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
7,3937,440 · page 155 / 203
langbase-automationAutomate Langbase tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlangchain-architectureMaster the LangChain framework for building sophisticated LLM applications with agents, chains, memory, and tool integration.sickn33langfuseExpert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and…sickn33langgraphExpert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph…sickn33language-auditAudit multilingual content consistency. Use when: checking language parity, regional compliance, or translation quality.indranilbanerjeelanguage-configConfigure language settings. Use when: setting primary languages, do-not-translate terms, or locale formatting.indranilbanerjeelaravel-expertSenior Laravel Engineer role for production-grade, maintainable, and idiomatic Laravel solutions. Focuses on clean architecture…sickn33laravel-patternsLaravel architecture patterns, routing/controllers, Eloquent ORM, service layers, queues, events, caching, and API resources for…mturaclaravel-plugin-discoveryDiscover and evaluate Laravel packages via LaraPlugins.io MCP. Use when the user wants to find plugins, check package health, or…mturaclaravel-security-auditSecurity auditor for Laravel applications. Analyzes code for vulnerabilities, misconfigurations, and insecure practices using…sickn33laravel-securityLaravel security best practices for authn/authz, validation, CSRF, mass assignment, file uploads, secrets, rate limiting, and…mturaclaravel-tddTest-driven development for Laravel with PHPUnit and Pest, factories, database testing, fakes, and coverage targets.mturaclaravel-verificationVerification loop for Laravel projects: env checks, linting, static analysis, tests with coverage, security scans, and deployment…mturaclast-mile-delivery-optimizerFinal delivery leg optimization skill including dynamic scheduling, time-window management, and delivery confirmationa5c-aiwriteslastpass-automationAutomate Lastpass tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlatex-document-compilerSkill for compiling and managing LaTeX documentsa5c-aiwriteslatex-paper-conversionThis skill should be used when the user asks to convert an academic paper in LaTeX from one format (e.g., Springer, IPOL) to…sickn33latex-physics-documenterLaTeX scientific documentation skill specialized for physics papers with equation rendering and journal formattinga5c-aiwriteslatex-proof-formatterFormat proofs and algorithms in publication-quality LaTeXa5c-aiwriteslaunch-ad-campaignLaunch paid ad campaigns. Use when: deploying ads on Google, Meta, LinkedIn, or TikTok with targeting and safeguards.indranilbanerjeelaunch-campaignOrchestrate the full multi-channel launch of an approved campaign plan — pre-launch checklist, asset readiness gate…indranilbanerjeewritesLaunchDarkly AutomationAutomate LaunchDarkly feature flag management -- list projects and environments, create and delete trigger workflows, and track…ComposioHQlaunch_darkly-automationAutomate LaunchDarkly tasks via Rube MCP (Composio): feature flags, environments, segments, and rollout management. Always search…ComposioHQlaunch-planBuild product launch playbooks. Use when: planning pre-launch, launch day, or post-launch phases.indranilbanerjeelaunch-strategyYou are an expert in SaaS product launches and feature announcements. Your goal is to help users plan launches that build…sickn33layered-designWeb and App implementation guide for Layered Design. Trigger when user wants multiple depth levels, floating panels, and…sickn33lbo-model-builderLeveraged Buyout model construction skill for private equity transaction analysisa5c-aiwriteslca-analyzerLife Cycle Assessment skill for environmental impact evaluation and sustainability analysisa5c-aiwriteslead-discoveryOrchestrator that runs first for lead generation requests. Gathers business context via website analysis or questions, identifies…gooseworks-aiwriteslead-importImport leads into CRM. Use when: loading leads from forms, CSV, or manual entry with deduplication and scoring.indranilbanerjeelead-research-assistantIdentifies high-quality leads for your product or service by analyzing your business, searching for target companies, and…Prat011leadfeeder-automationAutomate Leadfeeder tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQleadoku-automationAutomate Leadoku tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlean-proof-assistantInterface with Lean 4 proof assistant for formal theorem verificationa5c-aiwriteslearnResearch any topic online and create learning guides. Use when user asks to 'learn about', 'research topic', 'create learning…agent-shlearnSave a marketing learning or insight. Use when: capturing knowledge, recording campaign results, building compound intelligence.indranilbanerjeelearn-ruleCapture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, categorises, and…rohitg00learnHelp a user learn a topic through adaptive tutoring, lesson planning, practice, retrieval checks, explanations, study guides, or…sickn33learning-analytics-interpretationAnalyze learner data from LMS reports, assessments, and engagement metrics to identify patterns and inform instructional decisionsa5c-aiwriteslearning-needs-analysisConduct comprehensive learner audience analysis, identify performance gaps, and determine instructional requirements using…a5c-aiwriteslearning-objectives-writingWrite measurable, SMART learning objectives using Bloom's Taxonomy cognitive levels aligned with desired outcomes and assessment…a5c-aiwriteslearning-transfer-designDesign instructional strategies that promote knowledge and skill transfer to real-world application contextsa5c-aiwriteslease-accounting-calculatorASC 842/IFRS 16 lease accounting skill for right-of-use asset and liability calculationsa5c-aiwriteslegacy-modernizerRefactor legacy codebases, migrate outdated frameworks, and implement gradual modernization. Handles technical debt, dependency…sickn33legal-advisorDraft privacy policies, terms of service, disclaimers, and legal notices. Creates GDPR-compliant texts, cookie policies, and data…sickn33leiga-automationAutomate Leiga tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQLemlist AutomationAutomate Lemlist multichannel outreach -- manage campaigns, enroll leads, add personalization variables, export campaign data…ComposioHQlemmalyAlgorithm-first discipline: state Big-O, data structure, and algorithm family BEFORE writing loops, queries, or recursion.…sickn33
← Prev155 / 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