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
3,5533,600 · page 75 / 104
fomo-automationAutomate Fomo tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQforcemanager-automationAutomate Forcemanager tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQforecast-accuracy-analyzerForecast accuracy measurement and improvement skill with error decompositiona5c-aiwritesforensische-prompt-gutachten-erstellenWenn es um Prompt-Injection: Prüfung in diesem Spezialbereich geht: ordnet Akteninhalt, Belege, Lücken und Nachforderungen…Klotzketteforensische-pruefung-prompt-injectionWenn es um Prompt-Injection: Prüfung in diesem Spezialbereich geht: zerlegt Ergebnis, Frist, Zuständigkeit, Beweislast und…Klotzketteforgecad-build-modelBuild or edit a manufacture-realistic `.forge.js` model in a project, then validate it with run, render, inspect, and export…ForgeCADforgeos-skill-intakeUse this skill when importing an external Agent Skill repository into ForgeOS without executing untrusted code.casioreview20-glitchforgeos-skill-promotionUse this skill when deciding whether a filtered candidate skill should become a stable ForgeOS provider.casioreview20-glitchforgetDelete a memory from Origin by ID. Destructive and cannot be undone — prefer `/capture` with `supersedes` for corrections.…davepoonwritesformal-logic-reasonerSkill for formal logical reasoning and argument validationa5c-aiwritesformal-verification-guideFormal methods, theorem proving, and model checking for CS researchbrycewang-stanfordformbricks-automationAutomate Formbricks tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQformcarry-automationAutomate Formcarry tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQformdesk-automationAutomate Formdesk tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQformsite-automationAutomate Formsite tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQfoto-shooting-vertrag-model-release-locationWenn es um Influencer-Recht: Foto-Shooting – Vertrag, Model Release und Location in Influencer-Recht geht: ordnet Sachverhalt…Klotzkettefoundation-models-on-deviceApple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and…mturacfoursquare-automationAutomate Foursquare tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQfraud-risk-assessorFraud risk assessment skill based on the fraud triangle with red flag detectiona5c-aiwritesfraudlabs-pro-automationAutomate Fraudlabs Pro tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQfreshdesk-automationAutomate Freshdesk helpdesk operations including tickets, contacts, companies, notes, and replies via Rube MCP (Composio). Always…davepoonfreshdesk-automationAutomate Freshdesk helpdesk operations including tickets, contacts, companies, notes, and replies via Rube MCP (Composio). Always…sickn33freshservice-automationAutomate Freshservice ITSM tasks via Rube MCP (Composio): create/update tickets, bulk operations, service requests, and outbound…davepoonfreshservice-automationAutomate Freshservice ITSM tasks via Rube MCP (Composio): create/update tickets, bulk operations, service requests, and outbound…sickn33front-automationAutomate Front tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQfse-experimentsUse when designing or auditing ESEC/FSE empirical evaluations, covering real subject systems, fair baselines, SE-standard…brycewang-stanfordftir-analyzerFourier Transform Infrared spectroscopy skill for molecular identification and surface functional group analysisa5c-aiwritesfullenrich-automationAutomate Fullenrich tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQfusion-gene-detectorGene fusion detection skill for oncology applications with multiple caller integrationa5c-aiwritesfx-hedging-strategy-modelerForeign exchange exposure analysis and hedging strategy skill with hedge effectiveness testinga5c-aiwritesgaap-ifrs-compliance-checkerAutomated compliance validation skill for GAAP and IFRS accounting standards with codification referencesa5c-aiwritesgagelist-automationAutomate Gagelist tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQgamma-automationAutomate Gamma tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQgan-ai-automationAutomate Gan AI tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQgas-turbine-cycleExpert skill for gas turbine engine thermodynamic cycle analysis and optimizationa5c-aiwritesgatherup-automationAutomate Gatherup tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQgatk-variant-callerGATK best practices skill for germline and somatic variant calling with joint genotypinga5c-aiwritesgatling-scenario-creatorCreate gatling scenario creator operations. Auto-activating skill for Performance Testing. Triggers on: gatling scenario creator…jeremylongshorewritesgc-log-analyzerAnalyze gc log analyzer operations. Auto-activating skill for Performance Testing. Triggers on: gc log analyzer, gc log analyzer…jeremylongshorewritesgdt-drawingSpecialized skill for geometric dimensioning and tolerancing specification per ASME Y14.5 and ISO 1101a5c-aiwritesgeant4-detector-simulatorGeant4 detector simulation skill for particle transport, detector geometry, and physics process modelinga5c-aiwritesgemini-automationAutomate Gemini tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQgeminiGemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.Health-Yanggenderapi-io-automationAutomate Genderapi IO tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQgenderize-automationAutomate Genderize tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQgenerate_ai_inpainting_promptsGenerate optimized prompts for AI inpainting tools, handling both realistic style transfer (preserving structure) and object…ECNU-ICALKGenerate DALL-E prompts under 500 charactersGenerates descriptive prompts for DALL-E image generation based on user input, strictly adhering to a character limit of 500…ECNU-ICALKGenerate Inference Code for Image-to-HTML Keras ModelGenerates Python code to perform inference on a pre-trained Keras Image-to-HTML model, utilizing specific image preprocessing…ECNU-ICALK
← Prev75 / 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