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
2,1132,160 · page 45 / 104
prompt-engineering-patternsMaster advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.majiayu000prompt-engineering-patternsMaster advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use…majiayu000prompt-engineering-patternsMaster advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.majiayu000prompt-engineering-patternsMaster advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use…majiayu000prompt-engineering-suiteComprehensive prompt engineering with Chain-of-Thought, few-shot learning, prompt versioning, and optimization. Use when…majiayu000prompt-engineeringMaster advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use…majiayu000prompt-enhancerEnhance user prompts by analyzing project context (code structure, dependencies, conventions, existing patterns). Use when users…majiayu000Prompt EnhancerTransform vague prompts into actionable specs using intelligent analysis and session memory. Use when user input contains -e or…majiayu000prompt-enricherPhase 0.2 — Enriches the raw user prompt with discovered constraints, ambiguities, likely edge cases, and suggested scope…majiayu000prompt-execExecute the forged prompt exactly as written. Requires explicit consent and a ready artifact. Deletes artifact after successful…majiayu000prompt-forgeShape, refine, and stabilize human intent into a canonical prompt artifact. Iteratively clarifies ambiguity until user confirms…majiayu000prompt-generation-rulesYou are a coding standards expert specializing in prompt generation rules.majiayu000prompt-improverTransform vague prompts into rich, structured prompts with automatic fallbackmajiayu000prompt-improverThis skill enriches vague prompts with targeted research and clarification before execution. Should be used when a prompt is…majiayu000prompt-injection-detectorPrompt injection detection and prevention for secure LLM applicationsa5c-aiwritesprompt-iterationUse when iteratively improving agent prompts through automated LLM-as-Judge evaluation. Runs eval→fix→commit loop with circuit…majiayu000promptUse when the user asks to create, refine, evaluate, or optimize an LLM prompt. Do NOT trigger for Claude Code skills (use…majiayu000promptOrchestrator skill for the `prompt` skillset. Dispatches to member skills in a safe, predictable order. Separates intent…majiayu000prompt-libraryLibrary of 18+ ready-to-use prompt templates and executable agentsmajiayu000Prompt Library Minimalคลัง prompts แบบ minimal ที่ใช้ token น้อยที่สุดแต่ได้ผลลัพธ์ดี พร้อม templates และ best practicesmajiayu000prompt-libraryA comprehensive collection of battle-tested prompts inspired by…majiayu000prompt-lookupActivates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use…majiayu000prompt-managementCentralized prompt management for LLM operations. All prompts in lib/prompts/ as named exports. Multi-level extraction, system…majiayu000Prompt MasteryAdvanced LLM prompt engineering expertise for crafting highly effective prompts, system messages, and tool descriptions with…majiayu000prompt-optimization-claude-45Optimize CLAUDE.md files and Skills for Claude Code CLI. Use when reviewing, creating, or improving system prompts, CLAUDE.md…majiayu000prompt-optimizationAnalyze and improve existing prompts for better performancemajiayu000writesprompt-optimizerUse when a draft prompt, instruction set, or agent skill description needs refinement, clarity, or improved performance.majiayu000prompt-templates-datadrivenconstructi-ddc-skills-for-ai-agReusable prompt templates for construction AI tasks: cost estimation, schedule analysis, document processing, BIM queries.…majiayu000prompt-testingA/B testing and performance metrics for promptsmajiayu000writesprompt-versioning-managementプロンプトのライフサイクル管理を専門とするスキル。バージョン管理、デプロイ戦略、ロールバック、変更追跡により、本番環境で安全かつ効率的なプロンプト運用を実現します。 Anchors: • The Pragmatic Programmer (Andrew…majiayu000writespromptcraftUse when user asks to "create a skill", "make a command", "generate a prompt", "write a slash command", "build a Claude…majiayu000prompting-leitfadenPrompting-Leitfaden für juristische KI-Nutzung in Kanzleien: Anwendungsfall Anwalt oder Mitarbeitende wollen KI effektiver nutzen…majiayu000Prompton Code InterpreterSimulate the execution of Prompton, a Python-like language where `prompt'...'` expressions evaluate to the result of the query…majiayu000protein-phylogenyProtein (gene) phylogeny inference pipeline: generates a .qmd analysis script that performs alignment, optional trimming, and…majiayu000Network Protocol Analysis SkillNetwork protocol capture, analysis, and fuzzing capabilitiesa5c-aiwritesprototyping-critical-flowsUse when prototyping critical flows is required during ux work, especially when the result must be traceable, independently…casioreview20-glitchprove-plus-commGuide for completing Coq proofs involving arithmetic properties like addition commutativity. This skill should be used when…majiayu000prove-plus-commGuidance for proving mathematical properties in Coq using induction, specifically addition commutativity and similar arithmetic…majiayu000providersUse when switching between LLM providers, accessing provider-specific features (Anthropic caching, OpenAI logprobs), or using raw…majiayu000proxy-mode-referenceReference guide for using PROXY_MODE with external AI models. Use when running multi-model reviews, understanding which agents…majiayu000openclaw-world-agentOperate an AI agent inside OpenClaw World over HTTP IPC. Use when tasks involve registering or reconnecting an agent, moving…majiayu000push-notificationsMulti-platform push notification skill for implementing APNs (iOS), FCM (Android), and cross-platform notification systems with…a5c-aiwritesPwntools Exploitation SkillExploit development automation using pwntools frameworka5c-aiwritesPydantic AI Agent BuilderExpert guidance for building AI agents with Pydantic AI framework. Use when creating multi-agent systems, AI orchestration…majiayu000writespydantic-ai-agent-creationCreate PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents…majiayu000pydantic-ai-agent-creationCreate PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents…majiayu000pydantic-aiBuild production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model…majiayu000pydantic-ai-tool-systemRegister and implement PydanticAI tools with proper context handling, type annotations, and docstrings. Use when adding tool…majiayu000
← Prev45 / 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