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
6,7696,816 · page 142 / 203
flutter-dart-code-reviewLibrary-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod…mturacflutter-errorsUse when hitting layout errors (RenderFlex overflow, unbounded constraints, RenderBox not laid out), scroll errors, or…evancaflutter-pre-cachingUse when preloading fonts, asset/network images, Lottie/Rive animations, local JSON/config, warming initial API data, or…evancaflutterfire-configureUse when adding Firebase to a Flutter project, running flutterfire configure, initializing Firebase in main.dart, or configuring…evancaflutterwave-automationAutomate Flutterwave tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQfluxguard-automationAutomate Fluxguard tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQfmea-facilitatorFailure Mode and Effects Analysis facilitation skill for products and processes with risk prioritization and control…a5c-aiwritesfocus-groupRun synthetic focus groups. Use when: testing messaging, pricing, or positioning before live research spend.indranilbanerjeefocused-fixUse when the user asks to fix, debug, or make a specific feature/module/area work end-to-end. Triggers: 'make X work', 'fix the Y…alirezarezvanifolded-desc-skillA fixture whose description uses a YAML folded scalar, which parses with an embedded trailing newline unless normalized before…first-flukefolder-specific-claude-and-agents-mdCreate folder-scoped CLAUDE.md and AGENTS.md guidance for future agents working in that area.sickn33folk-automationAutomate Folk tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQfomo-automationAutomate Fomo tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQforcemanager-automationAutomate Forcemanager tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQforecast-accuracy-analyzerForecast accuracy measurement and improvement skill with error decompositiona5c-aiwritesform-croOptimize any form that is NOT signup or account registration — including lead capture, contact, demo request, application…sickn33formal-logic-analysisApply propositional, predicate, and modal logic systems to formalize arguments, construct proofs, and evaluate validity using…a5c-aiwritesformal-logic-reasonerSkill for formal logical reasoning and argument validationa5c-aiwritesformbricks-automationAutomate Formbricks tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQformcarry-automationAutomate Formcarry tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQformdesk-automationAutomate Formdesk tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQformik-patternsFormik form handling with validation patterns. Use when building forms, implementing validation, or handling form submission.sickn33formsite-automationAutomate Formsite tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQfoundation-models-on-deviceApple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and…mturacfounder-reportFounder-report packaging stage for the Diffmode growth-tactics pipeline — the post-gate step that turns the APPROVED synthesis.md…acogoodfour-core-documentsProduce the Four Core Documents at strategic depth (61 total steps): Business & SBU Analysis, Segmentation Framework, Brand…indranilbanerjeewritesfoursquare-automationAutomate Foursquare tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQfp-asyncPractical async patterns using TaskEither - clean pipelines instead of try/catch hell, with real API examplessickn33fp-backendFunctional programming patterns for Node.js/Deno backend development using fp-ts, ReaderTaskEither, and functional dependency…sickn33fp-data-transformsEveryday data transformations using functional patterns - arrays, objects, grouping, aggregation, and null-safe accesssickn33fp-either-refQuick reference for Either type. Use when user needs error handling, validation, or operations that can fail with typed errors.sickn33fp-errorsStop throwing everywhere - handle errors as values using Either and TaskEither for cleaner, more predictable codesickn33fp-option-refQuick reference for Option type. Use when user needs to handle nullable values, optional data, or wants to avoid null checks.sickn33fp-pipe-refQuick reference for pipe and flow. Use when user needs to chain functions, compose operations, or build data pipelines in fp-ts.sickn33fp-pragmaticA practical, jargon-free guide to functional programming - the 80/20 approach that gets results without the academic overheadsickn33fp-reactPractical patterns for using fp-ts with React - hooks, state, forms, data fetching. Works with React 18/19, Next.js 14/15.sickn33fp-refactorComprehensive guide for refactoring imperative TypeScript code to fp-ts functional patternssickn33fp-taskeither-refQuick reference for TaskEither. Use when user needs async error handling, API calls, or Promise-based operations that can fail.sickn33fp-ts-errorsHandle errors as values using fp-ts Either and TaskEither for cleaner, more predictable TypeScript code. Use when implementing…sickn33fp-ts-pragmaticA practical, jargon-free guide to fp-ts functional programming - the 80/20 approach that gets results without the academic…sickn33fp-ts-reactPractical patterns for using fp-ts with React - hooks, state, forms, data fetching. Use when building React apps with functional…sickn33fp-types-refQuick reference for fp-ts types. Use when user asks which type to use, needs Option/Either/Task decision help, or wants fp-ts…sickn33open-knowledge-pack-software-lifecycle-frame-a-proposalFrame a new design proposal (RFC-shape) under proposals/ — problem before solution, named beneficiary and observable change, real…inkeepframework-migration-legacy-modernizeOrchestrate a comprehensive legacy system modernization using the strangler fig pattern, enabling gradual replacement of outdated…sickn33fraud-risk-assessorFraud risk assessment skill based on the fraud triangle with red flag detectiona5c-aiwritesfraudlabs-pro-automationAutomate Fraudlabs Pro tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQfree-tool-strategyYou are an expert in engineering-as-marketing strategy. Your goal is to help plan and evaluate free tools that generate leads…sickn33freight-audit-validatorAutomated freight bill validation skill with discrepancy detection and payment processing automationa5c-aiwrites
← Prev142 / 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