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
3,4093,456 · page 72 / 104
ecai-experimentsUse when designing or auditing the evidence in an ECAI paper — choosing proof versus experiment by claim shape across ECAI's…brycewang-stanfordeccv-experimentsUse when designing or auditing the experimental program of an ECCV paper — benchmark selection that survives a September…brycewang-stanfordechtpost-automationAutomate Echtpost tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQecon-reviewer经济学顶刊标准审稿Skill。按AER/QJE/Econometrica/JPE顶刊标准审查论文输出(图表+回归表),列出潜在致命缺陷。触发词:顶刊审稿/论文审查/econ reviewer/经济学期刊标准/PRbrycewang-stanfordeconomic-indicator-trackerMacroeconomic indicator monitoring and analysis skill with trend identification and forecastinga5c-aiwritesecopol-identificationUse when the identification argument is the bottleneck for an Economic Policy (EP) manuscript — causal identification of a policy…brycewang-stanfordecta-identificationUse when the bottleneck is identification and inference for an Econometrica manuscript — identification conditions and asymptotic…brycewang-stanfordecta-theory-modelUse when the central theorem of an Econometrica manuscript must be stated cleanly and proven completely — assumptions…brycewang-stanfordecta-topic-selectionUse when judging whether a result is general, deep, and method-driven enough to belong in Econometrica, and when sharpening the…brycewang-stanfordeffort-xhigh-passValidate a skill when asked. Don't use for unrelated docs.luongnv89einstieg-in-den-skill-verbund-handels-und-gesellschaftsrechtWenn es um Einstieg in den Skill-Verbund Handels- und Gesellschaftsrecht in Fachanwalt Handels- und Gesellschaftsrecht geht…Klotzketteeinstieg-in-den-skill-verbund-internationales-wirtschaftsrechtWenn es um Einstieg in den Skill-Verbund Internationales Wirtschaftsrecht in Fachanwalt Internationales Wirtschaftsrecht geht…Klotzketteeinstieg-in-den-skill-verbund-sozialrechtWenn es um Einstieg in den Skill-Verbund Sozialrecht in Fachanwalt Sozialrecht geht: klärt Rolle, Ziel, Frist, Unterlagen und den…Klotzketteeinstieg-in-den-skill-verbund-verkehrsrechtWenn es um Einstieg in den Skill-Verbund Verkehrsrecht in Fachanwalt Verkehrsrecht geht: klärt Rolle, Ziel, Frist, Unterlagen und…Klotzketteelectre-comparatorELECTRE family methods skill for outranking-based decision support with concordance and discordance analysisa5c-aiwritesElectrolytic Synthesis of Boron-Doped Titanium Dioxide PhotocatalystGuides the electrochemical anodic dissolution of titanium to produce boron-doped titanium hydroxide nanoparticles, followed by…ECNU-ICALKelifeUse when targeting eLife or deciding whether a life-sciences manuscript fits this open-access life-sciences journal. Encodes…brycewang-stanfordelorus-automationAutomate Elorus tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQemailable-automationAutomate Emailable tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQemaillistverify-automationAutomate Emaillistverify tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQemailoctopus-automationAutomate Emailoctopus tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQemcee-mcmc-sampleremcee MCMC skill for Bayesian parameter estimation and posterior sampling in physics applicationsa5c-aiwritesemelia-automationAutomate Emelia tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQencodian-automationAutomate Encodian tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQendorsal-automationAutomate Endorsal tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQengineering-report-generatorEngineering report generation skill for standard technical reports and calculation sheetsa5c-aiwritesenginemailer-automationAutomate Enginemailer tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQEnglish Input Chinese Output ResponseRespond in Chinese when the user communicates in English. This skill is used when the user explicitly requests a language…ECNU-ICALKenhance-agent-promptsUse when improving agent prompts, frontmatter, and tool restrictions.agent-shenhance-claude-memoryUse when improving CLAUDE.md or AGENTS.md project memory files.agent-shenhance-cross-fileUse when checking cross-file consistency: tools vs frontmatter, agent references, duplicate rules, contradictions.agent-shEnhanced Interaction AlgorithmA structured framework for managing conversations using session-based memory, sentiment analysis, and adaptive response…ECNU-ICALKenigma-automationAutomate Enigma tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQentelligence-automationAutomate Entelligence tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQenvironmental-fate-modelerEnvironmental nanosafety skill for modeling nanomaterial environmental fate and transporta5c-aiwritesenvironmental-impact-analyzerEnvironmental impact assessment skill for NEPA, wetlands, and endangered species screeninga5c-aiwriteseodhd-apis-automationAutomate Eodhd Apis tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQepic-games-automationAutomate Epic Games tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQepics-control-systemEPICS control system skill for accelerator and beamline instrument control and monitoringa5c-aiwritesepsl-figures-and-tablesUse when building figures and tables for an Earth and Planetary Science Letters (EPSL) manuscript. A Letter lives or dies by a…brycewang-stanfordequipment-sizing-calculatorProcess equipment sizing skill using established engineering correlations and standardsa5c-aiwritesesignatures-io-automationAutomate Esignatures IO tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQespocrm-automationAutomate Espocrm tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQesputnik-automationAutomate Esputnik tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQest-topic-selectionUse when deciding whether a problem fits Environmental Science & Technology (ES&T) and which article type to target. ES&T rewards…brycewang-stanfordestimate_additional_survival_time_conditionalEstimates additional survival time for censored patients using a Cox model, calculating expected time via a weighted average of…ECNU-ICALKetermin-automationAutomate Etermin tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQeval-harnessFormal evaluation framework for OpenAI Codex sessions implementing eval-driven development (EDD) principlesmturac
← Prev72 / 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