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
2,7852,832 · page 59 / 104
agent-github-pr-managerAgent skill for github-pr-manager - invoke with $agent-github-pr-managerruvnetagent-goal-plannerAgent skill for goal-planner - invoke with $agent-goal-plannerruvnetagent-gossip-coordinatorAgent skill for gossip-coordinator - invoke with $agent-gossip-coordinatorruvnetagent-health-monitoringMonitor AI agent health, detect anomalies, set up alerting, and maintain observability dashboards for production multi-agent…cosmicstack-labsagent-hierarchical-coordinatorAgent skill for hierarchical-coordinator - invoke with $agent-hierarchical-coordinatorruvnetagent-implementer-sparc-coderAgent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coderruvnetagent-incident-postmortemRun a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway…mohitagw15856agent-issue-trackerAgent skill for issue-tracker - invoke with $agent-issue-trackerruvnetagent-linterAgent ve skill dosyalarinin yapisal dogrulamasi. Frontmatter kontrol, naming convention, zorunlu bolum kontrolu, tutarlilik…vibeevalagent-load-balancerAgent skill for load-balancer - invoke with $agent-load-balancerruvnetagent-mail-automationAutomate Agent Mail tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQagent-manager-skillManage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.sickn33agent-matrix-optimizerAgent skill for matrix-optimizer - invoke with $agent-matrix-optimizerruvnetagent-memory-coordinatorAgent skill for memory-coordinator - invoke with $agent-memory-coordinatorruvnetagent-memory-mcpA hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns…sickn33agent-memoryA hybrid memory system that provides persistent, searchable knowledge management for AI agents.sickn33agent-memory-systemsMemory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the…sickn33agent-mesh-coordinatorAgent skill for mesh-coordinator - invoke with $agent-mesh-coordinatorruvnetagent-multi-repo-swarmAgent skill for multi-repo-swarm - invoke with $agent-multi-repo-swarmruvnetagent-neural-networkAgent skill for neural-network - invoke with $agent-neural-networkruvnetagent-orchestration-improve-agentSystematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.sickn33agent-orchestration-multi-agent-optimizeOptimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving…sickn33agent-pagerank-analyzerAgent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzerruvnetagent-paymentsAgent skill for payments - invoke with $agent-paymentsruvnetagent-performance-analyzerAgent skill for performance-analyzer - invoke with $agent-performance-analyzerruvnetagent-performance-benchmarkerAgent skill for performance-benchmarker - invoke with $agent-performance-benchmarkerruvnetagent-performance-monitorAgent skill for performance-monitor - invoke with $agent-performance-monitorruvnetagent-performance-optimizerAgent skill for performance-optimizer - invoke with $agent-performance-optimizerruvnetagent-plannerAgent skill for planner - invoke with $agent-plannerruvnetagent-pr-managerAgent skill for pr-manager - invoke with $agent-pr-managerruvnetagent-production-validatorAgent skill for production-validator - invoke with $agent-production-validatorruvnetagent-project-board-syncAgent skill for project-board-sync - invoke with $agent-project-board-syncruvnetagent-pseudocodeAgent skill for pseudocode - invoke with $agent-pseudocoderuvnetagent-queen-coordinatorAgent skill for queen-coordinator - invoke with $agent-queen-coordinatorruvnetagent-quorum-managerAgent skill for quorum-manager - invoke with $agent-quorum-managerruvnetagent-raft-managerAgent skill for raft-manager - invoke with $agent-raft-managerruvnetagent-refinementAgent skill for refinement - invoke with $agent-refinementruvnetagent-release-managerAgent skill for release-manager - invoke with $agent-release-managerruvnetagent-release-swarmAgent skill for release-swarm - invoke with $agent-release-swarmruvnetagent-repo-architectAgent skill for repo-architect - invoke with $agent-repo-architectruvnetagent-researcherAgent skill for researcher - invoke with $agent-researcherruvnetagent-resource-allocatorAgent skill for resource-allocator - invoke with $agent-resource-allocatorruvnetagent-reviewerAgent skill for reviewer - invoke with $agent-reviewerruvnetagent-runtime-hooksAgent runtime lifecycle hooks. Use for before/after tool or step hooks, tool mocks, human intervention, sub-agent calls, context…lobehubagent-safla-neuralAgent skill for safla-neural - invoke with $agent-safla-neuralruvnetagent-sandboxAgent skill for sandbox - invoke with $agent-sandboxruvnetagent-scout-explorerAgent skill for scout-explorer - invoke with $agent-scout-explorerruvnetagent-sona-learning-optimizerAgent skill for sona-learning-optimizer - invoke with $agent-sona-learning-optimizerruvnet
← Prev59 / 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