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
1,1051,152 · page 24 / 104
cherry-assistant-guide从当前安装包查询 Cherry Studio 产品信息。当用户询问功能、路由、快捷键、Provider、语言、Agent、频道、定时任务、Code CLI 或当前版本时触发。CherryHQchoosing-deployment-strategyUse when choosing deployment strategy is required during operations work, especially when the result must be traceable…casioreview20-glitchchoosing-system-architectureUse when choosing system architecture is required during architecture work, especially when the result must be traceable…casioreview20-glitchchunking-strategyProvides chunking strategies for RAG systems. Generates chunk size recommendations (256-1024 tokens), overlap percentages…majiayu000writescitation-agentRetrieves verified citations from RAG DB only. Never invents citations. Returns citations with hashes.majiayu000citations-retrievalDocument citations and RAG (Retrieval-Augmented Generation) patterns for Claude. Activate for source attribution, document…majiayu000writescjk-aware-text-metricsCJK/Latin weighted token estimation for multilingual LLM pipelines. Use when processing Japanese/Chinese/Korean text with fixed…majiayu000clade-embeddings-searchImplement tool use (function calling) with Claude to let it execute actions, Use when working with embeddings-search patterns.…jeremylongshorewritesclade-multi-env-setupConfigure Claude across dev, staging, and production with different Use when working with multi-env-setup patterns. models, keys…jeremylongshorewritesclade-rate-limitsHandle Anthropic rate limits \u2014 understand tiers, implement backoff,\n\ Use when working with rate-limits patterns.\noptimize…jeremylongshorewritesclade-reliability-patternsBuild fault-tolerant Claude integrations \u2014 retries, circuit breakers,\n\ Use when working with reliability-patterns…jeremylongshorewritesclassification-helperQuick classifier training with automatic model selection, hyperparameter tuning, and comprehensive evaluation metrics.majiayu000classifier-agentClassifies legal domain, proceeding type, doc_type, court_type, draft_goal, language and style from MASTER_FACTS.json.majiayu000classifying-delivery-riskUse when classifying delivery risk is required during planning work, especially when the result must be traceable, independently…casioreview20-glitchclaude-advanced-tool-useAdvanced tool use patterns including tool search, programmatic calling, and production orchestration. Use when scaling to 10,000+…majiayu000claude-agent-sdkThis skill should be used when building applications with the Claude Agent SDK (Python). Use for creating orchestrators with…majiayu000claude-agent-sdk-pythonExpert guidance for building AI agents with the Claude Agent SDK in Python. Use when the user writes Python code with the SDK…majiayu000claude-agent-sdkAnthropic Claude Agent SDK for autonomous agents and multi-step workflows. Use for subagents, tool orchestration, MCP servers, or…majiayu000claude-agent-sdkBuild AI agents using the Claude Agent SDK. Covers query functions, ClaudeSDKClient, custom tools, MCP servers, hooks…majiayu000claude-agentsGuide for creating custom agents for Claude Code. Use when creating specialized agents, configuring agent tools.majiayu000claude-allow-stopReturn to normal stop behavior. Use PROACTIVELY after completing all tasks in continuous work mode, when work is committed and…majiayu000claude-allow-stopReturn to normal stop behavior. Use PROACTIVELY after completing all tasks in continuous work mode, when work is committed and…majiayu000writesclaudeA research-journal aesthetic printed on warm stone — authoritative, editorial, almost achromatic. Pages live on warm ivory…bergsideclaude-code-automationRun Claude Code programmatically in headless mode or via bidirectional stream-json protocol. Use when building agents, automating…majiayu000claude-code-expertEspecialista profundo em Claude Code - CLI da Anthropic. Maximiza produtividade com atalhos, hooks, MCPs, configuracoes…majiayu000claude-code-guideTo provide a comprehensive reference for configuring and using Claude Code (the agentic coding tool) to its full potential. This…majiayu000claude-code-tips自动从网络收集 Claude Code 的最新使用技巧、功能更新和最佳实践。当用户需要了解 Claude Code 的新功能、使用技巧、高级用法或 Claude Agent SDK 开发时使用此skill。支持本地缓存,避免重复搜索。majiayu000writesClaude Code X - Autonomous Execution SubagentExecute Claude Code autonomously in the background for well-defined tasks, enabling parallel execution of up to 5 concurrent…majiayu000writesclaude-do-not-stopEnable continuous work mode. Use PROACTIVELY when user says "keep working", "don't stop", "finish everything", "complete all…majiayu000claudeAnthropic Claude AI models for analysis and coding. Use for AI assistants.majiayu000claude-get-session-infoShared utility script for getting Claude PID and Session ID. Source this in other scripts to access CLAUDE_PID and SESSION_ID…majiayu000claude-gladiatorContinuous learning — hooks observe failures and prompt reflection, sibling synergy deepens analysis with history and tool…majiayu000claude-headless-modeGuide for using claude CLI in headless mode with --print, output formats, and JSON schemamajiayu000claude-improve-configSelf-reflect on the current session to identify mistakes and propose improvements to .claude configuration (CLAUDE.md, hooks…majiayu000claude-oratorPrompt rhetoric coach — deterministic scoring and restructuring using Anthropic best practicesmajiayu000claude-printRun a non-interactive Claude Code print-mode call from Codex. Use when the user asks to \"claude print\", \"ask claude\", \"run…majiayu000Claude SDK ExpertBuild autonomous AI agents using Claude Agent SDK with computer use, tool calling, MCP integration, and production best practices…majiayu000Claude SDK ExpertBuild autonomous AI agents using Claude Agent SDK with computer use, tool calling, MCP integration, and production best practicesmajiayu000Claude Tool Calling PatternsComprehensive guide for AI agents on proper Claude-style tool calling with correct syntax, patterns, and examplesmajiayu000claude-webAnthropic's Claude AI assistant via web interface.majiayu000claudekit-google-adk-pythonYou are an expert guide for Google's Agent Development Kit (ADK) Python - an open-source, code-first toolkit for building…majiayu000claudequantA股量化分析工具,提供实时行情、技术分析、资金流向和持仓分析。使用 AkShare 数据源(免费无需 Token)。当用户询问股票行情、A股分析、持仓查询、技术指标时触发此 skill。majiayu000claudismsClaude Code plugin enforcing operational guidelines, terse responses, sequential execution, and no destructive operations without…majiayu000cli-referenceClaude Code CLI commands, flags, headless mode, and automation patternsmajiayu000cloth-simulationCloth physics skill for softbody dynamics and constraint systems.a5c-aiwritescloud-neuralNeural network training and deployment in Flow Nexus cloud. Use for distributed ML training, model inference, and neural network…majiayu000cloudflare-agentsBuild AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Provides WebSockets, state persistence, scheduling, and…majiayu000cloudflare-agentsBuild AI agents on Cloudflare Workers with MCP integration, tool use, and LLM providers.majiayu000
← Prev24 / 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