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
2,2572,304 · page 48 / 104
regression-modelingModeling relationships between variables using regression. Covers simple linear regression, multiple regression, polynomial…majiayu000regulatory-draftingRegulatory Drafting agent for healthcare workflows.majiayu000reiSet up Rei Qwen3 Coder as a model provider. Use when configuring coder.reilabs.org, adding Rei to Clawdbot, or troubleshooting…majiayu000remote-configRemote configuration skill for feature flags.a5c-aiwritesREPL DevelopmentExpert skill for building interactive REPLs with rich editing and evaluation featuresa5c-aiwritesrepomixdescription: Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases…majiayu000repomix-explorerUse this skill when the user wants to analyze or explore a codebase (remote repository or local repository) using Repomix.…majiayu000report-writer-agentAutomated report generator for daily, weekly, and monthly performance summaries. Creates markdown reports with trading…majiayu000req-to-executable-prompt將使用者的自然語言需求,轉換成「Codex 可直接執行」的工程指令 prompt。 輸出內容包含:背景、明確目標、可驗收條件、操作步驟、不可違反的限制、與交付格式。 適用於任何語言、任何 repo、任何專案階段。majiayu000requesting-human-decisionsUse when requesting human decisions is required during kernel work, especially when the result must be traceable, independently…casioreview20-glitchresearchComprehensive research skill using Zai MCP web search and native Claude Code toolsmajiayu000research-analystComprehensive research and synthesis agent specializing in multi-source information gathering, critical analysis, and integrated…majiayu000research-and-incorporateResearch external topics, create comprehensive analysis, determine project applicability, and incorporate learnings into Serena…majiayu000research-and-synthesisFetch and summarize authoritative external sources into actionable guidance using MCP helpers. EXCLUSIVE to researcher agent.majiayu000writesresearch-carmandale-agent-configDocument codebase as-is with thoughts directory for historical contextmajiayu000research-cog#1 on DeepResearch Bench (Feb 2026). Deep research agent powered by CellCog. Market research, competitive analysis, stock…majiayu000research-ingredientDeep research on a specific ingredient using the product-research MCPmajiayu000research-agentPerforms legal research for complex petitions using websearch tool. Provides statutes, principles, and argument frameworks…majiayu000researchWeb research skill for augmenting agent context with current information. Used when outdated information could lead to broken…majiayu000research-learningsUse this skill when you need to search institutional learnings in docs/solutions/ for relevant past solutions before implementing…majiayu000research-literatureResearch Literature agent for healthcare workflows.majiayu000research-mission-generatorPackage conversation research into a GSD-ready mission package. Produces a three-stage Vision → Research → Mission pipeline as a…majiayu000research-mission-generatorPackage conversation research into a GSD-ready mission package. Produces a three-stage Vision → Research → Mission pipeline as a…majiayu000research-orchestrationParallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis…a5c-aiwritesresearch-skill调研最佳实践的 Skill。当需要了解某个领域的方法论、工具、最佳实践时触发。触发词:调研、research、了解一下、有什么方法、最佳实践。majiayu000research-wikiPersistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire…majiayu000writesresearch-wikiPersistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire…majiayu000writesresearcher-role-skillProfessional technical solutions research skill for investigating technologies, analyzing best practices, evaluating feasibility…majiayu000researching-codebaseThis skill should be used when the user asks to "research the codebase", "understand how X works", "explore the code", "gather…majiayu000researching-phasesUse this skill when researching how to implement a phase standalone, investigating implementation approaches before planning, or…majiayu000writesresearchquestionsWrite a structured research prompt document — questions only, no answersmajiayu000resolving-user-intentUse when resolving user intent is required during kernel work, especially when the result must be traceable, independently…casioreview20-glitchrespectfullyWraps any prompt with a reminder to respect CLAUDE.md filesmajiayu000response-timestampsAutomatically adds timestamps and execution duration to all Claude responsesmajiayu000retellai-advanced-troubleshootingRetell AI advanced troubleshooting \u2014 AI voice agent and phone call\ \ automation.\nUse when working with Retell AI for voice…jeremylongshorewritesretellai-architecture-variantsRetell AI architecture variants \u2014 AI voice agent and phone call\ \ automation.\nUse when working with Retell AI for voice…jeremylongshorewritesretellai-ci-integrationRetell AI ci integration \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice agents…jeremylongshorewritesretellai-cost-tuningRetell AI cost tuning \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice agents, phone…jeremylongshorewritesretellai-enterprise-rbacRetell AI enterprise rbac \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice agents…jeremylongshorewritesretellai-incident-runbookRetell AI incident runbook \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice agents…jeremylongshorewritesretellai-known-pitfallsRetell AI known pitfalls \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice agents…jeremylongshorewritesretellai-load-scaleRetell AI load scale \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice agents, phone…jeremylongshorewritesretellai-local-dev-loopRetell AI local dev loop \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice agents…jeremylongshorewritesretellai-multi-env-setupRetell AI multi env setup \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice agents…jeremylongshorewritesretellai-observabilityRetell AI observability \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice agents…jeremylongshorewritesretellai-performance-tuningRetell AI performance tuning \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice…jeremylongshorewritesretellai-policy-guardrailsRetell AI policy guardrails \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice agents…jeremylongshorewritesretellai-rate-limitsRetell AI rate limits \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice agents, phone…jeremylongshorewrites
← Prev48 / 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