before merging to verify work meets requirementssickn33requirements-interviewInteractive PM interview with expertise-adaptive questioning for requirements elicitationa5c-aiwritesresearch-first-devResearch-first development methodology that investigates existing solutions, brainstorms alternatives, and evaluates trade-offs…a5c-aiwritesresearch-orchestrationParallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis…a5c-aiwritesresemble-chatterboxUse Resemble AI Chatterbox for text-to-speech and voice-cloning workflows, including local open-weight Chatterbox, Chatterbox…calesthioresemble-detectDeepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply…Prat011responsive-imageGenerate responsive image sets with srcset, WebP/AVIF conversion, and art directiona5c-aiwritesrest-api-designRESTful API design principles, versioning, pagination, HATEOAS, and documentation.a5c-aiwritesrestaurant-bookingBook restaurant reservations via browser automation. Use when asked to make dinner reservations, book a table, or find…gooseworks-airetroThrowback design with vintage-inspired typography, high-contrast retro palettes, and nostalgic visual elements.bergsiderevenuecat-testingUse when testing RevenueCat purchases/subscriptions, setting up sandbox testing, debugging a purchase/restore/trial, verifying…evancareview-and-planUse when the user asks Codex to review a repository for improvement opportunities, feature inspiration, roadmap ideas, or…Optim-Agentreview-animationsUse when reviewing animation and motion code against a strict craft, performance, accessibility, and interaction-quality bar.sickn33review-intelligence-digestScrape G2, Capterra, and Trustpilot reviews for your product and competitors, then extract recurring themes, objections, proof…gooseworks-aireview-itCode review closeout for Claude Code, Codex, OpenCode, DeepSeek TUI, and Antigravity CLI: local dirty changes, branch vs main…smallnestreview-seo-page从目标用户的真实搜索场景出发,对抗式审查并修改 SEO 页面,找出搜索意图偏离、低信息量、批量同构、重复转化、AI 腔、术语漂移、无依据主张、metadata 问题和配图场景错位。需要审查 SEO 内容价值、降低 AI…tsingyuaireview-seo-performance使用 Bing Webmaster 页面与查询数据、索引状态、产品结果和 Bing AI Performance 证据复盘 SEO 页面,诊断收录、排名、点击率、意图、内容、转化和 AI 引用问题。需要比较周期表现、分析 citations、cited…tsingyuaireview-swarmParallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or…sickn33rewrite-planAuthor a long-running multi-file rewrite plan that subsequent patch-edit + diff-review + build-test stages will execute, with…nexu-ioara-rigor-reviewerPerforms ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence…Orchestra-Researchrisk-metrics-calculationCalculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk…sickn33risk-metrics-calculationCalculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk…wshobsonrisoA playful, joyful, two-color risograph print aesthetic built on a single warm off-white paper surface running through every…bergsideReinforcement Learning SkillRL training for robot control using simulation with sim-to-real transfera5c-aiwritesroadmap-managementRoadmap parsing, analysis, and mutation operations for ROADMAP.md. Handles phase and milestone lifecycle including add, insert…a5c-aiwritesRoadmap VisualizationGenerate roadmap visualizations and planning artifacts for product planninga5c-aiwritesroadrunner-import-sceneImport HD Map or OpenDRIVE files into a RoadRunner scene using MATLAB. Use when loading driving scenes in RoadRunner or…matlabroblox-datastoresPersist player data in Roblox with DataStoreService: GetDataStore, GetAsync/ SetAsync/UpdateAsync/IncrementAsync wrapped in…gamedev-skillsroblox-luauScript a Roblox experience in Luau: get services, create and parent Instances, connect events, run server Scripts vs client…gamedev-skills
← Prev88 / 203Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going