Agent skills

Skills for codex

9,699 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 62,644codex 9,699cursor 6,852copilot 2,269windsurf 126cline 82
CategoryWorkflow & Productivity 11,684AI & Agents 4,965Data & Analytics 4,693Code Review & Quality 2,936Security 2,762Backend & API 2,480Design & Presentation 2,329Documentation 2,157Content & Marketing 2,001Testing & QA 1,723DevOps & Cloud 1,266Databases 1,124Frontend 1,015Business & Finance 706Media & Video 507Other 21,420
9,699 found
5,6175,664 · page 118 / 203
brex-staging-automationAutomate Brex Staging tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbrightdata-automationAutomate Brightdata tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbrightpearl-automationAutomate Brightpearl tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbrilliant-directories-automationAutomate Brilliant Directories tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbroken-authenticationIdentify and exploit authentication and session management vulnerabilities in web applications. Broken authentication…sickn33brooks-harnessMaintenance orchestrator for the brooks-lint plugin itself. Runs a sequential subagent pipeline — author → eval → QA →…hyhmrrightbrooks-harnessMaintenance orchestrator for the brooks-lint plugin itself. Runs a sequential subagent pipeline — author → eval → QA →…sickn33brooks-lintAI code reviewer grounded in classic software engineering books for catching design smells, coupling issues, and architectural…sickn33browse-and-evaluateUse when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to…MoizIbnYousafbrowseai-automationAutomate Browseai tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbrowser-actBrowser automation CLI for AI agents. NEVER run browser-act commands directly via Bash — always invoke this skill first. Use…browser-actbrowser-actUse BrowserAct for authenticated browser automation, JS-rendered extraction, screenshots, parallel sessions, verification…sickn33browser-auth-flowProbe a site's authentication flow for redirect leaks, missing CSRF, weak session cookies, and OAuth misconfiguration; produces…ruvnetwritesbrowser-automationAutomate browser interactions using Playwright, Puppeteer, or Selenium — scraping, testing, and workflow automation for web…a5c-aiwritesbrowser-automationBrowser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable…sickn33browser-extension-builderExpert in building browser extensions that solve real problems - Chrome, Firefox, and cross-browser extensions. Covers extension…sickn33browser-extractExtract structured data via stored browser-templates or one-shot DOM queries, with mandatory AIDefence PII + prompt-injection…ruvnetbrowser-form-fillFill a web form by mapping field-name → value, with optional template lookup from browser-templates for known formsruvnetwritesbrowser-intentExecute a natural-language browser intent via page-agent (browser_act) when the target is easier to describe than to select —…ruvnetwritesbrowser-loginDrive an authentication flow once, sanitize cookies through AIDefence, and vault a reusable cookie handle in browser-cookies for…ruvnetwritesbrowser-qaUse this skill to automate visual testing and UI interaction verification using browser automation after deploying features.mturacbrowser-recordOpen a named, traced browser session into an RVF cognitive container with a ruvector trajectory recording every actionruvnetwritesbrowser-replayReplay a recorded session trajectory against the same URL or a mutated variant; uses browser-selectors embedding similarity to…ruvnetbrowserWeb browser automation with AI-optimized snapshots for claude-flow agentsruvnetbrowser-scrapeDEPRECATED in v0.2.0 -- use browser-extract instead; this is a thin shim for backward compatibility, removed in v0.3.0ruvnetwritesbrowser-screenshot-diffVisual + DOM diff between two recorded sessions at matching trajectory step ids; used for visual regression and replay…ruvnetwritesbrowser-testUI test recipe -- composes browser-record (capture) + browser-replay (verify) so every test produces a replayable RVF artifact…ruvnetbrowser-testing-with-devtoolsTests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need…addyosmanibrowser-testing-with-devtoolsTest browser apps with Chrome DevTools MCP by inspecting live DOM, console logs, network traffic, screenshots, accessibility, and…sickn33browser-tool-automationAutomate Browser Tool tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbrowserbase-tool-automationAutomate Browserbase Tool tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbrowserhub-automationAutomate Browserhub tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbrowserless-automationAutomate Browserless tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbrutalismWeb and App implementation guide for Brutalism. Trigger when user wants a raw appearance, intentionally unfinished look, and…sickn33industrial-brutalist-uiRaw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale…Leonxlnxbrutalist-typographyWeb and App implementation guide for Brutalist Typography. Trigger when user wants huge fonts, raw presentation, and aggressive…sickn33btcpay-server-automationAutomate Btcpay Server tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbubble-automationAutomate Bubble tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbudget-forecasting-engineDriver-based budgeting and forecasting skill with rolling forecast support and variance analysisa5c-aiwritesbudget-optimizerOptimize budget allocation. Use when: channel spend reallocation, data-driven budget planning, ROI-based justification.indranilbanerjeebudget-trackerTrack budget pacing in real time. Use when: cross-platform spend tracking, overspend alerts, reallocation recommendations.indranilbanerjeebug-captureCapture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in…rohitg00bug-investigatorUse when encountering any bug, test failure, or unexpected behavior during spec-superflow execution, before proposing fixes.…MageByte-Zerobug-triageTriage bugs reported in chat/issues, search for duplicates, file or update GitHub issues with full context, and push fix PRs.Untrivial-aibugbug-automationAutomate Bugbug tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbugherd-automationAutomate Bugherd tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbugs-are-annoyingAdversarial code auditor that hunts down bugs, logic errors, and security flaws. Use for deep correctness passes, not style…sickn33bugsnag-automationAutomate Bugsnag tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQ
← Prev118 / 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