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
2,0652,112 · page 44 / 104
polyclawBecome an autonomous prediction market trader on Polymarket with AI-powered analysis and a performance-backed token on Base.…majiayu000ponder-schema-specialistRead-only Ponder schema reference agent. Knows all tables, columns, types, indexes, and relations from ponder.schema.ts. Answers…majiayu000portfolio-manager-agentPortfolio allocation and rebalancing optimizer. Manages asset allocation across stocks/cash/bonds, performs periodic rebalancing…majiayu000post-processingPost-processing skill for bloom, DOF, motion blur, color grading, and TAA.a5c-aiwritespostmortemUse when documenting an incident, outage, or production failure using the structured DERP model (Detection, Escalation, Recovery…majiayu000postmortemBrutally honest incident postmortem. Reconstructs what happened from git, deploys, and logs — not from memory. Questions the…majiayu000potential-analysisThis skill group covers electrostatic potential analysis from first-principles calculations.majiayu000ppw:literatureSearch academic literature via Semantic Scholar MCP, select papers interactively, and generate verified BibTeX entries.…majiayu000prd-implementation-precheckUse this skill at Step 1 (PRD pre-check) and Step 2 (TDD alignment) of the v2 12-step SOP to find blockers and warnings in PRD /…charliehzmpreparing-mobile-store-releaseUse when preparing mobile store release is required during mobile product work, especially when the result must be traceable…casioreview20-glitchpreventing-duplicate-abstractionsUse when preventing duplicate abstractions is required during implementation work, especially when the result must be traceable…casioreview20-glitchpreventing-ecommerce-fraudUse when preventing ecommerce fraud is required during ecommerce product work, especially when the result must be traceable…casioreview20-glitchproactive-agentPatterns and workflows for proactive agent behavior.majiayu000probuilderUnity ProBuilder skill for level prototyping.a5c-aiwritesprocedural-animationProcedural animation skill for IK solvers and physics-driven animation.a5c-aiwritesprocedural-generationProcedural level generation skill for PCG algorithms.a5c-aiwritesproject-developmentThis skill covers the principles for identifying tasks suited to LLM processing, designing effective project architectures, and…majiayu000project-retrospectiveAnalyze a project's session history by dispatching parallel historian agents to read each export, then synthesizing their…majiayu000promptUse when optimizing prompts, skill descriptions, or agent instructions for clarity, specificity, and behavioral effectiveness.majiayu000prompt-architectComprehensive framework for analyzing, creating, and refining prompts for AI systems. Use when creating prompts for Claude…majiayu000prompt-cachingCaching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use…majiayu000prompt-cachingCaching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation)majiayu000prompt-cachingCaching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use…majiayu000prompt-compileCompile the YAML artifact into PROMPT.md with deterministic structure. A final agent pass polishes for fluidity, conciseness, and…majiayu000prompt-composerAutomated prompt generation from pattern library. Input asset specifications → output production-ready Gemini prompt with…majiayu000prompt-compressionToken-efficient prompt compression techniques for cost optimizationa5c-aiwritesprompt-compressorCompress verbose prompts & context before LLM processing. This skill should be used when input exceeds 1500 tokens, contains…majiayu000arcanea-prompt-craftMaster the Arcanean Prompt Language - advanced prompt engineering using mythological frameworks, constraint architecture, and the…majiayu000prompt-creationTechniques and templates for creating optimal prompts following Anthropic conventionsmajiayu000writesprompt-creationCreate standardized context prompts for AI assistants in prompts/ directory. Two types: technology-stack (project config with…majiayu000promptLoad and execute a prompt from the project's .claude/prompts/ directorymajiayu000prompt-engineer设计、优化和测试AI模型提示词,使用系统化的提示工程技术,包括少样本学习、思维链和结构化输出。majiayu000prompt-engineerUse when designing prompts for LLMs, optimizing model performance, building evaluation frameworks, or implementing advanced…majiayu000prompt-engineerUse when designing prompts for LLMs, optimizing model performance, building evaluation frameworks, or implementing advanced…majiayu000prompt-engineerTransforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE…majiayu000prompt-engineerTransforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE…majiayu000prompt-engineer-llmWorld-class expert in prompt engineering, LLM fine-tuning, RAG systems, and AI/ML workflows. Use when crafting prompts, designing…majiayu000prompt-engineerOptimize system prompts for Claude Code agents using proven prompt engineering patterns. Use when users request prompt…majiayu000prompt-engineerTransforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE…sickn33prompt-engineeringPrompt engineering knowledge base for designing prompts, evaluating them, reviewing AI-facing assets, and improving safety…majiayu000prompt-engineeringAdvanced prompt engineering techniques for optimal AI responses. Use this when crafting prompts, optimizing AI interactions, or…majiayu000writesPrompt Engineering SkillCraft effective prompts that get the best results from language models.majiayu000prompt-engineering通用提示词工程与提示词改写技能,用于设计、优化、评审、模板化与迭代 LLM 提示词;当任务涉及明确目标/约束/输出格式、角色与指令层级、few-shot 示例、结构化标签、链式分解、长上下文管理、评估与回归测试、跨模型迁移或提示词标准化时使用。majiayu000prompt-engineering-helperLLMプロンプトの最適化・テスト支援スキル。プロンプトのパフォーマンス評価、改善提案、A/Bテスト、ベストプラクティス適用、再現性検証を行います。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 in production. Use…majiayu000prompt-engineering-patternsMaster advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use…majiayu000prompt-engineering-patterns掌握高级提示工程技术,以最大化生产环境中LLM的性能、可靠性和可控性。在优化提示、改进LLM输出或设计生产提示模板时使用。majiayu000
← Prev44 / 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