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
6,2416,288 · page 131 / 203
datadogUse when the user says "check Datadog", "查 Datadog", "查日志", "check logs", "crash logs", "查 crash", "gateway crash", "查告警", "check…nexu-iodatagma-automationAutomate Datagma tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQdatarobot-automationAutomate Datarobot tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQdate-time-manipulationHandle date and time manipulation — timezone conversions, duration calculations, date formatting, and internationalization-aware…a5c-aiwritesdbr-schedulerDrum-Buffer-Rope scheduling skill for constraint-based production pacing with buffer managementa5c-aiwritesdbt_ingestMap dbt `schema.yml` / `properties.yml` models and sources into ktx semantic-layer overlays and column notes. Covers `sources:`…Kaeliodcf-modelerBuilds DCF models with terminal value, WACC calculation, sensitivity tablesa5c-aiwritesdcf-valuation-modelerDiscounted Cash Flow model builder for comprehensive company valuations with WACC calculation, terminal value estimation, and…a5c-aiwritesddd-aggregateScaffold an aggregate root with entity, value objects, repository interface, domain events, and test stubs. Use when adding a new…ruvnetwritesddd-contextCreate and manage a DDD bounded context with standard directory structure. Use when starting a new subdomain, splitting a…ruvnetwritesddd-validateValidate domain boundaries -- detect cross-context import violations and aggregate invariant issues. Use when auditing a DDD…ruvnetwritesddmrp-buffer-managerDemand-Driven MRP buffer positioning and management skill with dynamic adjustmenta5c-aiwritesdead-skillA fixture skill that is installed but never invoked. Pure context tax.anandsaini18dead-stock-identifierSlow-moving and obsolete inventory identification skill with disposition planning and working capital optimizationa5c-aiwritesdeadline-funnel-automationAutomate Deadline Funnel tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQdeal-flow-trackerCRM integration for tracking deals through pipeline stages with automated status updatesa5c-aiwritesdeal-scoring-engineAutomated deal scoring based on thesis alignment, market size, team, and traction metricsa5c-aiwritesdebateStructured AI debate templates and synthesis. Use when orchestrating multi-round debates between AI tools, 'debate topic', 'argue…agent-shdebt-covenant-monitorAutomated covenant compliance monitoring and calculation skill with early warning alertsa5c-aiwritesdebugInvestigate-then-decide root-cause analysis for a defect whose cause is unknown (distinct from /fix, which assumes a known bug).…arbiterForgedebug-buttercupAll pods run in namespace crs. Use when pods in the crs namespace are in CrashLoopBackOff, OOMKilled, or restarting, multiple…sickn33debuggerDebugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues. 'sickn33debugging-and-error-recoveryGuides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter…addyosmanidebugging-and-error-recoveryGuides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter…sickn33debugging-strategiesMaster systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any…wshobsondebugging-toolkitUse when working with debugging toolkit smart debug (Alias for debugging-toolkit-smart-debug)sickn33debugging-toolkit-smart-debugUse when working with debugging toolkit smart debugsickn33decision-journalDecision documentation and learning skill for capturing decision context, rationale, and outcomesa5c-aiwritesdecision-navigatorGuide stuck or overwhelmed users through targeted branching questions until they reach concrete next steps.sickn33decision-tree-analyzerDecision tree analysis skill with expected value, risk analysis, and utility theory.a5c-aiwritesdecision-tree-builderAutomated decision tree construction skill for structuring complex decisions with probabilities, payoffs, and expected value…a5c-aiwritesdecision-varianceReconcile the project's architectural artifacts against the scaffold and prior decisions, then present each variance as a SMARTS…arbiterForgedecision-visualizationDecision-specific visualization skill for creating clear, actionable visual representations of analysesa5c-aiwritesdecomposeThe greenfield decomposition interview. Routed to at startup when .codearbiter/CONTEXT.md lacks the <!--INITIALIZED--> body…arbiterForgedeel-automationAutomate Deel tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQdeep-discuss结构化深度讨论 Skill,用于与用户进行多轮问题分析和方案设计。当用户描述一个问题现象、故障表现、 技术困惑、方案选择困难,或明确说"讨论一下"、"帮我分析"、"我遇到一个问题"、"你觉得怎么样"、 "帮我想想"、"我在纠结"时,必须使用本…zhu1090093659deep-research-agentComprehensive research agent for in-depth investigation. Use when users ask for deep research, comprehensive analysis, market…shobcoderdeep-researchMulti-agent research orchestration: split a research goal into parallel sub-goals, run each via headless `claude -p`…feiskyerwritesdeep-researchMulti-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with…mturacdeep-researchOrchestrate multi-phase deep research with web search, memory retrieval, pattern matching, and synthesis into structured findingsruvnetdeep-researchAnswer a broad, open-ended, or multi-part question by iteratively searching MFS-indexed sources, following up on gaps, and…zilliztechdeepapiUse DeepAPI for supported scraping, research, and email workflows with explicit credentials and approval.sickn33deepgram-automationAutomate Deepgram tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhivemind-memoryGlobal team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling…activeloopaiwritesdeepvariant-callerDeepVariant deep learning variant calling skill for high-accuracy SNV and indel detectiona5c-aiwritesdefi-amm-securitySecurity checklist for Solidity AMM contracts, liquidity pools, and swap flows. Covers reentrancy, CEI ordering, donation or…mturacdefi-protocol-templatesImplement DeFi protocols with production-ready templates for staking, AMMs, governance, and lending systems. Use when building…sickn33defuddleExtract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of…kepano
← Prev131 / 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