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
3,6973,744 · page 78 / 104
hermes-ops-producaoOperar Hermes Agent em produção no VPS — update, restart de gateway, health-check, profiles múltiplos e ambientes sem systemd…Hermes-brasilheyreach-automationAutomate Heyreach tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQheyzine-automationAutomate Heyzine tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhf-memHugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hubsickn33hf-memHugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face…waybarrioshighergov-automationAutomate Highergov tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhighlevel-automationAutomate Highlevel tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQHistology Mnemonic GeneratorGenerates mnemonics for histology topics, ensuring all items are relevant histological structures or cellular components…ECNU-ICALKhive-mind-advancedAdvanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent…foryourhealth111-pixelhive-mind-advancedAdvanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent…ruvnethive-mindByzantine fault-tolerant consensus and distributed coordination. Queen-led hierarchical swarm management with multiple consensus…ruvnethivemind-graphQuery the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/. Use when the user…activeloopaiwriteshivemind-memoryGlobal team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling…activeloopaiwriteshoneybadger-automationAutomate Honeybadger tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhoneyhive-automationAutomate Honeyhive tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhook-developerComplete Claude Code hooks reference - input/output schemas, registration, testing patternsparcadeihookdeck-automationAutomate Hookdeck tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhookify-rulesThis skill should be used when the user asks to create a hookify rule, write a hook rule, configure hookify, add a hookify rule…mturachotspotsystem-automationAutomate Hotspotsystem tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhpo-phenotype-matcherHuman Phenotype Ontology skill for phenotype-driven gene prioritizationa5c-aiwriteshtml-to-image-automationAutomate Html To Image tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhubspot-automationAutomate HubSpot CRM operations (contacts, companies, deals, tickets, properties) via Rube MCP using Composio integration.davepoonhubspot-automationAutomate HubSpot CRM operations (contacts, companies, deals, tickets, properties) via Rube MCP using Composio integration.sickn33hudDiverga HUD (Heads-Up Display) management skill. Configure and manage the research project statusline display. Supports multiple…brycewang-stanfordhumanitix-automationAutomate Humanitix tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhumanloop-automationAutomate Humanloop tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhumann-functional-profilerHUMAnN functional profiling skill for metagenomic pathway analysisa5c-aiwriteshydraulic-analysis-engineHydraulic analysis skill for open channel flow, culverts, and pipe networksa5c-aiwriteshydrologic-modeling-engineHydrologic modeling skill for rainfall-runoff analysis, flood frequency, and watershed analysisa5c-aiwriteshypeauditor-automationAutomate Hypeauditor tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhyperbrowser-automationAutomate Hyperbrowser tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhyperflow-cacheHyperflow memory manager. Use to view, search, add, edit, prune, or clear hyperflow project memory — "show memory", "search…jeremylongshorehyperfocusADHD-friendly output formatting for Claude Code. Restructures responses with evidence-based cognitive accessibility: chunking…jeremylongshorehyperise-automationAutomate Hyperise tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhyperparameter-tunerManage hyperparameter tuner operations. Auto-activating skill for ML Training. Triggers on: hyperparameter tuner, hyperparameter…jeremylongshorewriteshypersonic-aerothermoSpecialized skill for hypersonic vehicle aerodynamic and thermal analysisa5c-aiwriteshypothesis-trackerHypothesis management skill for tracking business hypotheses through testing and validationa5c-aiwriteshystruct-automationAutomate Hystruct tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhysys-dynamic-simulatorAspen HYSYS integration skill for dynamic simulation, pressure-flow networks, and process dynamicsa5c-aiwritesIBM PS/2 MS-DOS SimulationSimulates an IBM PS/2 Model 25-286 computer booting MS-DOS. Interprets user input as DOS commands and returns only the simulated…ECNU-ICALKicalp-topic-selectionUse when deciding whether a theoretical computer science result belongs at ICALP (EATCS) and, if so, whether it is a Track A…brycewang-stanfordiccv-experimentsUse when designing the experimental program for an ICCV paper against the early-March deadline, covering benchmark-drift audits…brycewang-stanfordicims-talent-cloud-automationAutomate Icims Talent Cloud tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQiclr-experimentsUse when designing or auditing ICLR experiments, including baselines, ablations, scaling laws, robustness, statistics…brycewang-stanfordiclr-submissionUse when auditing an ICLR main-conference submission for OpenReview readiness, double-blind anonymity, page limits, reciprocal…brycewang-stanfordicml-submissionUse when auditing an ICML main-track submission for OpenReview, LaTeX formatting, 8-page body, anonymity, supplementary material…brycewang-stanfordicp-evidence-analysisTurn a source-bound company and market dossier into testable ideal-customer-profile hypotheses, buying roles, triggers…elvisunicsme-experimentsUse when designing or auditing IEEE ICSME empirical evaluations, covering real evolving subject systems…brycewang-stanford
← Prev78 / 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