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
1,5371,584 · page 33 / 104
google-gemini-file-searchGoogle Gemini File Search for managed RAG with 100+ file formats. Use for document Q&A, knowledge bases, or encountering…majiayu000google-scholarThis skill should be used when the user asks to "search Google Scholar", "find academic papers", "scholar search", "lookup…majiayu000gptme-wrappedAnalyze your gptme conversation history for insights like token usage, costs, model preferences, and usage patterns - inspired by…majiayu000writesgpu-memory-analysisSpecialized skill for GPU memory hierarchy analysis and optimization. Analyze memory access patterns, detect bank conflicts…a5c-aiwritesgpu-resource-optimizerOptimize gpu resource optimizer operations. Auto-activating skill for ML Deployment. Triggers on: gpu resource optimizer, gpu…majiayu000writesgradient-clipping-helperConfigure with gradient clipping helper operations. Auto-activating skill for ML Training. Triggers on: gradient clipping helper…majiayu000writesgradient-clipping-helperGradient Clipping Helper - Auto-activating skill for ML Training. Triggers on: gradient clipping helper, gradient clipping helper…majiayu000writesgraphrag-patternsGraphRAG implementation patterns for hybrid search, Text2Cypher, and agentic retrieval. Use when implementing RAG workflows with…majiayu000writesGrasp Planning SkillGrasp planning and execution for robotic manipulation tasksa5c-aiwritesgrowth-experimentExperimentation Agent. A/B 테스트 설계, 가설 검증, 통계 분석을 담당합니다.majiayu000writesgrowth-model-analyzer增长模型分析技能 - 提供全面的增长黑客分析工具,包括裂变策略评估、用户细分、Uplift建模、ROI优化等。支持多种增长场景的机器学习建模和智能决策建议。适用于用户增长、营销优化、产品迭代等增长分析场景。majiayu000writesgrpc-protocolExpert skill for gRPC protocol implementation, debugging, and performance optimizationa5c-aiwritesgsd-toolsCentral utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates…a5c-aiwritesguardrails-ai-setupGuardrails AI validation framework setup for LLM applications. Implement input/output validation, safety checks, and structured…a5c-aiwritesgupp-propulsionInterrupt controller converting polled to proactive agent execution. Per-runtime strategies, configurable thresholds, Deacon…majiayu000gupp-propulsionInterrupt controller converting polled to proactive agent execution. Per-runtime strategies, configurable thresholds, Deacon…majiayu000handling-uncertaintyUse when handling uncertainty is required during kernel work, especially when the result must be traceable, independently…casioreview20-glitchview-resultsView and analyze Hawk evaluation results. Use when the user wants to see eval-set results, check evaluation status, list samples…majiayu000view-resultsView and analyze Hawk evaluation results. Use when the user wants to see eval-set results, check evaluation status, list samples…majiayu000headless-cli-agentsBuild agentic systems using Claude CLI in headless mode or the Claude Agent SDK. Use when building automation pipelines, CI/CD…majiayu000headless-cli-agentsThis skill provides comprehensive guidance for running AI coding agents in non-interactive (headless) mode for automation, CI/CD…majiayu000headless-modeGuide for using Claude Code programmatically via CLI flags and SDKs. Use for automation, CI/CD pipelines, scripting, and building…majiayu000writesHeadless RunnerRun Claude Code in headless/programmatic mode for automation, CI/CD, and agent workflows. Use when user asks about headless mode…majiayu000hello-worldA simple skill that should be used to respond to a user when the enter the phrase "hello world".majiayu000helpShow help for claude-talk voice chat commands.majiayu000hierarchyDisplay PAI agent hierarchy and command structuremajiayu000highlight-scannerCombined analysis skill to find viral-worthy highlights from videos. Scans transcripts, detects laughter, analyzes…majiayu000hintsALWAYS apply these hints automatically in your responses. No need to invoke this skill - just follow its rules when your response…majiayu000bio-read-alignment-hisat2-alignmentAlign RNA-seq reads with HISAT2, a memory-efficient splice-aware aligner. Use when STAR's memory requirements are too high or for…majiayu000hive-createStep-by-step guide for building goal-driven agents. Qualifies use cases first (the good, bad, and ugly), then creates package…majiayu000hive-createStep-by-step guide for building goal-driven agents. Qualifies use cases first (the good, bad, and ugly), then creates package…majiayu000hive-credentialsSet up and install credentials for an agent. Detects missing credentials from agent config, collects them from the user, and…majiayu000hive-debuggerInteractive debugging companion for Hive agents - identifies runtime issues and proposes solutionsmajiayu000hls-cpp-to-rtlExpert skill for C/C++ to RTL conversion using High-Level Synthesis toolsa5c-aiwriteshlslHLSL shader programming skill for DirectX, compute shaders, and optimization.a5c-aiwriteshook-creatorThis skill should be used when the user asks to "create a hook", "write hook config", "add hooks.json", "configure event hooks"…majiayu000hook-creator创建和配置 Claude Code 钩子以自定义代理行为。当用户需要以下操作时使用:(1) 创建新钩子,(2) 配置自动格式化、日志记录或通知,(3) 添加文件保护或自定义权限,(4) 设置工具执行前后的操作,(5) 询问钩子事件如…majiayu000houdiniHoudini Engine skill for procedural assets and HDA deployment.a5c-aiwriteshugging-face-model-trainerTrain or fine-tune TRL language models on Hugging Face Jobs, including SFT, DPO, GRPO, and GGUF export.majiayu000huggingface-classifierHugging Face transformer model fine-tuning and inference for intent classificationa5c-aiwritesHuggingFace Model TrainerTrain and fine-tune LLMs using HuggingFace TRL, Transformers, and cloud GPU infrastructure with SFT, DPO, GRPO methodsmajiayu000huggingface-transformersUse Hugging Face Transformers for local model inference, embeddings, and fine-tuning. Covers pipelines, model selection…majiayu000human-extractorGPU-accelerated pipeline for detecting, tracking, and classifying humans in dashcam footage. This skill should be used when users…majiayu000hybrid-search-implementationCombine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when…majiayu000hybrid-search-implementationCombine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when…majiayu000hybrid-search-implementationCombine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when…majiayu000hybrid-search-implementationCombine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when…sickn33hybrid-search-implementationCombine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when…wshobson
← Prev33 / 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