Agent skills

AI & Agents skills

4,965 skills an agent can load when the work is AI & Agents — read straight from the source repositories, with what each one does, what ships alongside it, and where it came from.

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
4,8014,848 · page 101 / 104
turso-automationAutomate Turso tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtwitch-automationAutomate Twitch tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtwitter-automationAutomate Twitter/X tasks via Rube MCP (Composio): posts, search, users, bookmarks, lists, media. Always search tools first for…davepoontwitter-automationAutomate Twitter/X tasks via Rube MCP (Composio): posts, search, users, bookmarks, lists, media. Always search tools first for…sickn33twocaptcha-automationAutomate Twocaptcha tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtypefully-automationAutomate Typefully tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtypespec-create-agentGenerate a complete TypeSpec declarative agent with instructions, capabilities, and conversation starters for Microsoft 365…githubtypless-automationAutomate Typless tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQu301-automationAutomate U301 tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQubiquitous-languageExtract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical…stevesolunudi-labeling-generatorUnique Device Identification (UDI) and labeling compliance skill for generating compliant labels and device identifiersa5c-aiwritesultraworkBinding ultrawork mode directive for omo-senpi. When a prompt contains ultrawork or ulw, the omo input hook injects the full…code-yeongyuUndertaker Meme Prank RoleplayA roleplay skill where the AI responds helpfully and flirtatiously to a question, suggests a date, then abruptly segues to an…ECNU-ICALKunified-ai-gatewayOperate and evaluate Unified AI System through nine governed MCP tools, including provider-free prompt enhancement, while…sickn33uninstallCompletely remove claude-ops plugin, all stored credentials, cached files, shell exports, and MCP registrations. Confirms each…davepoonwritesunione-automationAutomate Unione tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQunique_mac_and_cheese_generator_with_image_promptsGenerates creative macaroni and cheese recipes using unique cheeses, formatted with specific metadata, horizontal nutrition…ECNU-ICALKUnique Macaroni and Cheese Recipe Generator with Image PromptGenerates unique macaroni and cheese recipes using non-traditional cheeses, formatted with specific time metrics, US…ECNU-ICALKUnity AI Agent with Interruptible TargetingImplement or modify Unity AI scripts where agents patrol checkpoints but interrupt movement to attack the nearest target within a…ECNU-ICALKUnity ML-Agents Dynamic Object Observation with Null SafetyImplement the CollectObservations method for a Unity ML-Agent to track the agent's position and a list of dynamic objects (like…ECNU-ICALKunpause-subsRe-enable the skill bus after pausing. Restores subscription processing.composio-communityupdate-pr-summaryThis skill should be used when user asks to "update PR summary", "update PR description", "rewrite PR body", "refresh PR title…fcakyonupdown-io-automationAutomate Updown IO tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQuptimerobot-automationAutomate Uptimerobot tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQuse-related-risk-analyzerUse-related risk analysis skill for identifying hazards associated with user interaction per IEC 62366-1a5c-aiwritesused-skillA fixture skill that gets invoked in the fixture transcript.anandsaini18User ResearchA comprehensive skill for user research — covering research methods, interview techniques, participant recruitment, synthesis…cosmicstack-labsuser-story-generatorGenerate user story generator operations. Auto-activating skill for Enterprise Workflows. Triggers on: user story generator, user…jeremylongshorewritesuserlist-automationAutomate Userlist tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQusing-agent-relayUse when you are a registered relay agent (a spawned worker, or a lead that called register_agent) coordinating with peers in…AgentWorkforceusing-elicitationsAsks the user mid-run from inside an FSM action or Python `type: user` agent via the elicitation tools — `request_tool_access`…friday-platformusing-startup-superpowersUse at the start of any conversation about a startup idea, product validation, founder strategy, or work inside a `startup/`…davepoonusing-superpowersUse when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response…BioTender-maxusing-superpowersUse when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response…ECNU-ICALKusing-superpowersUse when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response…sickn33uv-vis-nir-analyzerUV-Vis-NIR spectroscopy skill for optical property characterization including plasmon resonance and bandgap analysisa5c-aiwritesv0-automationAutomate V0 tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQV3 Performance OptimizationAchieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory…ruvnetvalidate-pluginValidate a Claude Code plugin structure, frontmatter, and MCP tool referencesruvnetwritesvarlock-claude-skillSecure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commitssickn33varlockSecure-by-default environment variable management for Claude Code sessions.sickn33vasp-dft-calculatorVASP DFT calculation skill for electronic structure, band structures, and materials property predictionsa5c-aiwritesvasp-dft-executorVASP DFT calculation skill for electronic structure, geometry optimization, and property prediction of nanomaterialsa5c-aiwritesvaultr-memoryExtract and update personal memories from Vaultr notes into structured memory files. Use when the user wants to update their…skoowoovector-db-patternsEmbedding strategies, ANN algorithms, hybrid search, RAG chunking strategies, and reranking for semantic search and retrieval.vibeevalvector-searchVector search via embeddings_* (large-scale HNSW) and ruvllm_hnsw_* (WASM router for ≤11 hot patterns), with RaBitQ 1-bit…ruvnetvendor-risk-scorerComprehensive supplier risk scoring skill with multi-dimensional risk assessmenta5c-aiwritesvenly-automationAutomate Venly tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQ
← Prev101 / 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