Agent skills

AI & Agents skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
4,965 found
3,4573,504 · page 73 / 104
eval-harnessFormal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principlesvibeevalevaluating-with-leakage-gatesEvaluate an OpenMed de-identification or clinical NER model against the leakage-first release gates G1a through G8, which gate…maziyarpanahievaluationBuild evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context engineering…sickn33evenium-automationAutomate Evenium tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQevent-staffing-complianceAssess worker-classification and compliance risk for temporary event staffing in the US and Canada — W-2 vs 1099…sickn33eventee-automationAutomate Eventee tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQeventzilla-automationAutomate Eventzilla tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQeverhour-automationAutomate Everhour tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQeversign-automationAutomate Eversign tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQevo2Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing…BioTender-maxevo2Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing…xuzhougengevolutionThis skill enables makepad-skills to self-improve continuously during development.sickn33evotown-dispatch-completeReport Evotown dispatch job completion after the agent finishes real work.EXboysexa-automationAutomate Exa tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQexa-searchNeural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel…mturacexam-readyActivate this skill when a student provides study material (PDF or pasted notes) and a syllabus, and wants to prepare for an…githubexample-internal-skillAn example private skill — replace me. Use when demonstrating that org-private skills load, override, and stay inside your…mohitagw15856executive-summary-creatorCreate executive summary creator operations. Auto-activating skill for Enterprise Workflows. Triggers on: executive summary…jeremylongshorewritesexist-automationAutomate Exist tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQexpecon-theory-modelUse when turning the behavioral or game-theoretic argument behind an Experimental Economics (ExpEcon) manuscript into…brycewang-stanfordexperiment-controllerUse this skill whenever the user wants to execute experiments based on a finalized method and record results. Triggers include…BioTender-maxexperiment-engineOtonom deney dongusu. Kod degisikligi yap, olc, karsilastir, kabul et veya geri al. Metrik bazli karar verme ile performans…vibeevalexpert_prompt_architect_creatorIteratively creates, mixes, and refines ChatGPT prompts using a strict three-section output format and first-person perspective.ECNU-ICALKexpert_prompt_creator_and_optimizerAn iterative prompt engineering assistant that optimizes user prompts using role, background, and constraints, providing…ECNU-ICALKexpert_prompt_creator_iterativeActs as an expert prompt engineer to iteratively create and refine tailored ChatGPT prompts through a structured feedback loop…ECNU-ICALKExplain concepts with step-by-step numerical examplesUse this skill when explaining abstract mathematical or algorithmic concepts. The user requires explanations to be lively and…ECNU-ICALKexplanation-guidanceSurfaces Han's shared standard for explaining technical work to a reader who will not implement it into the calling skill's own…testdoubleexploreMeta-skill for internal codebase exploration at varying depths (quick/deep/architecture)parcadeiwritesexpofp-automationAutomate Expofp tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQexport-agentConverts agent definitions between frameworks — exports to Claude Code, OpenAI, CrewAI, Lyzr, and GitHub Models formats, and…open-gitagentextract-clinical-entities-to-fhirExtract clinical entities from synthetic or already de-identified text with OpenMed and map them into deterministic FHIR R4…maziyarpanahiextracta-ai-automationAutomate Extracta AI tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQfable-judgeAdversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs…Sahir619fable-safe-promptRewrite allowed prompts to reduce false-positive safety triggers without bypassing policy or changing intent.sickn33faceup-automationAutomate Faceup tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQfactcheck-guardUse this skill when making any factual claim about the codebase — existence, absence, or behavior. Converts the…vibeevalfactorial-automationAutomate Factorial tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQfaf-goGuided interview to Gold Code (100% AI-Readiness). Use when helping users improve their .faf file through questions. Leverages…sickn33fai-inspectionSkill for first article inspection planning and execution per AS9102a5c-aiwritesfair-esm2Embed proteins with Meta AI's ESM-2 (`fair-esm` package). Use this skill ML, (2) Masked-LM likelihood / mutation effect scoring…BioTender-maxfair-esm2Embed proteins with Meta AI's ESM-2 (`fair-esm` package). Use this skill ML, (2) Masked-LM likelihood / mutation effect scoring…xuzhougengfal-kling-o3Generate images and videos with Kling O3 — Kling's most powerful model family — via fal.ai.nexu-iofatigue-analysisSpecialized skill for fatigue life assessment and durability prediction under cyclic loading conditionsa5c-aiwritesfatigue-dtSpecialized skill for fatigue life prediction and damage tolerance assessmenta5c-aiwritesfatigue-life-predictorFatigue life prediction skill for implants and load-bearing devices using validated approachesa5c-aiwritesfea-mesh-generatorFinite element mesh generation skill optimized for biomedical geometries including implants, anatomical structures, and tissue…a5c-aiwritesfea-structural-engineFinite Element Analysis skill for linear and nonlinear structural analysis, modal analysis, and load combination processinga5c-aiwritesfeathery-automationAutomate Feathery tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQ
← Prev73 / 104Next →
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