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
5,4735,520 · page 115 / 203
azure-virtual-desktopExpert knowledge for Azure Virtual Desktop development including troubleshooting, best practices, decision making, architecture &…MicrosoftDocsazure-virtual-network-managerExpert knowledge for Azure Virtual Network Manager development including troubleshooting, best practices, architecture & design…MicrosoftDocsazure-virtual-networkExpert knowledge for Azure Virtual Network development including troubleshooting, best practices, decision making, architecture &…MicrosoftDocsazure-virtual-wanExpert knowledge for Azure Virtual WAN development including troubleshooting, decision making, architecture & design patterns…MicrosoftDocsazure-vm-scalesetsExpert knowledge for Azure Virtual Machine Scale Sets development including troubleshooting, best practices, decision making…MicrosoftDocsazure-vmware-solutionExpert knowledge for Azure VMware Solution development including troubleshooting, best practices, decision making, architecture &…MicrosoftDocsazure-vpn-gatewayExpert knowledge for Azure VPN Gateway development including troubleshooting, best practices, decision making, architecture &…MicrosoftDocsazure-web-application-firewallExpert knowledge for Azure Web Application Firewall development including troubleshooting, best practices, decision making…MicrosoftDocsazure-web-pubsubExpert knowledge for Azure Web PubSub development including troubleshooting, best practices, decision making, architecture &…MicrosoftDocsazure-web-pubsub-tsReal-time messaging with WebSocket connections and pub/sub patterns.sickn33azure-well-architectedExpert guidance for designing, assessing, and optimizing Azure workloads using Azure Well Architected. Covers design review…MicrosoftDocsbabysitOrchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called…a5c-aibabysit-babysitter-issuesThis skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process…a5c-aibackend-architectExpert backend architect specializing in scalable API design, microservices architecture, and distributed systems.sickn33backend-async-processingImplement backend async and background processing patterns — event-driven architectures, message queues, async task runners, and…a5c-aiwritesbackend-development-feature-developmentOrchestrate end-to-end backend feature development from requirements to deployment. Use when coordinating multi-phase feature…sickn33backend-developmentBackend API design, database architecture, microservices patterns, and test-driven development. Use for designing APIs, database…MoizIbnYousafbackend-patternsBackend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and…mturacbackend-security-coderExpert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for…sickn33backend-selectorMulti-backend comparison and selection skill for optimal hardware choicea5c-aiwritesbackendless-automationAutomate Backendless tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbackground-checkerIntegrates with background check services, social media analysis, reference verificationa5c-aiwritesbackground-job-processingImplement reliable background job processing systems — queue management, retry policies, dead-letter handling, and distributed…a5c-aiwritesbacklink-gapFind referring domains that link to your competitors but not to you, ranked by an opinionated outreach-priority score with DR /…indranilbanerjeebamboohr-automationAutomate BambooHR tasks via Rube MCP (Composio): employees, time-off, benefits, dependents, employee updates. Always search tools…sickn33bannerbear-automationAutomate Bannerbear tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbarren-plateau-analyzerAnalysis skill for detecting and mitigating barren plateaus in variational circuitsa5c-aiwritesbart-automationAutomate Bart tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbaseDatabase management, forms, reports, and data operations with LibreOffice Base.sickn33basecamp-automationAutomate Basecamp project management, to-dos, messages, people, and to-do list organization via Rube MCP (Composio). Always…sickn33baseline-uiQuickly deslop UI code by fixing spacing, hierarchy, typography, and small layout issues. Use when the interface needs a fast…sickn33baselinker-automationAutomate Baselinker tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbaserow-automationAutomate Baserow tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbash-linuxBash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.sickn33bash-proMaster of defensive Bash scripting for production automation, CI/CD pipelines, and system utilities. Expert in safe, portable…sickn33bash-scriptingBash scripting workflow for creating production-ready shell scripts with defensive patterns, error handling, and testing.sickn33bashLanguage-specific super-code guidelines for bash.sickn33basin-automationAutomate Basin tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbatch-orchestrationDecompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations…rohitg00batch-vs-stream-tradeoffsAnalyze and decide between batch and stream processing architectures — latency requirements, cost modeling, and hybrid…a5c-aiwritesbattlenet-automationAutomate Battlenet tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQbayesian-inference-engineBayesian probabilistic reasoning for prior specification, posterior computation, and belief updatinga5c-aiwritesbayesian-network-analyzerBayesian network construction and inference skill for probabilistic reasoning, causal analysis, and belief updatinga5c-aiwritesbazel-build-optimizationOptimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build…sickn33bcc-clean-cutBCC minimal implement from locked PLAN.md (ponytail ladder + verify). Slash: /bcc-clean-cut · chat: bcc:clean-cut · "implement…bo-caobdi-mental-statesThis skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create…sickn33bdistill-knowledge-extractionExtract structured domain knowledge from AI models in-session or from local open-source models via Ollama. No API key needed.sickn33beaconchain-automationAutomate Beaconchain tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQ
← Prev115 / 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