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
5,5215,568 · page 116 / 203
beaconstac-automationAutomate Beaconstac tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbeamer-automationAutomate Beamer tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbearing-capacity-calculatorSoil bearing capacity calculation skill using multiple methods for various foundation typesa5c-aiwritesbeautiful-proseA hard-edged writing style contract for timeless, forceful English prose without modern AI tics. Use when users ask for prose or…sickn33beeminder-automationAutomate Beeminder tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbefore-you-buildReview product risk before coding by checking demand, alternatives, channels, switching costs, and failure signals.sickn33behavioral-modesAI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.sickn33bench-automationAutomate Bench tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbenchmark-email-automationAutomate Benchmark Email tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbenchmarkUse this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.mturacbenchmark-suite-managerManage benchmarks for algorithm engineering experiments and evaluationsa5c-aiwritesbenchmarking-analystBenchmarking study skill for internal, competitive, and best-in-class performance comparisona5c-aiwritesbenefits-enrollmentManage benefits enrollment and administration workflows including elections, life events, open enrollment, and compliance trackinga5c-aiwritesbenefits-tracking-dashboardTrack and visualize benefit realization against targetsa5c-aiwritesbento-uiWeb and App implementation guide for Bento UI. Trigger when user wants modular grid cards, Apple-like dashboard style, or…sickn33benzinga-automationAutomate Benzinga tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbestbuy-automationAutomate Bestbuy tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbetter-proposals-automationAutomate Better Proposals tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbetter-stack-automationAutomate Better Stack tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbevy-ecs-expertMaster Bevy's Entity Component System (ECS) in Rust, covering Systems, Queries, Resources, and parallel scheduling.sickn33bi-dashboardsBusiness intelligence and marketing dashboard creation with multi-platform supporta5c-aiwritesbi-reportingBusiness intelligence and dashboard creation for marketing analytics and reportinga5c-aiwritesbidsketch-automationAutomate Bidsketch tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbig-data-cloud-automationAutomate Big Data Cloud tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbig-planUse big-plan for broad or risky repo changes needing codebase inspection, websearch, and deeper refinement; exclude direct…Optim-Agentbigmailer-automationAutomate Bigmailer tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbigml-automationAutomate Bigml tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbigpicture-io-automationAutomate Bigpicture IO tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbilig-workpaperUse formula-backed WorkPaper JSON and MCP tools for agent spreadsheet tasks without driving Excel or a browser UI.sickn33bim-clash-detectionBIM clash detection skill for identifying and managing coordination conflicts between disciplinesa5c-aiwritesbinary-analysis-patternsComprehensive patterns and techniques for analyzing compiled binaries, understanding assembly code, and reconstructing program…sickn33biocompatibility-test-selectorBiocompatibility test selection and protocol recommendation skill based on device categorizationa5c-aiwritesbioethics-deliberationApply bioethical principles (autonomy, beneficence, non-maleficence, justice) and case-based reasoning to healthcare decisions…a5c-aiwritesbiopythonBiopython is a comprehensive set of freely available Python tools for biological computation. It provides functionality for…sickn33bioreactor-protocol-generatorBioreactor culture protocol development skill for tissue construct maturationa5c-aiwritesbitbucket-automationAutomate Bitbucket repositories, pull requests, branches, issues, and workspace management via Rube MCP (Composio). Always search…sickn33bitquery-automationAutomate Bitquery tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbitwarden-automationAutomate Bitwarden tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQblackbaud-automationAutomate Blackbaud tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQblackboard-automationAutomate Blackboard tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQblast-sequence-searchBLAST skill for sequence similarity searching, homology detection, and database queryinga5c-aiwritesblindspot-passSurface the user's unknown unknowns before work starts. Use when the user is entering an unfamiliar codebase area, an unfamiliar…NeeeophyteeblocUse when creating a Cubit or Bloc, modeling state with sealed classes or status enums, wiring…evancablock-no-verify-hookConfigure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use…wshobsonblockchain-developerBuild production-ready Web3 applications, smart contracts, and decentralized systems. Implements DeFi protocols, NFT platforms…sickn33blocknative-automationAutomate Blocknative tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQblockrunBlockRun works with Claude Code and Google Antigravity.sickn33blog-writing-guideThis skill enforces Sentry's blog writing standards across every post — whether you're helping an engineer write their first blog…sickn33
← Prev116 / 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