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
3,1693,216 · page 67 / 104
cloudpress-automationAutomate Cloudpress tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcmuxControl cmux workspaces, panes, surfaces, and agent sessions safely from macOS terminal workflows.sickn33cnc-programmingExpert skill for CNC programming and toolpath optimization using CAM softwarea5c-aiwritescoassemble-automationAutomate Coassemble tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcoda-automationAutomate Coda tasks via Rube MCP (Composio): manage docs, pages, tables, rows, formulas, permissions, and publishing. Always…davepooncoda-automationAutomate Coda tasks via Rube MCP (Composio): manage docs, pages, tables, rows, formulas, permissions, and publishing. Always…sickn33codacy-automationAutomate Codacy tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcode-llm-papers-guideSurvey and paper collection on LLMs for code generationbrycewang-stanfordcodebase-migrateRun large codebase migrations and multi-file refactors. Uses the Composio CLI to coordinate issue tracking, batched PRs, and CI…composio-communityCodeGPT Expert Dialogue and Code GenerationSimulates a structured dialogue between 5 specific experts to refine complex coding requirements, then generates high-complexity…ECNU-ICALKcodeinterpreter-automationAutomate Codeinterpreter tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcodereadr-automationAutomate Codereadr tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcodex-deadA fixture Codex skill that is installed but never invoked.anandsaini18codex-usedA fixture Codex skill that gets invoked in the fixture rollout.anandsaini18coding-agentDelegate coding work to Codex, Claude Code, OpenCode, or Pi as background workers; not simple edits or read-only code lookup.Health-Yangcoding-agentDelegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or…nexu-iocoding-agentDelegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or…SafeAI-Lab-Xcognitive-patternDefine and manage cognitive patterns for agent reasoning and decision-makingruvnetwritescohere-webhooks-eventsImplement Cohere streaming event handling, SSE patterns, and connector webhooks. Use when building streaming UIs, handling…jeremylongshorewritescoinmarketcal-automationAutomate Coinmarketcal tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcoinmarketcap-automationAutomate Coinmarketcap tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcoinranking-automationAutomate Coinranking tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcolloidal-stability-analyzerColloidal stability assessment skill for evaluating nanoparticle dispersion stability through zeta potential, aggregation…a5c-aiwritescolm-submissionUse when preparing or auditing a COLM submission on OpenReview — the late-March abstract and full-paper deadlines, the strict…brycewang-stanfordcommitStage, commit, and push changes for the sewage project. Creates a branch, commits with a descriptive message, pushes, and…brycewang-stanfordwritescommit-stagedThis skill should be used when user asks to "commit these changes", "write commit message", "stage and commit", "create a…fcakyoncomparable-company-analyzerPublic company comparable analysis skill with peer selection, multiple calculation, and football field visualizationa5c-aiwritescompetitive-intelligence-trackerCompetitive intelligence collection and analysis skill for systematic competitor monitoringa5c-aiwritescomposing-contextInternal pattern guide for composing turn-local retrieval-gated context into a synthetic user-message preface. Documents the…friday-platformcomposio-automationAutomate Composio tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcomposio-search-automationAutomate Composio Search tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcomputer-use-agentsBuild AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text.…sickn33comsol-multiphysics-executorCOMSOL Multiphysics skill for continuum-scale nanomaterial and device modelinga5c-aiwritescomsol-multiphysics-modelerCOMSOL finite element skill for multiphysics simulations including electromagnetics, heat transfer, and fluid dynamicsa5c-aiwritesconda-env-managerUse this skill whenever the user wants to create, activate, list, export, update, clone, remove, or otherwise manage conda…BioTender-maxConfigurable Transformer Training with Best Model CheckpointingImplements a PyTorch Transformer model with configurable layer dimensions (lists for d_model and dim_feedforward), correct…ECNU-ICALKconfigure-eccInteractive installer for Everything OpenAI Codex — guides users through selecting and installing skills and rules to user-level…mturacconfluence-page-generatorGenerate confluence page generator operations. Auto-activating skill for Enterprise Workflows. Triggers on: confluence page…jeremylongshorewritesconfusion-matrix-generatorGenerate confusion matrix generator operations. Auto-activating skill for ML Training. Triggers on: confusion matrix generator…jeremylongshorewritesconn-toolUse this skill whenever the user wants to perform advanced functional connectivity (ROI-to-ROI, seed-to-voxel, ICA) or effective…BioTender-maxconnect-appsConnect Claude to external apps like Gmail, Slack, GitHub. Use this skill when the user wants to send emails, create issues, post…ComposioHQconnect-appsConnect Claude to external apps like Gmail, Slack, GitHub. Use this skill when the user wants to send emails, create issues, post…ECNU-ICALKconnecteam-automationAutomate Connecteam tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQconnection-pool-analyzerAnalyze connection pool analyzer operations. Auto-activating skill for Performance Testing. Triggers on: connection pool…jeremylongshorewritesconsequence-modelerConsequence analysis skill for dispersion modeling, fire/explosion analysis, and effect zone determinationa5c-aiwritesopen-knowledge-pack-knowledge-base-consolidatePromote existing research into a canonical article under `articles/` in a Knowledge Base project (the `knowledge-base` starter…inkeepconstitutional-aiAnthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with…Orchestra-Researchconstraint-identifierSystem bottleneck identification and exploitation skill with throughput analysis and five focusing steps implementationa5c-aiwrites
← Prev67 / 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