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
1,2491,296 · page 27 / 104
CREATE_DEEP_RESEARCH_PROMPTGenerate a structured deep research prompt. USE WHEN the user needs to research a complex topic, market, or bug deeply.…majiayu000create-motion-graphicsUse whenever the agent needs to add, create, hand-author, patch, or place Motion Graphic JSX assets in a OpenChatCut project.…0xslinecreate-promptExpert prompt engineering for Claude, GPT, and LLMs. ALWAYS use when the user says "write a prompt", "create a prompt", "optimize…majiayu000create-subagentGuide for creating specialized Claude Code subagents with proper YAML frontmatter, focused descriptions, system prompts, and tool…majiayu000create-tia-agentGuides users through creating a new TIA XMPP agent based on mistral-minimal. Use when the user wants to create, build, set up, or…majiayu000writescreate-workerUse when creating custom agents for Claude Code, configuring specialized AI assistants, or when the user asks about agent…majiayu000creating-claude-agentsUse when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definition, tool…majiayu000creator-intelligenceTransform Claude Code into your personal Jarvis - an AI operating system that knows your projects, preferences, and workflows…majiayu000crewai-setupCrewAI multi-agent orchestration setup for collaborative AI systemsa5c-aiwritescross-validation-setupCross Validation Setup - Auto-activating skill for ML Training. Triggers on: cross validation setup, cross validation setup Part…majiayu000writescrypto-bd-agentProduction-tested patterns for building AI agents that autonomously discover, > evaluate, and acquire token listings for…majiayu000cs-mlML: supervised/unsupervised/RL, CNN/RNN/Transformer, training, evaluation, MLOps, LLM fine-tuningmajiayu000cuda-debuggingExpert skill for GPU debugging using CUDA-GDB and NVIDIA Compute Sanitizer. Detect memory errors, race conditions, uninitialized…a5c-aiwritescurating-library-kgGuide users through curating the library knowledge index — reviewing block categories, marking common/important blocks, and…matlabcuriosity-drivenSchmidhuber's curiosity-driven learning: Intrinsic motivation via compression progress. Seek states that improve world model.majiayu000cursor-agentA comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes…majiayu000cursor-agentSpecialized agent for Cursor IDE integration and workflows.majiayu000cursor-subagent-creatorCreates Cursor-specific AI subagents with isolated context for complex multi-step workflows. Use when creating subagents for…majiayu000daa-agentCreate and adapt Dynamic Agentic Architecture agents that learn and evolvemajiayu000writesdamage-controlRecovers broken agent state via crash recovery, context overflow, and merge conflict protocols. Use when an agent session fails…majiayu000dba-architectDBA Architect Agent. 스키마 설계, 정규화, 데이터 모델링을 담당합니다.majiayu000writesdba-tunerDBA Tuner Agent. 쿼리 최적화, 인덱스 설계, 슬로우 쿼리 분석을 담당합니다.majiayu000writesdebateStructured multi-perspective deliberation through adversarial dialoguemajiayu000Debugger Integration SkillAdvanced debugging integration for vulnerability researcha5c-aiwritesdebugging-agentSelf-Improving Agent that monitors all other agent skills, analyzes their logs, detects issues, and proposes improvements.…majiayu000decay-scoringSistema de scoring temporal para nodes de conhecimento do corpus RAG. Calcula scores de obsolescencia baseado em idade, validacao…majiayu000writesdeciding-release-scopeUse when deciding release scope is required during planning work, especially when the result must be traceable, independently…casioreview20-glitchdecision-framework-invokerTriggers for automatically invoking the decision-framework skill before irreversible or high-blast-radius operations. Use as a…majiayu000decisive-agentEnforces decisive decision-making. Search best practices, decide on ONE option, provide reasoning. NEVER ask user to choose.majiayu000decisive-agentEnforces decisive decision-making by searching best practices, choosing ONE option, and providing reasoning. Use when making…majiayu000decomposing-bounded-contextsUse when decomposing bounded contexts is required during architecture work, especially when the result must be traceable…casioreview20-glitchdeep-agents-coreINVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format…majiayu000deep-agents-memoryINVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral)…majiayu000Deep AnalysisAdvanced problem-solving skill using sequential thinking. Use for complex architectural decisions, debugging hard problems, or…majiayu000deep-linkingUniversal links and deep linking skill for implementing iOS Universal Links, Android App Links, custom URL schemes, and deferred…a5c-aiwritesdeep-reasoning-agentThree-stage Chain of Thought (CoT) analyzer for /deep-reasoning page. Performs comprehensive analysis in 3 stages Direct Impact →…majiayu000deep-researchOrchestrates two-round parallel agent research with Exa orientation, breadth-first discovery, and depth-focused synthesis. Use…majiayu000deep-research深度调研的多实例(多 Agent)编排工作流:把一个调研目标拆成可并行子目标,用 Codex CLI(`codex exec`)在默认 `workspace-write` 沙箱内运行子进程;联网与采集优先使用已安装的 skills,其次使用 MCP…majiayu000deep-research深度调研的多Agent编排工作流:把一个调研目标拆成可并行子目标,用 Claude Code 非交互模式(`claude -p`)运行子进程;联网与采集优先使用已安装的 skills,其次使用 MCP…majiayu000writesdeep-researchDeep research via Gemini CLI OR free search APIs — runs in background sub-agent to save Claude tokens.majiayu000writesdeep-researchOrchestrated multi-source research with parallel agent fan-out. Use for thorough investigation of complex topics requiring…majiayu000writesdeep-researchOrchestrate multi-phase deep research with web search, memory retrieval, pattern matching, and synthesis into structured findingsmajiayu000deep-research-teamThis skill should be used when the user asks for "deep research", "research team", "comprehensive analysis", "research report"…majiayu000deep-researcherPerforms comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple…majiayu000deepagents-cliDeep Agents CLI reference and usage guide. Use when the user wants to: (1) Launch or configure the deepagents terminal coding…majiayu000deepagents-cliDeep Agents CLI reference and usage guide. Use when the user wants to: (1) Launch or configure the deepagents terminal coding…majiayu000deepagents-cliDeep Agents CLI reference and usage guide. Use when the user wants to: (1) Launch or configure the deepagents terminal coding…majiayu000deepagents-cliDeep Agents CLI — the LangGraph-based terminal coding agent. Use this skill whenever the user mentions deepagents, deep agents…majiayu000
← Prev27 / 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