Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 551 files from 1 750 authors, of which 61 898 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Expert knowledge for Microsoft Foundry Classic (aka Azure AI Foundry classic) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Foundry agents, RAG pipelines, OpenAI integrations, secure VNets/Private Link, or CI/CD deployments, and other Microsoft Foundry Classic related development tasks. Not for Microsoft Foundry (use microsoft-foundry), Microsoft Foundry Local (use microsoft-foundry-local), Microsoft Foundry Tools (use microsoft-foundry-tools).
Expert knowledge for Microsoft Foundry Local (aka Azure AI Foundry Local) development including best practices, configuration, and integrations & coding patterns. Use when compiling HF models with Olive, using Foundry Local CLI, chat/embeddings APIs, transcription, or tool calling, and other Microsoft Foundry Local related development tasks. Not for Microsoft Foundry (use microsoft-foundry), Microsoft Foundry Classic (use microsoft-foundry-classic), Microsoft Foundry Tools (use microsoft-foundry-tools), Azure Local (use azure-local).
Expert knowledge for Microsoft Foundry Tools (aka Azure AI services, Azure Cognitive Services) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. Use when using Content Moderator, Content Safety, Content Understanding analyzers, REST/.NET APIs, or document extraction workloads, and other Microsoft Foundry Tools related development tasks. Not for Microsoft Foundry (use microsoft-foundry), Microsoft Foundry Classic (use microsoft-foundry-classic), Microsoft Foundry Local (use microsoft-foundry-local).
Expert knowledge for Microsoft Foundry (aka Azure AI Foundry) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Foundry agents with IQ retrieval, Azure OpenAI models, MCP tools, VNet/private access, or Teams apps, and other Microsoft Foundry related development tasks. Not for Microsoft Foundry Classic (use microsoft-foundry-classic), Microsoft Foundry Local (use microsoft-foundry-local), Microsoft Foundry Tools (use microsoft-foundry-tools).
>- Delegate a coding task to the Google Antigravity CLI (`agy`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Antigravity or agy - phrasings like "have Antigravity do X", "delegate this to agy", "run it through agy", or "use Antigravity to implement/fix/refactor" - or wants to run a queue of coding tasks through agy while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
>- Delegate a coding task to a separate Claude Code CLI process or another Claude session as an implementer, then review its diff and land it yourself. Use only when the user explicitly asks to delegate implementation to Claude Code, another Claude session, or the `claude` CLI — for example, "have another Claude implement this", "delegate this to Claude Code", or "run this queue through a separate Claude session." Do not trigger merely because the current orchestrator is Claude, and do not use when the user asks the current Claude to implement directly without delegation.
>- Delegate a coding task to the OpenAI Codex CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Codex — phrasings like "have Codex do X", "delegate this to Codex", "run it through Codex", or "use Codex to implement/fix/refactor" — or to run a queue of coding tasks through Codex while staying the reviewer. Prefer it over a one-shot Codex forwarder (such as the codex-rescue agent) when the user will review the diff and commit it themselves. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
>- Delegate a coding task to the Cursor Agent CLI (`cursor-agent`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Cursor — phrasings like "have Cursor implement X", "delegate this to Cursor", "run it through Cursor Agent", or "use Cursor to implement/fix/refactor" — or wants to run a queue of coding tasks through Cursor while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
>- Delegate a coding task to the Grok Build CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Grok — phrasings like "have Grok do X", "delegate this to Grok", "run it through Grok", "use Grok Build to implement/fix/refactor", or "have grok CLI do this" — or to run a queue of coding tasks through Grok while staying the reviewer. Prefer it when the user will review the diff and commit it themselves. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
>- Delegate a coding task to the Kimi Code CLI (`kimi`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Kimi - phrasings like "have Kimi implement X", "delegate this to Kimi", "run it through Kimi Code", or "use Kimi to implement/fix/refactor" - or wants to run a queue of coding tasks through Kimi while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
>- Delegate a coding task to the OpenCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to OpenCode — phrasings like "have OpenCode do X", "delegate this to OpenCode", "run it through OpenCode", or "use OpenCode to implement/fix/refactor" — or wants to run a queue of coding tasks through OpenCode while staying the reviewer. Prefer it when the user will review the diff and commit it themselves. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
>- Delegate a coding task to the Pi coding agent CLI (`pi`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Pi - phrasings like "have Pi implement X", "delegate this to pi", "run it through Pi", or "use pi to implement/fix/refactor" - or wants to run a queue of coding tasks through Pi while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
>- Delegate a coding task to the Qoder CLI (`qodercli`) as a background implementer, then review its diff and land it yourself. Use this whenever the user asks to have Qoder implement, fix, refactor, or run a queue of coding tasks while the orchestrator remains the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants code written directly without delegation.
>- Delegate a coding task to the Mistral Vibe CLI (`vibe`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Vibe — phrasings like "have Vibe implement X", "delegate this to Vibe", "run it through Mistral Vibe", "use vibe to implement/fix/refactor" — or wants to run a queue of coding tasks through Vibe while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
> AI hotspot monitoring and trending topic discovery across multiple sources (Bing, Google, DuckDuckGo, HackerNews, monitoring keywords, tech/AI news discovery, generating hotspot reports, "最近有什么热点", "帮我关注XX动态", "查一下XX最新消息", "生成热点报告", "monitor XX", "what's trending in XX", or any request to search/track/discover current events and trending content across Chinese and international platforms.
>- Draft, audit, or minimally revise English- or Chinese-language academic prose to reduce formulaic, vacuous, mechanically repetitive, or process-leaking language while preserving claims, evidence strength, logical relations, manuscript-wide terminology identity, document-level pattern variation, and scholarly register. Use for papers, abstracts, grants, cover letters, and reviewer responses when the user asks to de-AI, humanize, audit AI-like phrasing, or rewrite text without changing meaning. English is primary; Chinese is supported. Not for detector evasion, policy circumvention, pure translation, non-academic copy, or adding facts, citations, examples, or author experiences that the source does not contain.
Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan. Use when the user asks to make a new skill from real run history, extract a reusable workflow from conversation/logs/files, summarize lessons into a new skill, or produce a plan before writing files. Do not use to upgrade an existing skill or to execute the business workflow itself.
Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill. Use when the user asks to improve an existing skill from recent runs, recurring failures, outdated sources, excessive bloat, changed platform behavior, or validated workflow feedback. Do not use to create a brand-new skill or to execute the business workflow itself.
Create a concise continuation prompt that a fresh agent session can paste in to resume a long or degraded session. Use when the user asks for a handoff prompt, restart prompt, continuation prompt, context transfer, fresh-session resume, or a compact summary for opening a new session. Do not use for ordinary summaries, task-forest maintenance, durable user-profile updates, automatic session creation, code execution, or external publishing.
>- reference to $task-clarifier, or trigger phrases "帮我理清需求" / "需求澄清" / "clarify" / "clarify my needs" / "help me clarify". Once activated, keeps needs, the AI fully understands the user's needs, and the user confirms the AI's understanding is correct. Does not auto-activate; does not intervene in task execution unless explicitly invoked.
Maintains a repo-local task forest or task DAG for the current workspace. Use when the user asks to initialize, update, close a session, summarize evolving project tasks, decide whether a new request is a global task or subtask, track task progress/history/deviations/todos, export a task graph HTML, or provide task data for gap-router/local-agent-control-room. Do not use for executing the tasks themselves.
Local user-profile maintenance skill for Codex, Claude Code, OpenClaw, OpenCode, and other agent harnesses. Use only when the user explicitly invokes this skill or asks to create, initialize, update, query, correct, delete, export, or audit a local persistent user profile. Also use to extract durable collaboration preferences, requirement-expression habits, capability boundaries, recurring omissions, risk preferences, privacy boundaries, and typical events from the current session into auditable, confirmable, retractable local profile data. Do not auto-invoke, upload profile data, or replace task-clarifier's normal clarification flow.
Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.
Language-agnostic coding principles for maintainability, readability, and quality. Use when implementing features, refactoring code, or reviewing code quality.
Documentation creation criteria including PRD, ADR, Design Doc, and Work Plan requirements with templates. Use when creating or reviewing technical documents, or determining which documents are required.
Captures and persists access methods for resources outside the repository (design source, design system, API schema, IaC source, secret store) so downstream work can reach them deterministically. Use when work depends on external resources, or when the user mentions design source, design system, API schema, IaC source, secret store, or canonical source.
Applies React/TypeScript-specific technical decision criteria, anti-pattern detection, debugging, and frontend quality gates. Use when reviewing components, hooks, browser behavior, or frontend implementation completeness.
Implementation strategy selection framework. Use when planning implementation strategy, selecting development approach, or defining verification criteria.
Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria. Use when designing integration tests, E2E tests, or reviewing test quality.
Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.
Separates the outcome a change must produce from the requirements proposed to reach it, records what the user excluded, and bands cost from structure. Use when a requirement enters a workflow, before design begins.
Implements React/TypeScript unit, integration, and browser E2E tests with the repository's configured runner, mocks, setup, and browser harness. Use when creating or completing frontend tests and generated test skeletons.
Language-agnostic testing principles including TDD, test quality, coverage standards, and test design patterns. Use when writing tests, designing test strategies, or reviewing test quality.
React/TypeScript frontend development rules including type safety, component design, state management, and error handling. Use when implementing React components, TypeScript code, or frontend features.
Investigate problem, verify findings, and derive solutions
Adjust an already-implemented UI in-session with verification against the design source
Execute materialized frontend task files in autonomous execution mode
Execute from codebase analysis to frontend design document creation
Create frontend work plan from design document and obtain plan approval
Design Doc compliance and security validation with optional auto-fixes
Execute tasks following appropriate rules with rule-advisor metacognition
Update existing design documents (Design Doc / PRD / ADR) with review
Guides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode.
Performs metacognitive task analysis and skill selection. Use when determining task complexity, selecting appropriate skills, or estimating work scale.
Add integration/E2E tests to existing codebase using Design Docs
Execute materialized task files in autonomous execution mode
Execute from codebase analysis to design document creation
Execute materialized fullstack task files with layer-aware agent routing
Orchestrate full-cycle implementation across backend and frontend layers
Orchestrate the complete implementation lifecycle from requirements to deployment
Create work plan from design document and obtain plan approval
Verifies the work plan is implementable end-to-end and resolves verification-lane / fixture / E2E-environment gaps before the build phase begins. Use when "implement-ready/verification readiness/lane setup/E2E environment missing" is mentioned, or before any build phase begins on a work plan whose readiness has not been preflight-checked.
Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow
Design Doc compliance and security validation with optional auto-fixes
Execute tasks following appropriate rules with rule-advisor metacognition
Add integration/E2E tests to existing codebase using Design Docs
Execute materialized task files in autonomous execution mode
Execute from codebase analysis to design document creation
Orchestrate the complete implementation lifecycle from requirements to deployment
Create work plan from design document and obtain plan approval
Claude Skills — questions
Answers built from the skills we actually parsed.