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
3,7933,840 · page 80 / 104
ip2location-automationAutomate Ip2location tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQip2location-io-automationAutomate Ip2location IO tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQip2proxy-automationAutomate Ip2proxy tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQip2whois-automationAutomate Ip2whois tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQipdata-co-automationAutomate Ipdata co tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQipinfo-io-automationAutomate Ipinfo IO tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQiqair-airvisual-automationAutomate Iqair Airvisual tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQiso-standards-compliance-checkerMedical device standards compliance verification skill for ISO 13485, ISO 14971, IEC 62304, IEC 60601, and related standardsa5c-aiwritesiso10993-evaluatorBiological evaluation planning skill implementing ISO 10993-1 for biocompatibility testing strategya5c-aiwritesiso14971-risk-analyzerComprehensive risk management skill implementing ISO 14971:2019 methodology for medical device risk analysisa5c-aiwritesissta-author-responseUse when drafting an ISSTA author response for the rebuttal window or planning a Major-Revision resubmission, covering…brycewang-stanfordjanitor-discoverFind new skills on GitHub or check a specific skill before installing. Use when the user wants to search for skills, evaluate a…jeremylongshorejanitor-fixAutomatically fix skill problems (safe preview first). Also use with --prune to find and remove broken symlinks, empty…jeremylongshorejanitor-reportFull health check of all your skills in one report. Use when the user wants to check for errors, find duplicates, detect broken…jeremylongshorejapan-utility-klageantraege-verletzungWenn es um Japan Utility Model Vergleich in gebrauchsmusterrecht geht: erstellt den passenden Entwurf aus Sachverhalt, Norm…Klotzkettejbes-rebuttalUse when a Journal of Business & Economic Statistics (JBES) decision letter arrives (R&R or major revision) and a response…brycewang-stanfordjeea-literature-positioningUse when the contribution of a Journal of the European Economic Association (JEEA) manuscript relative to the frontier is fuzzy…brycewang-stanfordjeea-theory-modelUse when a Journal of the European Economic Association (JEEA) manuscript contains a theoretical or structural model whose…brycewang-stanfordjeem-theory-modelUse when a Journal of Environmental Economics and Management (JEEM) manuscript needs a resource/pollution-control or…brycewang-stanfordjegeo-identificationUse when the inference argument is the bottleneck for a Journal of Economic Geography (JEG) manuscript — spatial causal designs…brycewang-stanfordjep-editor-strategyUse when working with the Journal of Economic Perspectives (JEP) editorial team — the managing-editor-led model and the symposium…brycewang-stanfordjie-rebuttalUse when drafting the response letter for a revise-and-resubmit at the Journal of International Economics (JIE) — answering…brycewang-stanfordjigsawstack-automationAutomate Jigsawstack tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQjira-automationAutomate Jira tasks via Rube MCP (Composio): issues, projects, sprints, boards, comments, users. Always search tools first for…davepoonjira-automationAutomate Jira tasks via Rube MCP (Composio): issues, projects, sprints, boards, comments, users. Always search tools first for…sickn33jira-ticket-generatorGenerate jira ticket generator operations. Auto-activating skill for Enterprise Workflows. Triggers on: jira ticket generator…jeremylongshorewritesjleo-rebuttalUse when a Journal of Law, Economics, and Organization (JLEO) decision letter has arrived and you need a response-letter strategy…brycewang-stanfordjleo-theory-modelUse when building or sharpening the formal model for a Journal of Law, Economics, and Organization (JLEO) manuscript —…brycewang-stanfordjmsc-algorithmUse when designing and analyzing a solution algorithm for a 《管理科学学报》 (Journal of Management Sciences in China) manuscript —…brycewang-stanfordjmsc-behavioral-omUse when taking the behavioral operations (行为运作) path of a 《管理科学学报》 (Journal of Management Sciences in China) manuscript —…brycewang-stanfordjmsc-fit-positioningUse when judging whether a manuscript fits 《管理科学学报》 (Journal of Management Sciences in China) — a 数理/定量 (mathematical /…brycewang-stanfordjmsc-managerial-insightsUse when deriving managerial insights for a 《管理科学学报》 (Journal of Management Sciences in China) manuscript — translating proven…brycewang-stanfordjmsc-model-buildingUse when building the formal model for a 《管理科学学报》 (Journal of Management Sciences in China) manuscript — making decision…brycewang-stanfordjmsc-problem-formulationUse when formalizing the decision problem before model building for a 《管理科学学报》 (Journal of Management Sciences in China)…brycewang-stanfordjmsc-proofsUse when stating and proving propositions / theorems for a 《管理科学学报》 (Journal of Management Sciences in China) manuscript —…brycewang-stanfordjobnimbus-automationAutomate Jobnimbus tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQjournal-of-climateUse when targeting Journal of Climate or deciding whether a climate-dynamics or climate-variability manuscript fits this venue.…brycewang-stanfordjqte-econometric-methodsUse when the empirical core of a 《数量经济技术经济研究》 (JQTE) manuscript is an econometric model — time series, cointegration…brycewang-stanfordjqte-measurementUse when the contribution of a 《数量经济技术经济研究》 (JQTE) manuscript is productivity / efficiency / index measurement — TFP, Malmquist…brycewang-stanfordjumpcloud-automationAutomate Jumpcloud tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQjunglescout-automationAutomate Junglescout tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQjupyter-reproducibility-checkerSkill for checking and ensuring Jupyter notebook reproducibilitya5c-aiwritesk6-script-generatorGenerate k6 script generator operations. Auto-activating skill for Performance Testing. Triggers on: k6 script generator, k6…jeremylongshorewriteskadoa-automationAutomate Kadoa tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQkaggle-automationAutomate Kaggle tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQkaizen-event-facilitatorRapid improvement workshop planning and execution skill with team coordination, metrics tracking, and follow-up managementa5c-aiwriteskaleido-automationAutomate Kaleido tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQkaytantoprofiiliPlugarikokoelman räätälöinti organisaation omiin käytäntöihin. Käytä tätä skilliä, kun käyttäjä haluaa mukauttaa, konfiguroida…akunikkola
← Prev80 / 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