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
7,0097,056 · page 147 / 203
green-chemistry-metricsGreen chemistry metrics calculation skill for atom economy, E-factor, and process mass intensitya5c-aiwritesgreen-synthesis-evaluatorSustainability assessment skill for evaluating and designing environmentally friendly nanomaterial synthesis routesa5c-aiwritesgrill-me针对方案或设计的高强度追问式面试(adversarial design review / grill session),暴露假设漏洞与缺失约束,过程中同步维护领域模型(术语表和 ADR)。手动调用 /grill-me。feiskyergrill-meA relentless interview to sharpen a plan or design.sickn33grill-with-docsA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.sickn33grillingInterview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses…sickn33griptape-automationAutomate Griptape tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQgrist-automationAutomate Grist tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQgromacs-biosim-runnerGROMACS molecular dynamics skill specialized for biomolecular systems, protein simulations, and free energy calculationsa5c-aiwritesgromacs-md-executorGROMACS molecular dynamics skill for nanoparticle-biomolecule interaction simulationsa5c-aiwritesgrowth-engineMotor de crescimento para produtos digitais -- growth hacking, SEO, ASO, viral loops, email marketing, CRM, referral programs e…sickn33growth-factors-miningBuilds a per-run LIGHT growth-vector database for the Diffmode growth-tactics pipeline by mining public growth case studies…acogoodgrowth-planProduce the 11-section Growth Plan — the flagship Part 8 client-facing deliverable that synthesises the entire engagement into a…indranilbanerjeewritesgsap-coreOfficial GSAP skill for the core API — gsap.to(), from(), fromTo(), easing, duration, stagger, defaults, gsap.matchMedia()…nexu-iogsap-frameworksOfficial GSAP skill for Vue, Svelte, and other non-React frameworks — lifecycle, scoping selectors, cleanup on unmount. Use when…nexu-iogsap-performanceOfficial GSAP skill for performance — prefer transforms, avoid layout thrashing, will-change, batching. Use when optimizing GSAP…nexu-iogsap-performanceGSAP performance guidance — prefer transforms, avoid layout thrashing, use will-change selectively, and batch animation work. Use…TheGoat395gsap-pluginsOfficial GSAP skill for GSAP plugins — registration, ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia, Observer…nexu-iogsap-reactOfficial GSAP skill for React — useGSAP hook, refs, gsap.context(), cleanup. Use when the user wants animation in React or…nexu-iogsap-scrolltriggerOfficial GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending…nexu-iogsap-timelineOfficial GSAP skill for timelines — gsap.timeline(), position parameter, nesting, playback. Use when sequencing animations…nexu-iogsap-utilsOfficial GSAP skill for gsap.utils — clamp, mapRange, normalize, interpolate, random, snap, toArray, wrap, pipe. Use when the…nexu-iogsc-ai-performanceQuery and interpret the new Google Search Console AI Performance Report (AI Overviews + AI Mode…indranilbanerjeegsea-pathway-analyzerGene Set Enrichment Analysis skill for functional annotation and pathway interpretationa5c-aiwritesGumroad AutomationAutomate Gumroad product management, sales tracking, license verification, and webhook subscriptions using natural language…ComposioHQhabitica-automationAutomate Habitica tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhackernews-automationAutomate Hackernews tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhadsUse when writing technical documentation that needs to be readable by both humans and AI models, converting existing docs to HADS…wshobsonhand-drawn-diagramsGenerate hand-drawn Excalidraw diagrams from a prompt — animated SVG, hosted edit link, and PNG export. Works with Claude Code…nexu-iohandling-qualitiesSpecialized skill for aircraft handling qualities evaluationa5c-aiwriteshandoff-ds把执行性编码/调查任务整包交给 DeepSeek 后台执行,省主会话额度。后台运行,完成后自动通知。支持并行多任务,支持续接(resume)上次会话继续派发后续任务。dazuibahandoff将当前对话压缩为交接文档(handoff document / session handoff brief),供下一个 agent 接续工作。手动调用 /handoff。feiskyerhandoff-gemini把执行性编码/调查任务整包交给 gemini 后台执行,省主会话额度。后台运行,完成后自动通知。支持并行多任务,支持续接(resume)上次会话继续派发后续任务。dazuibahandoff-opus把关键决策/验收类任务交给 Claude Opus 执行。后台运行,完成后自动通知。支持并行多任务,支持续接(resume)上次会话继续派发后续任务。dazuibahandoff-protocolsManages work transitions between team members or agents by creating structured handoff documents, summarizing project status…rohitg00handoffCompact the current conversation into a handoff document for another agent to pick up.sickn33happy-scribe-automationAutomate Happy Scribe tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhardware-interface-testingTest hardware interfaces and peripheral drivers including GPIO, ADC, DAC, and communication bus validation.a5c-aiwriteshardware-verification-uvmImplement UVM-based hardware verification testbenches — stimulus generation, scoreboarding, coverage-driven verification, and…a5c-aiwritesharness-benchManage `@metaharness/darwin` bench suites — `bench create <repo>` scaffolds a JSON suite from a repo's test corpus; `bench verify…ruvnetwritesharness-drift-from-historyOne-command drift detection. Composes audit-list + oia-audit + audit-trend into a single primitive — finds the most recent audit…ruvnetwritesharness-evolveRun `@metaharness/darwin evolve <repo>` to mutate a harness's seven policy surfaces…ruvnetwritesharness-genome7-section repo readiness report from `metaharness genome <path>`. Returns repo_type / agent_topology / risk_score / mcp_surface /…ruvnetwritesharness-gepaInspect and audit GEPA genomes via the `@metaharness/darwin/gepa` library entry (darwin 0.8.0) — load/validate a genome (default…ruvnetwritesharness-learnRun a GEPA learning cycle via `metaharness learn` (upstream ADR-235, metaharness@0.3.0) — optimizes a harness genome against a…ruvnetwritesharness-mcp-scanStatic security scan of a harness's declared MCP surface via `harness mcp-scan <path>`. Reads `.mcp/servers.json` +…ruvnetwritesharness-mintScaffold a custom AI agent harness via `metaharness new <name> --template <id> --host <id>`. Defaults to DRY-RUN (no writes)…ruvnetwritesharness-oia-auditComposite Phase-2 audit worker (ADR-150). Bundles harness oia-manifest + threat-model + mcp-scan into one timestamped audit…ruvnetwrites
← Prev147 / 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