Agent skills

Skills for codex

9,782 skills that declare support for codex. The SKILL.md format is shared, so most of these work in the other agents too — the declaration only says where the author tested it.

Toolclaude-code 63,296codex 9,782cursor 7,187copilot 2,384windsurf 127cline 83
CategoryWorkflow & Productivity 11,752AI & Agents 4,985Data & Analytics 4,761Code Review & Quality 2,986Security 2,828Backend & API 2,504Design & Presentation 2,373Documentation 2,183Content & Marketing 2,060Testing & QA 1,778DevOps & Cloud 1,275Databases 1,133Frontend 1,043Business & Finance 724Media & Video 514Other 21,532
9,782 found
9,2179,264 · page 193 / 204
targeting-ligand-designerActive targeting skill for designing and validating nanoparticle targeting strategiesa5c-aiwritestask-decompositionBreaks down complex software, writing, or research tasks into small, atomic, independently completable units with dependency…rohitg00task-scheduling-cron-jobsImplement reliable task scheduling and cron job systems — distributed schedulers, missed-job recovery, and job monitoring.a5c-aiwritestask-to-prdConvert a raw task (tracker ticket, email, or text) into a fully characterized PRD. User-facing entry point that dispatches to…a5c-aidesign-taste-frontendAnti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design…Leonxlnxdesign-taste-frontend-v1The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is…Leonxlnxtavily-automationAutomate Tavily tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtavily-usageThis skill should be used when user asks to "search the web", "fetch content from URL", "extract page content", "use Tavily…fcakyontavily-webWeb search, content extraction, crawling, and research capabilities using Tavily API. Use when you need to search the web for…sickn33tax-provision-calculatorASC 740 income tax provision calculation skill with deferred tax analysisa5c-aiwritestaxjar-automationAutomate Taxjar tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtcm-constitution-analyzer分析中医体质数据、识别体质类型、评估体质特征,并提供个性化养生建议。支持与营养、运动、睡眠等健康数据的关联分析。sickn33writestco-calculatorTotal Cost of Ownership calculation skill for comprehensive supplier and sourcing decision analysisa5c-aiwritestddThe test-first gate. Routed to by /feature (after the spec is approved), /fix, and /refactor before any implementation code is…arbiterForgetdd-guideTest-first development route for TDD, writing failing tests first, RED -> GREEN -> REFACTOR, and behavior-changing…foryourhealth111-pixeltdd-orchestratorMaster TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive…sickn33tdd-repairTest-Driven Repair — given a failing test, spawn a bounded headless `claude -p` (Read/Edit/Bash only) that makes the test pass…ruvnetwritestddDrive a change through a red-green-refactor loop - failing test first, minimal code to pass, then clean up. Use when implementing…rohitg00tdd-workflowUse this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage…mturactdd-workflowTDD London School workflow -- mock-first, outside-in test developmentruvnetwritestdd-workflowTest-Driven Development workflow principles. RED-GREEN-REFACTOR cycle.sickn33tdd-workflowsUse when working with tdd workflows tdd cycle (Alias for tdd-workflows-tdd-cycle)sickn33tdd-workflows-tdd-cycleUse when working with tdd workflows tdd cyclesickn33tdd-workflows-tdd-redGenerate failing tests for the TDD red phase to define expected behavior and edge cases.sickn33tdd-workflows-tdd-refactorUse when working with tdd workflows tdd refactorsickn33team-assignAssign marketing tasks to team members by scoring role fit, channel expertise, current utilization, and region alignment; also…indranilbanerjeeteam-builderInteractive agent picker for composing and dispatching parallel teamsmturacteam-composition-analysisDesign optimal team structures, hiring plans, compensation strategies, and equity allocation for early-stage startups from…sickn33teamcamp-automationAutomate Teamcamp tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtech-debt-auditThorough, file-cited technical debt audit across 9 dimensions using AST-grep (tree-sitter), grep, language-native tooling, and…code-yeongyutech-seo-auditRun a technical SEO audit of a site — crawlability, indexation, Core Web Vitals, redirects, structured data, mobile, security —…indranilbanerjeetech-stack-scannerAutomated technical architecture review, security assessment, scalability analysisa5c-aiwritestechnical-analysisImplement technical analysis indicators and charting patterns — moving averages, RSI, MACD, candlestick patterns, and signal…a5c-aiwritestechnical-change-trackerTrack code changes with structured JSON records, state machine enforcement, and AI session handoff for bot continuitysickn33technical-leadershipExercise technical leadership — driving architectural decisions, mentoring engineers, managing technical debt, and aligning…a5c-aiwritestei-text-encodingEncode texts following Text Encoding Initiative standards for digital editions, annotations, and scholarly apparatusa5c-aiwritestelegram-automationAutomate Telegram tasks via Rube MCP (Composio): send messages, manage chats, share photos/documents, and handle bot commands.…sickn33telegram-bot-builderExpert in building Telegram bots that solve real problems - from simple automation to complex AI-powered bots. Covers bot…sickn33telegram-mini-appExpert in building Telegram Mini Apps (TWA) - web apps that run inside Telegram with native-like experience. Covers the TON…sickn33telnyx-automationAutomate Telnyx tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQteltel-automationAutomate Teltel tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtem-image-analyzerTransmission Electron Microscopy image analysis skill for nanoparticle size, morphology, and crystallography assessmenta5c-aiwritestemplated-automationAutomate Templated tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtemporal-logic-translatorTranslate between temporal logic formalisms and generate property specificationsa5c-aiwritestemporal-python-proMaster Temporal workflow orchestration with Python SDK. Implements durable workflows, saga patterns, and distributed…sickn33tensor-network-simulatorTensor network-based simulation skill for large circuit approximationa5c-aiwritestensorflow-physics-mlTensorFlow machine learning skill specialized for physics applications including neural network potentials and surrogate modelsa5c-aiwritesterm-comparatorCompares term sheets against market standards, identifies outliersa5c-aiwrites
← Prev193 / 204Next →
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 655 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 103 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