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
3,8413,888 · page 81 / 104
keap-automationAutomate Keap tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQkeen-io-automationAutomate Keen IO tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQkeep-segmentCustomer segmentation model builder — tiers customers by ARR, health, and expansion potential; defines CS motion per tier; maps…jeremylongshorewriteskegg-analysisMulti-step KEGG bioinformatics workflows — pathway enrichment from gene lists, drug-target investigation, cross-species metabolic…davepoonKeras Bidirectional SimpleRNN Model DefinitionDefines a Keras Sequential model utilizing a Bidirectional SimpleRNN layer for sequence tagging, adhering to a specific…ECNU-ICALKKeras Grid Search Script GeneratorGenerates a Python script using Keras and scikit-learn to perform grid search hyperparameter tuning. The script tests different…ECNU-ICALKKeras Iterative Training and Prediction WrapperGenerates Keras implementations for an iterative training loop (finding the best model over multiple attempts) and a prediction…ECNU-ICALKkhoj-research-guideAI second brain for deep research and personal knowledge managementbrycewang-stanfordkickbox-automationAutomate Kickbox tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQkig-foundation-model-anbieterpflichten-spezialWenn es um KIG: GPAI Anbieterpflichten in diesem Spezialbereich geht: zerlegt Ergebnis, Frist, Zuständigkeit, Beweislast und…Klotzkettekinetic-modelerReaction kinetics modeling skill for parameter estimation, mechanism validation, and rate equation developmenta5c-aiwriteskiro-steeringMaintain {{KIRO_DIR}}/steering/ as persistent project memory (bootstrap/sync). Use when initializing or updating steering…gotalabwriteskit-automationAutomate Kit tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQklipfolio-automationAutomate Klipfolio tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQknowledge-agentBuild and query AI-powered knowledge bases from claude-mem observations. Use when users want to create focused "brains" from…thedotmackknowledge-builder内容工厂专用知识整理 Skill,把项目资料、素材和运营经验整理成场景生成与内容生产可用的事实输入。limecloudknowledge-graph-constructionBuild research knowledge graphs for literature synthesis and RAG systemsbrycewang-stanfordknowledge-graphKnowledge graph integration for token-efficient codebase understanding. Uses codebase-memory MCP for AST indexing, dependency…vibeevalknowledge-opsKnowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores…mturacknowledge-retrievalSemantic search over ingested documents using RAG (LlamaIndex/ChromaDB or Foundational RAG)open-gitagentko-fi-automationAutomate Ko Fi tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQKommo AutomationAutomate Kommo CRM operations -- manage leads, pipelines, pipeline stages, tasks, and custom fields -- using natural language…ComposioHQkontent-ai-automationAutomate Kontent AI tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQkosmos-scientist-guideClaude Code-driven autonomous AI Scientist for discoverybrycewang-stanfordkpi-trackerKPI definition, calculation, and tracking skill for business intelligence dashboardsa5c-aiwriteskraken-io-automationAutomate Kraken IO tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQkraken2-taxonomic-classifierKraken2 taxonomic classification skill for rapid metagenomic read assignmenta5c-aiwriteskwant-quantum-transportKwant quantum transport skill for mesoscopic physics, scattering matrix calculations, and nanostructure modelinga5c-aiwriteskyoko-instrumentWire an AI agent's telemetry into Kyoko and prove one real run shows up.kayba-ail2s-automationAutomate L2s tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlabs64-netlicensing-automationAutomate Labs64 Netlicensing tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlaienhilfe-merkzeichenWenn es um Laienverstaendlicher Sozialrechts-Skill zu Merkzeichen in Fachanwalt Sozialrecht geht: erstellt den passenden Entwurf…Klotzkettelaienhilfe-reha-antragWenn es um Laienverstaendlicher Sozialrechts-Skill zu Reha Antrag in Fachanwalt Sozialrecht geht: erstellt den passenden Entwurf…Klotzkettelaienhilfe-telefonat-behoerdeWenn es um Laienverstaendlicher Sozialrechts-Skill zu Telefonat Behörde in Fachanwalt Sozialrecht geht: erstellt den passenden…Klotzkettelaienhilfe-ueberpruefungsantrag-44-sgbxWenn es um Laienverstaendlicher Sozialrechts-Skill zu Überprüfungsantrag 44 Sgbx in Fachanwalt Sozialrecht geht: erstellt den…Klotzkettelaienhilfe-verletztenrenteWenn es um Laienverstaendlicher Sozialrechts-Skill zu Verletztenrente in Fachanwalt Sozialrecht geht: erstellt den passenden…Klotzkettelambda-langNative agent-to-agent language for compact multi-agent messaging. A shared tongue agents speak directly, not a translation layer.…sickn33lammps-md-executorLAMMPS molecular dynamics skill for nanoscale system simulation with force field managementa5c-aiwriteslammps-md-simulatorLAMMPS molecular dynamics simulation skill for atomistic simulations, force field setup, and large-scale parallel computationsa5c-aiwriteslandbot-automationAutomate Landbot tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlangbase-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.sickn33LangChain Local PDF RAG PipelineGenerates a Python script using LangChain to load PDFs from a local directory, create embeddings using Chroma and Ollama, and…ECNU-ICALKlangfuseExpert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and…sickn33langfuse-webhooks-eventsConfigure Langfuse webhooks for prompt change notifications and event-driven workflows. Use when setting up prompt change…jeremylongshorewriteslaravel-plugin-discoveryDiscover and evaluate Laravel packages via LaraPlugins.io MCP. Use when the user wants to find plugins, check package health, or…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.ComposioHQ
← Prev81 / 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