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 29,140 codex 4,755 cursor 3,111 copilot 976 windsurf 55 cline 34

CategoryWorkflow & Productivity 4,979 AI & Agents 3,037 Data & Analytics 2,345 Code Review & Quality 1,376 Backend & API 1,244 Security 1,194 Design & Presentation 1,154 Documentation 965 Content & Marketing 916 Testing & QA 777 DevOps & Cloud 576 Databases 550 Frontend 469 Business & Finance 328 Media & Video 257 Other 9,833

4,965 found

1,729–1,776 · page 37 / 104

llm-campaign-drift-gateGate resumption of any multi-day LLM batch-scoring campaign that calls an unpinned model alias (deepseek-chat, gpt-*-latest…kennethkhoocy

llm-classifierLLM-based zero-shot and few-shot classification for flexible intent detectiona5c-aiwrites

llm-classifierLLM-based zero-shot and few-shot classification for flexible intent detectionmajiayu000writes

LLM and AI Cost OptimizationStrategies for managing and reducing costs in LLM-powered applications, from token economics to RAG architectures.majiayu000

llm-engineeringPatterns for building LLM applications - prompt engineering, RAG pipelines, cost optimization, multi-model routing, and…majiayu000

llm-evaluationLLM testing and evaluation tools including promptfoo, trulens, and evals frameworksmajiayu000

llm-evaluationMaster comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.majiayu000

llm-gateway-routingLLM gateway and routing configuration using OpenRouter and LiteLLM. Invoke when: - Setting up multi-model access (OpenRouter…majiayu000

llm-gold-bound-failure-checkDiagnose whether an LLM classifier's validation-gate failure is GOLD-BOUND before spending on prompt revision or model changes.…kennethkhoocy

llm-guardrailsComprehensive guide for LLM safety and guardrails implementation.majiayu000

llm-integrationGuide for using LLM utilities in speedy_utils, including memoized OpenAI clients and chat format transformations.majiayu000

Llm Local DeploymentComprehensive guide for deploying LLMs locally using Ollama, vLLM, and llama.cpp. Local deployment offers privacy, cost control…majiayu000

llmMulti-provider LLM integration. Unified interface for OpenAI, Anthropic, Google, and local models.majiayu000

llm-opsLocal LLM health checks and cache management. Probe Ollama/vLLM/SGLang endpoints, clean model caches.majiayu000writes

llm-opsLLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade…majiayu000

llm-patternsAI-first application patterns, LLM testing, prompt managementmajiayu000

llm-pipelinePydantic-AI agents, RAG, embeddings for Pulse Radar knowledge extraction.majiayu000

llm-routerThis skill should be used when users want to route LLM requests to different AI providers (OpenAI, Grok/xAI, Groq, DeepSeek…majiayu000

llm-structured-outputGet reliable JSON, enums, and typed objects from LLMs using response_format, tool_use, and schema-constrained decoding across…majiayu000

Llm Txt ProtocolLLM Text Protocol provides standardized patterns for text-based interactions with language models. It encompasses prompt…majiayu000

ln-001-standards-researcherResearch standards/patterns via MCP Ref. Generates Standards Research for Story Technical Notes subsection. Reusable worker.majiayu000

ln-014-agent-instructions-auditorAudits CLAUDE.md, AGENTS.md, GEMINI.md for token budget, prompt cache safety, compact instructions, and cross-agent consistency.…majiayu000

ln-014-agent-instructions-managerCreates AGENTS.md canonical and CLAUDE.md @AGENTS.md stub; audits token budget, cache safety, import-pattern compliance. Use when…majiayu000

ln-014-agent-instructions-managerCreates missing instruction files (CLAUDE.md, AGENTS.md, GEMINI.md) and audits all for token budget, prompt cache safety, and…majiayu000

lobby-systemLobby management skill for party systems and session handling.a5c-aiwrites

local-llm-fine-tuningGuides users through the process of preparing datasets and fine-tuning local Large Language Models (LLMs) using techniques like…majiayu000

local-rag-searchLocal Retrieval-Augmented Generation with vector search.majiayu000

localizationGame localization skill for text tables and cultural adaptation.a5c-aiwrites

localsetup-communication-and-toolsCommunication and response guidelines, tool selection and enhancement, periodic context updates. Use for user communication…majiayu000

locomo-benchmarkRun LoCoMo benchmark for long-term conversational memorymajiayu000

lodLevel of Detail skill for mesh simplification and HLOD generation.a5c-aiwrites

logit-lensDecode intermediate layer predictions using the Logit Lens technique. Use when analyzing what a model predicts at each layer…majiayu000

long-document-llm-pipelineUse when processing documents over 50K characters through LLM APIs with section splitting and batch cost reduction.majiayu000

longbridge-catalyst-radar自选股跟踪扫描雷达。为用户监控自选股，定时生成晨晚报。基于 Longbridge 开放平台，监控用户自选股列表，扫描财报超预期、政策变化、异常资金流、内部人交易、分析师评级变动等7维催化剂信号，按市场分组生成盘前/盘后增量简报。支持美股、A股、港股、新加坡四个…majiayu000

longbridge-earnings-previewPre-earnings analysis skill — extracts prior guidance, tracks events, summarises earnings call Q&A, and generates a structured…majiayu000

longbridge-execution-modelTrade execution modelling framework (backtesting analysis only) via Longbridge — covers slippage models (linear / square-root…majiayu000

longbridge-hkipo-analysisHK IPO 打新分析 — 港股新股是否值得申购的"四维评估"诊断（定价合理性 / 发行质量 / 市场时机 / 基本面展望）。输出推荐 / 中性 / 回避三档评级 + 招股书精华 + 风险提示 +…majiayu000

longbridge-ml-strategyMachine-learning prediction strategy framework via Longbridge Securities — walk-forward rolling training with feature engineering…majiayu000

lora-trainer-guideUse when helping users configure LoRA training — select presets, understand parameters, and pick the right settings for their…majiayu000

lottie-animationsLottie animation skill for integrating After Effects animations into iOS, Android, and cross-platform mobile apps with playback…a5c-aiwrites

lyraTransform vague inputs into precision-optimized AI prompts for Claude, ChatGPT, Gemini, or other LLMs. Use when user mentions…majiayu000

macro-systemsExpert skill for designing and implementing macro systems including hygienic macros, procedural macros, and macro expansion.…a5c-aiwrites

managed-agentRun an Anthropic Claude Managed Agent — a cloud agent harness (container + filesystem + tools), the cloud counterpart of the…majiayu000writes

managing-artifact-lineageUse when managing artifact lineage is required during kernel work, especially when the result must be traceable, independently…casioreview20-glitch

managing-change-impactUse when managing change impact is required during planning work, especially when the result must be traceable, independently…casioreview20-glitch

managing-ecommerce-inventoryUse when managing ecommerce inventory is required during ecommerce product work, especially when the result must be traceable…casioreview20-glitch

← Prev37 / 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

Collections, ranked →

Which skill collections are moving this week, from our own snapshots.

Open Source Radar →

The repositories behind these skills, watched daily.

The makers →

Who publishes the skills you install.

Startup rankings →

The companies building in the same ecosystem.