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
9,6499,696 · page 202 / 204
wiki-changelogGenerate structured changelogs from git history. Use when user asks \"what changed recently\", \"generate a changelog\"…sickn33wiki-onboardingGenerate two complementary onboarding documents that together give any engineer — from newcomer to principal — a complete…sickn33wiki-page-writerYou are a senior documentation engineer that generates comprehensive technical documentation pages with evidence-based depth.sickn33wiki-vitepressTransform generated wiki Markdown files into a polished VitePress static site with dark theme and interactive Mermaid diagrams.…sickn33wind-load-calculatorWind load calculation skill per ASCE 7 for MWFRS and components and claddinga5c-aiwriteswind-tunnel-correlationSpecialized skill for correlating CFD predictions with experimental wind tunnel dataa5c-aiwriteswindows-desktop-e2eE2E testing for Windows native desktop apps (WPF, WinForms, Win32/MFC, Qt) using pywinauto and Windows UI Automation.mturacwindows-hook-debuggingWindows环境下Claude Code插件Hook执行错误的诊断与修复。当遇到hook error、cannot execute binary file、.sh regex误匹配、WSL/Git Bash冲突时使用。foryourhealth111-pixelwindows-privilege-escalationProvide systematic methodologies for discovering and exploiting privilege escalation vulnerabilities on Windows systems during…sickn33windows-shell-reliabilityReliable command execution on Windows: paths, encoding, and common binary pitfalls.sickn33winston-ai-automationAutomate Winston AI tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQwireshark-analysisExecute comprehensive network traffic analysis using Wireshark to capture, filter, and examine network packets for security…sickn33wit-ai-automationAutomate Wit AI tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQwitnessSign, verify, and track fix-marker regressions over time using a deterministic Ed25519 witness manifest. Works in any project —…ruvnetwriteswiz-automationAutomate Wiz tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQwjs-auditing-projectUse when the user asks to audit what's wrong with a project, "make it right", "看看项目出了什么问题", "为什么用户的需求还没上线", "为什么没提交App Store"…jianshuowjs-eating-and-growing吃一堑长一智 — 走完 5 步交互式反思(堑 → 自动输出 → 旧权重 → 新参数 → 替代动作),从「情绪复盘」推进到「行为训练」,把第一反应这一层 L3 权重练新。Use when 王建硕 reflects on a personal setback…jianshuowjs-editing-multicamUse when the user has 2+ recordings of the same event (each with a `.sync.json` sidecar from wjs-syncing-multicam) and wants them…jianshuowjs-polishing-x-engagement把一条平淡的中文 tweet/推文/帖子改写成"有真实事实支撑 + 带互动钩子"的高参与度版本,每次给 2-3 个不同钩子的版本,风格务必短、白、口语。只要用户贴出一条中文…jianshuowjs-publishing-testflight为 iOS 项目配置 fastlane + GitHub Actions,实现推送 main 分支自动构建并上传 TestFlight。参考实现:Cathier 项目。触发词:「testflight」「fastlane」「自动构建」「CI…jianshuowjs-syncing-multicamUse when the user has 2+ video / audio recordings of the same event captured by different devices (cameras, phones, separate…jianshuowjs-teaching-englishUse when the user wants to teach / learn an English word as a video — turn a single English word into a self-contained HLS…jianshuowjs-translating-subtitlesUse when the user has an SRT (or transcript text) in one language and wants it translated to another, with punctuation-bounded…jianshuowjs-voicedrop-choosing-coverUse when 王建硕 wants to decide whether a VoiceDrop article should get an AI 题图 (公众号封面), and which style of image prompt to use —…jianshuowjs-voicedropVoiceDrop 的入口。所有能力都在 MCP 里(voicedrop.cn/mcp,32 个工具:文章读写与版本、文风与蒸馏、挖矿与重写、社区与投币、算力、分享/公众号/小红书)。本 skill 只做一件事——把你接上那个 MCP:用它的 login…jianshuowjs-voicedrop-post-processingUse when a newly mined VoiceDrop article needs automated post-processing — invoked headless by the 5-minute poller (launchd…jianshuowjttc-builderPLAN and GENERATE WJTTC (Championship-Grade) test suites for any project. Analyzes the codebase, classifies components across the…sickn33wjttc-testerF1-inspired test EXECUTOR + reporter. Runs a test plan, finds and reproduces bugs, audits suite signal integrity, then files a…sickn33wolfram-alpha-api-automationAutomate Wolfram Alpha API tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQwoodpecker-co-automationAutomate Woodpecker co tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQwordpress-centric-high-seo-optimized-blogwriting-skillGenerate clean, human-sounding, SEO-optimized WordPress blog posts with optional Yoast metadata, JSON-LD schema markup, and image…sickn33wordpress-penetration-testingAssess WordPress installations for common vulnerabilities and WordPress 7.0 attack surfaces.sickn33wordpress-plugin-developmentWordPress plugin development workflow covering plugin architecture, hooks, admin interfaces, REST API, security best practices…sickn33wordpressComplete WordPress development workflow covering theme development, plugin creation, WooCommerce integration, performance…sickn33wordpress-theme-developmentWordPress theme development workflow covering theme architecture, template hierarchy, custom post types, block editor support…sickn33wordpress-woocommerce-developmentWooCommerce store development workflow covering store setup, payment integration, shipping configuration, customization, and…sickn33workUse for execution, debugging, verification, planning, and shipping when the user's Emulo working profile should guide the task.…ohad6kwork-sampling-analyzerWork sampling analysis skill for activity distribution and utilization studies.a5c-aiwriteswork-with-prFull PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA →…code-yeongyuworkable-automationAutomate Workable tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQWorkday AutomationAutomate HR operations in Workday -- manage workers, time off requests, absence balances, and employee data through natural…ComposioHQworker-benchmarksRun comprehensive worker system benchmarks and performance analysisruvnetworker-integrationWorker-Agent integration for intelligent task dispatch and performance trackingruvnetworkflow-automationWorkflow creation, execution, and template management. Automates complex multi-step processes with agent coordination. Use when…ruvnetworkflow-automationWorkflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a…sickn33workflow-automatorOperational workflow automation skill with task sequencing, approval routing, and exception handlinga5c-aiwritesworkflow-createAuthor a workflow — either an MCP workflow template (persisted, lifecycle) or a native .claude/workflows/*.js orchestration…ruvnetwritesworkflow-orchestration-patternsMaster workflow orchestration architecture with Temporal, covering fundamental design decisions, resilience patterns, and best…sickn33
← Prev202 / 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