GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
reflect
Compare meaning candidates from Wonder with the user's intended meaning, one pair at a time. In the Socrates loop, Reflect writes only the current cycle's ### Reflect section. Triggers (EN): reflect, compare meanings, surface meaning gap, check what I meant Do NOT use when: expanding meanings (-> wonder), merging meanings into shared meaning (-> refine), restating a goal (-> restate), or running the full Seed loop (-> socrates) vs wonder: Wonder expands candidates; Reflect checks where each candidate matches or diverges from the user's intention.
refine
Merge meaning gaps from Reflect into one user-approved shared meaning. In the Socrates loop, Refine writes only the current cycle's ### Refine section. Triggers (EN): refine, create shared meaning, merge meanings, consolidate intent Do NOT use when: expanding meanings (-> wonder), comparing meaning gaps (-> reflect), restating a goal (-> restate), or running the full Seed loop (-> socrates) vs reflect: Reflect exposes differences; Refine turns the accepted differences into one shared meaning.
referral-program
When the user wants to design, launch, or optimize a referral or affiliate program. Use when they mention 'referral program,' 'affiliate program,' 'word of mouth,' 'refer a friend,' 'incentive program,' 'customer referrals,' 'brand ambassador,' 'partner program,' 'referral link,' or 'growth through referrals.' Covers program mechanics, incentive design, and optimization — not just the idea of referrals but the actual system.
refactoring-specialist
Use when a task needs a low-risk structural refactor that preserves behavior while improving readability, modularity, or maintainability.
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
red-team
Use when planning or executing authorized red team engagements, attack path analysis, or offensive security simulations. Covers MITRE ATT&CK kill-chain planning, technique scoring, choke point identification, OPSEC risk assessment, and crown jewel targeting.
recall
Load context from vault memory. Temporal queries (yesterday, last week, session history) use native JSONL timeline. Topic queries use QMD BM25 search. "recall graph" generates interactive temporal graph of sessions and files. Every recall ends with "One Thing" - the single highest-leverage next action synthesized from results. Use when user says "recall", "what did we work on", "load context about", "remember when we", "prime context", "yesterday", "what was I doing", "last week", "session history", "recall graph", "session graph".
react-state-management
Master modern React state management with Redux Toolkit, Zustand, Jotai, and React Query. Use when setting up global state, managing server state, or choosing between state management solutions.
react-specialist
Use when a task needs a React-focused agent for component behavior, state flow, rendering bugs, or modern React patterns.
react-modernization
Upgrade React applications to latest versions, migrate from class components to hooks, and adopt concurrent features. Use when modernizing React codebases, migrating to React Hooks, or upgrading to latest React versions.
react:components
Converts Stitch designs into modular Vite and React components using system-level networking and AST-based validation.
ramp
Student semester onboarding — clinic procedures, tool walkthrough, practice exercises before real cases. Reads the handbook the professor uploaded at setup and teaches it interactively. Use when a new clinic student says "onboard me", "I'm new to the clinic", "getting started", or at the start of each semester; pass --card for the one-page reference.
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution
ralphinho-rfc-pipeline
RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.
ralph
Self-referential loop until task completion with configurable verification reviewer
ralph-init
Initialize a PRD (Product Requirements Document) for structured ralph-loop execution
rag-implementation
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
rag-architect
Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems.