Agent skills

Skills for codex

9,782 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 63,296codex 9,782cursor 7,187copilot 2,384windsurf 127cline 83
CategoryWorkflow & Productivity 11,752AI & Agents 4,985Data & Analytics 4,761Code Review & Quality 2,986Security 2,828Backend & API 2,504Design & Presentation 2,373Documentation 2,183Content & Marketing 2,060Testing & QA 1,778DevOps & Cloud 1,275Databases 1,133Frontend 1,043Business & Finance 724Media & Video 514Other 21,532
9,782 found
9,5059,552 · page 199 / 204
V3 Performance OptimizationAchieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory…ruvnetV3 Security OverhaulComplete security architecture overhaul for claude-flow v3. Addresses critical CVEs (CVE-1, CVE-2, CVE-3) and implements…ruvnetV3 Swarm Coordination15-agent hierarchical mesh coordination for v3 implementation. Orchestrates parallel execution across security, core, and…ruvnetvalidate-deliveryUse when user asks to \"validate delivery\", \"check readiness\", or \"verify completion\". Runs tests, build, and requirement…agent-shvalidate-outputValidate marketing content against a structural schema — required sections, word counts, markdown formatting, placeholder text…indranilbanerjeevalidate-pluginValidate a Claude Code plugin structure, frontmatter, and MCP tool referencesruvnetwritesvalidate-profileRead-only health check that a brand profile is production-ready: required fields, voice and audience completeness, guardrails…indranilbanerjeewritesvaluation-updaterMarks portfolio positions to fair value per ASC 820/IPEV guidelinesa5c-aiwritesvalue-at-risk-calculatorValue at Risk (VaR) and related risk metrics calculation skill for financial and operational risk assessmenta5c-aiwritesvalue-stream-mapperValue stream mapping skill for current state analysis, waste identification, and future state design with implementation roadmapsa5c-aiwritesvalue-stream-mappingCreate and analyze value stream maps with waste identification and process efficiency metricsa5c-aiwritesvaporwaveWeb and App implementation guide for Vaporwave. Trigger when user wants neon colors, retro digital aesthetics, 90s OS elements…sickn33variant-analysisFind similar vulnerabilities and bugs across codebases using pattern-based analysis. Use when hunting bug variants, building…sickn33varicent-icmVaricent incentive compensation management platforma5c-aiwritesvarlock-claude-skillSecure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commitssickn33varlockSecure-by-default environment variable management for Claude Code sessions.sickn33vasp-dft-calculatorVASP DFT calculation skill for electronic structure, band structures, and materials property predictionsa5c-aiwritesvasp-dft-executorVASP DFT calculation skill for electronic structure, geometry optimization, and property prediction of nanomaterialsa5c-aiwritesvector-clusterCluster code by graph community detection via npx ruvector@0.2.25 hooks graph-cluster (spectral / Louvain)ruvnetwritesvector-database-engineerExpert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus…sickn33vector-embedGenerate embeddings via npx ruvector@0.2.25 embed text (ONNX all-MiniLM-L6-v2, 384-dim), normalize, and store in HNSW indexruvnetwritesvector-hyperbolicEmbed hierarchical data via npx ruvector@0.2.25 embed text and project into the Poincare ball in user code (no --model poincare…ruvnetwritesvector-searchVector search via embeddings_* (large-scale HNSW) and ruvllm_hnsw_* (WASM router for ≤11 hot patterns), with RaBitQ 1-bit…ruvnetvector-setupFirst-run setup for ruvector@0.2.25 — installs ONNX/Brain/SONA add-ons, registers the MCP server, and verifies the install via…ruvnetwritesvehicle-dynamics-simDeep integration with vehicle dynamics simulation tools for handling, ride, and stability analysisa5c-aiwritesvehicle-routing-solverVehicle routing problem solver for logistics optimization with time windows, capacity constraints, and multiple depots.a5c-aiwritesvendor-risk-scorerComprehensive supplier risk scoring skill with multi-dimensional risk assessmenta5c-aiwritesvendor-scorecardEvaluate and track vendor performance using scorecards and metricsa5c-aiwritesvenice-audio-musicMusic generation queueing, retrieval, and completion endpoints via Venice.ai. Suited for jingles, background loops, and prototype…nexu-iovenice-audio-speechText-to-speech models, voices, formats, and streaming via Venice.ai. Useful for narration, voiceover, and conversational agent…nexu-iovenice-image-editImage edits, upscaling, and background removal via the Venice.ai API.nexu-iovenice-image-generateImage generation endpoints and available styles via the Venice.ai API.nexu-iovenice-videoVideo generation and transcription workflows via the Venice.ai API.nexu-iovenly-automationAutomate Venly tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQveo-automationAutomate Veo tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQvep-variant-annotatorVariant Effect Predictor skill for comprehensive variant annotation with clinical database integrationa5c-aiwritesvercel-automationAutomate Vercel tasks via Rube MCP (Composio): manage deployments, domains, DNS, env vars, projects, and teams. Always search…sickn33vercel-cli-with-tokensDeploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens…sickn33vercel-deploymentExpert knowledge for deploying to Vercel with Next.jssickn33verificationUse when checking whether agent edits are reflected in the OpenChatCut project and editor.0xslineverification-before-completionCompletion-evidence route used before claiming work is complete, fixed, passing, committed, or PR-ready. Requires fresh…foryourhealth111-pixelverification-before-completionClaiming work is complete without verification is dishonesty, not efficiency. Use when ANY variation of success/completion…sickn33verification-gatesCreates explicit validation checkpoints (verification gates) between project phases to catch errors early and ensure quality…rohitg00verification-loopA comprehensive verification system for OpenAI Codex sessions.mturacVerification & Quality AssuranceComprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring…foryourhealth111-pixelVerification & Quality AssuranceComprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring…ruvnetverifiedemail-automationAutomate Verifiedemail tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQverify-claimsExtract every verifiable claim in marketing copy — statistics, rankings, awards, citations, performance and time-bound assertions…indranilbanerjee
← Prev199 / 204Next →
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 655 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 103 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