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
4,1774,224 · page 88 / 104
openfate-baziUse this skill for Bazi / Four Pillars, BaZi compatibility, True Solar Time, Ten Gods, Da Yun luck cycles, lunar-to-solar…openfate-aiopenfermion-hamiltonianMolecular Hamiltonian construction skill using OpenFermiona5c-aiwritesopenfold3Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab. Use this skill…BioTender-maxopenfold3Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab. Use this skill…xuzhougengopengraph-io-automationAutomate Opengraph IO tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQopenloomi-hooksOpenLoomi × Claude Code hooks installer. Use when the user wants Claude Code's lifecycle (SessionStart, UserPromptSubmit…melandlabsopenloomi-installOpenLoomi install & first-use setup helper for Claude Code. Use when the user wants to install OpenLoomi, configure it, or…melandlabsopenloomiOpenLoomi entrypoint for skill-only agent runtimes without a plugin mechanism. Use when the user mentions OpenLoomi or Loomi…melandlabsopenperplex-automationAutomate Openperplex tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQopenrouter-automationAutomate Openrouter tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQopensim-modelerOpenSim musculoskeletal modeling skill for biomechanical simulation and analysisa5c-aiwritesOpenSSL Manual TLS with Epoll and Memory BIOsImplements TLS connections using OpenSSL where the application handles all network I/O via Linux system calls (send/recv/epoll)…ECNU-ICALKops-daemonCheck claude-ops background daemon end-to-end and auto-fix common issues. Detects stale plist paths after plugin upgrades…davepoonwritesops-doctorHealth check and auto-repair for the ops plugin. Diagnoses manifest errors, broken permissions, invalid configs, stale caches…davepoonwritesops-inspectorAIOps-style one-click inspection skill for CloudBase resources. Use this skill when users need to diagnose errors, check resource…TencentCloudBaseops-orchestrateAutonomous multi-project orchestration engine. Audits all registered projects, structures work into dependency-wired tasks…davepoonwritesops-speedupCross-platform, hardware-adaptive system optimizer. Auto-detects macOS / Linux / WSL / Windows (MINGW/Cygwin/MSYS2) and…davepoonwritesops-triageCross-platform issue triage. Pulls from Sentry (MCP), Linear (MCP), GitHub Issues (gh). Cross-references against code to find…davepoonwritesoptim-agentUse when optimizing configurable system parameters against a measurable scalar objective.Optim-Agentoptim-agentGuide agent-driven parameter optimization for configurable systems with measurable objectives. Use for HPO, inference tuning…sickn33optimoroute-automationAutomate Optimoroute tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQoptuna-study-creatorCreate optuna study creator operations. Auto-activating skill for ML Training. Triggers on: optuna study creator, optuna study…jeremylongshorewritesoracleBest practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).SafeAI-Lab-Xorbital-debrisSkill for orbital debris risk assessment and mitigation planninga5c-aiwritesorchestratorUnified Agent Teams orchestrator for Diverga v12.0.0. Manages Agent Teams creation, VS Arena debate, and subagent dispatch.…brycewang-stanfordorgsci-contribution-framingUse when drafting the mandatory <500-word contribution statement and the discussion section for an Organization Science…brycewang-stanfordorgstud-theory-developmentUse when building the theoretical engine for an Organization Studies (OS) manuscript — the mechanism, process model, or…brycewang-stanfordors-literature-positioningUse when placing an Operations Research (OR) manuscript against the OR/MS literature — separating your model, results, and…brycewang-stanfordors-topic-selectionUse when deciding whether a problem is a fit for Operations Research (OR) and which of its editorial areas it belongs to —…brycewang-stanfordOSI Layer Protocol MappingExplain how a specific network technology interacts with all 7 layers of the OSI model, detailing the specific protocols involved…ECNU-ICALKOverly Verbose AI PersonaAdopt an extremely verbose communication style that constantly over-emphasizes the AI nature of the model in every sentence or…ECNU-ICALKoversized-skillA skill whose body deliberately exceeds the 500-line recommendation.first-flukeowl-protocol-automationAutomate Owl Protocol tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQowner-routingInternal process for the owner-router agent. Defines the step-by-step procedure for determining likely bug owners using strict…jeremylongshorepackaging-validation-plannerSterile barrier system validation planning skill per ISO 11607a5c-aiwritespage-x-automationAutomate Page X tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpagerduty-automationAutomate PagerDuty tasks via Rube MCP (Composio): manage incidents, services, schedules, escalation policies, and on-call…davepoonpagerduty-automationAutomate PagerDuty tasks via Rube MCP (Composio): manage incidents, services, schedules, escalation policies, and on-call…sickn33paper-pipelineOrchestrate the complete post-first-draft polishing pipeline for an academic LaTeX paper by invoking five existing skills in…brycewang-stanfordwritespaper-search-usageThis skill should be used when user asks to "search for papers", "find research papers", "search arXiv", "search PubMed", "find…fcakyonpaper-to-agent-guideTransform research papers into interactive AI agents for explorationbrycewang-stanfordpapersgpt-zotero-guideAI plugin for Zotero with ChatGPT, Claude, and DeepSeek supportbrycewang-stanfordpaperzillaChat with your agent about projects, recommendations, and canonical papers in Paperzilla. Use when users ask for recent project…K-Dense-AIparadym-automationAutomate Paradym tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQparallel-agentsMulti-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when…sickn33parallel-automationAutomate Parallel tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpareto-analyzerPareto analysis skill for identifying vital few causes and prioritizing improvement efforts.a5c-aiwritesparma-automationAutomate Parma tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQ
← Prev88 / 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