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 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
4,965 found
4,4654,512 · page 94 / 104
retently-automationAutomate Retently tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQreturns-authorization-processorAutomated return authorization and routing skill optimizing return paths and customer experiencea5c-aiwritesreturns-disposition-optimizerAI-powered returns inspection and disposition decision skill maximizing value recoverya5c-aiwritesrev-ai-automationAutomate Rev AI tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQReverse Query GenerationGenerates a natural language query or question that would lead to a specific provided response, ensuring the output matches the…ECNU-ICALKrevolt-automationAutomate Revolt tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQRingCentral AutomationRingCentral automation via Rube MCP -- toolkit not currently available in Composio; no RING_CENTRAL_ tools foundComposioHQring_central-automationAutomate RingCentral tasks via Rube MCP (Composio): calls, messages, meetings, and unified communications. Always search tools…ComposioHQrippling-automationAutomate Rippling tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQrisk-assessment-creatorCreate risk assessment creator operations. Auto-activating skill for Enterprise Workflows. Triggers on: risk assessment creator…jeremylongshorewritesrisk-register-managerRisk register management skill for systematic risk identification, assessment, and trackinga5c-aiwritesrisk-registerBuild and maintain a project or product risk register. Use when asked to create a risk register, identify project risks, build a…mohitagw15856ritekit-automationAutomate Ritekit tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQrkvst-automationAutomate Rkvst tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQroadmap-generatorGenerate roadmap generator operations. Auto-activating skill for Enterprise Workflows. Triggers on: roadmap generator, roadmap…jeremylongshorewritesroc-curve-plotterManage roc curve plotter operations. Auto-activating skill for ML Training. Triggers on: roc curve plotter, roc curve plotter…jeremylongshorewritesrocketlane-automationAutomate Rocketlane tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQroot-cause-analyzerSystematic root cause identification skill with 5 Whys, fishbone diagrams, fault tree analysis, and hypothesis testinga5c-aiwritesrootly-automationAutomate Rootly tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQroute-optimization-engineAI-powered route planning and optimization skill using advanced algorithms (VRP, TSP) to minimize transportation costs, reduce…a5c-aiwritesroute4me-automationAutomate Route4me tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQrouterbase-model-gatewayConfigure RouterBase as an OpenAI compatible model gateway for AI apps, with routing, fallback, media generation, and credential…cosmicstack-labsrt-journal-matchUse when an author asks "which journal should I send this to?" or needs the best resubmission target after a reject. Profiles the…brycewang-stanfordrula-reba-assessorRapid Upper Limb Assessment (RULA) and Rapid Entire Body Assessment (REBA) skill for posture evaluation.a5c-aiwritesrulesyncGenerates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a…dyoshikawarun-agentConfigures and runs agents with different adapters including Claude, OpenAI, CrewAI, Lyzr, and GitHub Models. Supports local…open-gitagentrun-deep-sweRun reproducible DeepSWE coding-agent benchmark evaluations through OpenRouter and mini-swe-agent.sickn33run_modelsUse this skill whenever the user wants to run phenotype-prediction models, browse model cards, map model inputs/outputs, or…BioTender-maxruntime-adaptersUse when creating Codex, Claude Code, Gemini CLI, Cursor, or AGENTS.md runtime adapters from one canonical agent core. Use…agentlas-airvf-manageManage RVF (Ruflo Vector Format) files for portable agent memory and cross-platform transferruvnetwritessafe-modePrevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict…rohitg00safety-assessmentSkill for structured safety assessment following ARP4761 guidelinesa5c-aiwritessafety-guardUse this skill to prevent destructive operations when working on production systems or running agents autonomously.mturacsafety-stock-calculatorDynamic safety stock and reorder point optimization skill based on demand variability, lead times, and service level targetsa5c-aiwritessafetyculture-automationAutomate Safetyculture tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsage-automationAutomate Sage tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsalesforce-automationAutomate Salesforce tasks via Rube MCP (Composio): leads, contacts, accounts, opportunities, SOQL queries. Always search tools…davepoonsalesforce-automationAutomate Salesforce tasks via Rube MCP (Composio): leads, contacts, accounts, opportunities, SOQL queries. Always search tools…sickn33salesforce-service-cloud-automationAutomate Salesforce Service Cloud tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsalesmate-automationAutomate Salesmate tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsalmon-quantifierSalmon pseudo-alignment skill for fast and accurate transcript quantificationa5c-aiwritessample-skillUse when validating the SkillForge validator itself - exercises every supported frontmatter feature: boolean user-invocable, an…tripleyakwritessandbox-claude-insideRun Claude Code INSIDE a ca-sandbox box (`--with-claude`). Routed to when the user wants an agent loop running against an…arbiterForgesap-successfactors-automationAutomate SAP SuccessFactors tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsatismeter-automationAutomate Satismeter tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsaxs-waxs-analyzerSmall/Wide Angle X-ray Scattering skill for nanostructure size, shape, and organization analysisa5c-aiwritesscale-up-analyzerProcess scale-up analysis skill for dimensional analysis, similarity criteria, and pilot-to-production transitionsa5c-aiwritesscale-up-process-analyzerProcess engineering skill for analyzing and optimizing nanomaterial synthesis scale-up from lab to productiona5c-aiwrites
← Prev94 / 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