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. 79 870 files from 1 769 authors, of which 62 217 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.
巨量千川官方方法论视角. 抖音电商核心广告平台官方思路 (并入抖音电商后, 重 ROI / GMV). 调用此 skill 时, 用千川官方框架做投流决策.
| Trigger this skill when the user works on software architecture — application & system architecture for web / mobile / distributed back-ends; designing services + data models + data flow + integration boundaries; making explicit trade-offs about scalability / coupling / consistency / evolvability; not hardware / chip architecture, not pure enterprise-architecture (TOGAF/Zachman), not pure DevOps / SRE, not pure security architecture (those are adjacent disciplines). problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「软件架构」「系统设计」「system design」「应用架构」「service design」
| 触发词：「侍酒师」「sommelier」「葡萄酒」「wine」「盲品」
| 触发词：「语音转文字」「语音识别」「asr」「speech to text」「stt」
| Trigger this skill when the user works on 留学咨询规划 problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「留学咨询」「留学规划」「出国留学」「study abroad」「留学」
| Trigger this skill when the user works on 研学旅行与营地教育（体验式教育新赛道，从业者 + 运营视角）— 中国 2016 年教育部《关于推进中小学生研学旅行的意见》政策驱动后形成的细分赛道，含 (a) 子赛道：自然教育 / 科技研学 / 红色研学（爱国主义+党史）/ 历史人文研学 / 国际游学营地 / 户外营地（夏令营·冬令营）；(b) 课程设计：项目制(PBL)·探究式·体验式学习设计、研学手册、学习目标与学科融合、课程评价；(c) 营地与基地运营：安全管理（师生比·应急预案·保险·食宿交通）、营期排期、辅导员(camp counselor)/研学导师排班、基地/营地建设与等级认定；(d) 政策合规：教育部研学旅行政策、研学实践教育基地/营地认定、营地与户外教育团体标准、双减后校外培训监管边界；(e) 商业模式：B 端（学校集采·教育局采购·公立校综合实践课时）、C 端（家庭付费夏令营·亲子）、渠道分销（旅行社·机构代理）、获客与履约。核心矛盾：教育属性 vs 旅游属性、安全 vs 体验、标准化课程 vs 在地化资源。不含：纯 K12 学科培训 / 留学中介 / 纯旅行社跟团 / 学校内 STEAM 硬件采购。 problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「研学」「研学旅行」「营地教育」「研学营地」「自然教育」
| Trigger this skill when the user works on Traditional Chinese Medicine (TCM) clinical practice — the cognitive operating system of practicing TCM physicians covering (a) 经典理论 (阴阳/五行/脏腑/气血津液/经络/六淫/七情/六经/卫气营血/三焦) classical theory, (b) 四诊 (望闻问切) clinical observation/inquiry/pulse + 八纲 (阴阳/表里/寒热/虚实) syndrome differentiation, (c) 治法 (汗吐下和温清消补 + 扶正祛邪) therapeutic principles, (d) 方剂学 (经方 时方 验方) formula science, (e) 中药学 (四气五味/归经/七情/炮制/配伍禁忌) materia medica, (f) 针灸学 (经络穴位/手法/灸法/电针) acupuncture+moxibustion, (g) 推拿按摩 tuina massage, (h) 中医各科 (内/外/妇/儿/骨伤/皮肤/眼/耳鼻喉/肛肠/老年/急症) clinical specialties, (i) 中西医结合 integrative medicine, (j) 循证中医 + 临床流行病学 evidence-based TCM + 现代研究, (k) 中医诊所备案 / 中医师资格 / NATCM 监管 / 药典 / GMP regulatory framework, (l) 国家级名老中医 学术继承人 项目 transmission program; NOT 道家修炼 / 风水 / 算命八字 (那是 玄学不是 中医), NOT 中医养生科普 (是 衍生 不是 临床主体), NOT 中医美容 (是 商业化分支), NOT 民族医学 (藏蒙维傣 是 平行体系 不在本 skill 主线 — 仅作 边界标注). problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「中医」「中医学」「中医药」「中医诊疗」「中医临床」
| Trigger this skill when the user works on UniFi/UBNT Enterprise Wi-Fi Engineering problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「造大师 UBNT Wi-Fi」「UBNT WiFi 工程」「UniFi 高密度部署」「我做企业 Wi-Fi」「80 人办公网慢」
| 触发词：「推特 ai 博主」「推特中文 ai」「x ai 自媒体」「推特 thread」「推特爆款推文」
| Andrew von Nagy 视角 — 高密度 Wi-Fi 工程的容量优先设计学派代表 (Revolution Wi-Fi 博客, ex-Target Senior Wireless Architect, 现 Nile Principal Architect, CCIE-Wireless + CWNE). 加载后让 AI 用「capacity-first」「retry-rate-over-RSSI」「predictive-must-validate」「client-is-weakest-link」「spectrum-is-shared」五大镜片诊断企业 Wi-Fi 问题, 特别是高密度场景 (≥30 客户端共享区域, 典型 80 人办公室).
| Chris Sherwood / Crosstalk Solutions 视角 — UBNT-native 实战派的代表 YouTuber (475K+ 订阅, 1000+ 视频, UI Toolkit 作者). 加载后让 AI 用 "先演示再讲理论" / "UBNT GUI 默认不够好" / "生态绑定换性价比" 的视角看 UniFi 部署 — 尤其适合 SMB / 家庭实验室 / MSP 场景. 即使用户只是说「这个 UDM-Pro 该怎么开箱配」「80 人办公 UBNT 怎么选硬件」「我家 UniFi 慢」也应触发.
| Devin Akin 视角 — CWNP 联合创始人 / CWNE 流派奠基 / Wi-Fi Vitae 播客主持 / Divergent Dynamics 创办人. 加载后让 AI 用「RF 物理是地基, vendor 是装修」/「教育是 bottleneck 不是技术」/「AIOps 多数是营销层叠加」三大镜片审视企业 Wi-Fi 决策, 特别是 vendor 选型 / 培训路径 / 厂商话术辨别 / AIOps 评估场景. 反 marketing 倾向 + 25 年 instructor 视角 + vendor-neutral 立场.
| Trigger this skill when the user works on Venture capital / early-stage investor — 风险投资人(GP / Partner / Principal)的早期投资判断与基金运营实战 problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「VC」「venture capital」「风险投资」「early stage」「天使投资」
| 触发词：「网文写作」「网络小说」「写网文」「网文作者」「写小说」
| 触发词：「线上展览」「虚拟展厅」「web 线上展览」「云展厅」「数字展馆」
| Trigger this skill when the user works on WeChat Official Account article writing — 微信公众号「文章」这个 artifact 的写作、生产、分发、变现 (单篇文章为单位的 craft + ops + 商业化, 不含 SCRM / 私聊 / 群运营 / 朋友圈 SOP — 那些归 private-domain-ops) problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「公众号」「公众号写作」「公众号运营」「微信公众号」「服务号」
| 触发词：「小红书 ai 博主」「小红书 ai 自媒体」「小红书 ai 赛道」「小红书爆款文案」「小红书 ai 教程」
群响刘思毅视角. 操盘手社群头部 + 私域 + 矩阵派代表. 调用此 skill 时, 用刘思毅的认知框架做小红书操盘手 + 私域 + 矩阵决策.
古麦嘉禾创始团队视角. 内容驱动派代表方法论, 强调内容 IP 化 + 真实分享. 调用此 skill 时, 用古麦嘉禾的认知框架做小红书内容运营决策.
| Trigger this skill when the user works on xiaohongshu operations problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「小红书」「种草」「薯条」「信息流」「笔记」
千瓜数据创始团队视角. 数据驱动派代表方法论 + 工具派. 调用此 skill 时, 用千瓜的认知框架做小红书数据 / 选题 / 投放决策.
| Trigger this skill when the user works on Youth Mental Health Education problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「青少年心理」「心理健康教育」「校园心理」「学校心理辅导」「社交情感学习」
| 触发词：「知乎 ai 博主」「知乎 ai 自媒体」「知乎 ai 赛道」「知乎高赞回答」「知乎 ai 文章」
| Trigger this skill when the user works on Youth Coding Education problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「少儿编程」「青少年编程」「编程教育」「编程启蒙」「Scratch教学」
Investigate unexpected behavior and mysterious bugs. Use when the cause of a problem is unknown and the user needs to understand WHY something is happening — symptoms like: sudden unexplained changes in metrics or behavior, works locally but not in staging/production, inconsistent or intermittent failures, correct code producing wrong results, operations succeeding but having no effect, environment-specific failures, duplicate executions, stale data, or any \"why did this change?\" or \"why is this happening?\" situation. Covers infrastructure anomalies (cache hit rates dropping, latency spikes, queue behavior shifts) as well as code bugs. The key signal is confusion about root cause, not a request to implement a known fix. Do NOT use for feature requests, known fixes, planning, or documentation tasks.
Use when the user wants to save knowledge as a file so others don't have to rediscover it — \"turn this into a doc\", \"write this up\", \"document how X works\", \"we figured this out and want to capture it\", \"nobody should have to figure this out again\". Covers any request to create or update durable written artifacts: onboarding guides, runbooks, ADRs, API docs, architecture notes, postmortems, changelogs, setup guides. The trigger: user wants knowledge captured in a file for future reference, not just a conversation. Do NOT use when still making decisions (→ give-plan), just asking for explanation without a file (→ ask), or writing code (→ cook).
Fix bugs and broken behavior when there is enough evidence to act on a repair path. Use for errors, crashes, incorrect results, API failures (500, 404, 403), CORS problems, database exceptions, broken rendering, duplicated or wrong data, off-by-one mistakes, timezone/date bugs, broken forms, config-caused runtime failures, and regressions. Trigger when the user wants the bug repaired and the conversation already contains a clear failing area, a reproducible failing test, a concrete error path, or a prior diagnosis to implement. Do NOT use for new features, pure explanation, architecture discussion, broad research, or bug reports where the main need is figuring out why the behavior happens — use diagnose for that.
Brainstorms and debates approaches, then drives toward an actionable decision. Use whenever someone needs a thinking partner for a decision they're facing: 'discuss', 'debate', 'brainstorm', 'weigh options', 'tradeoffs', 'should I do X or Y', 'help me decide', 'I'm torn between', 'sanity check my thinking', or 'what do you think about'. The user must be asking for help reasoning through a choice — not asking to build, fix, evaluate, plan, or modify something (even if the topic involves this skill itself). Picks the right decision lens, surfaces tradeoffs and blind spots, pushes back when reasoning is genuinely weak, and never implements.
Answer questions about code, architecture, and technical decisions — no implementation. Trigger on questions asking 'why', 'what does this do', 'what is the purpose of', 'explain', 'what's the difference', 'compare', or 'what are the tradeoffs' — even when referencing specific files, code snippets, or inline code. The key signal is the user wants to UNDERSTAND something, not change it. Do NOT trigger for requests to build, fix, plan, review, research, or add/modify code.
Implement, build, create, or add any feature, endpoint, page, component, or functionality. Use this skill whenever the user asks you to write new code or make code changes — whether it's adding an API endpoint, building a UI page, creating an export feature, wiring up a webhook, implementing a search/filter, or any other hands-on coding task. This is the default skill for all 'build this', 'add this', 'create this', 'wire up', 'implement' requests. Covers the full cycle: clarify requirements, plan if needed, write code, verify, and review. Do NOT use for pure research, debugging, documentation, or explanation — only when the user wants working code delivered.
Fetch up-to-date documentation for any library, framework, API, or service into context. Use when the user wants to look up API references, check function signatures or required fields, find feature-specific docs, or verify how an external tool actually works. Triggers for queries about third-party libraries like Stripe, SQLAlchemy, Tailwind, FastAPI, shadcn, Drizzle, Hono, Better Auth — any time the answer lives in official docs rather than in the project codebase. Use this instead of guessing from trained knowledge, which is stale.
Builds distinctive, production-grade UIs that avoid generic AI aesthetics. Use whenever the user wants to build, restyle, or give visual direction to any interface — pages, dashboards, landing pages, components, onboarding flows, mobile screens, or design systems — even without an explicit 'design' request. Also triggers for: picking an aesthetic direction, improving the look of a dull/generic existing page, adding visual personality, or choosing colors/typography. Includes a bundled design intelligence database for concrete guidance across web (React, Next.js, Vue, Tailwind) and mobile (React Native, Flutter, SwiftUI).
Specialized visual and multimedia processing tools. Use this skill whenever a task involves complex visual content — UI mockups, dense screenshots, design images, charts, artwork — where precise details like spacing, hex colors, font sizes, and component hierarchy need to be extracted accurately. Also use for: reviewing or auditing existing UI against designs, comparing screenshots for visual regressions, transcribing audio/video, extracting data from PDFs with complex layouts, and generating images. Trigger whenever the user wants to implement from a design, review or compare UI screenshots, analyze visual details precisely, describe artwork or aesthetic content, or process any media file (audio, video, PDF).
Use when the user wants a written, reviewable plan or spec produced before coding starts. Triggers on: mapping out changes without implementing, thinking through risks of upgrades or migrations, evaluating approaches before committing to one, writing specs for team review, phasing work into stages, or any request that explicitly defers coding ('don't implement yet', 'before we build'). The distinguishing signal is that the user wants a plan artifact — not implementation, not a conversational answer. MUST activates inside Claude's native plan mode to have a better planning behavior.
Use when the user wants to work on a Claude Code skill file (SKILL.md): writing one from scratch, testing whether an existing one works well, running evals or benchmarks, improving its instructions, or fixing why it isn't triggering. Triggers on: 'make a skill for X', 'test this skill', 'run evals on my SKILL.md', 'touch-skill', sharing a SKILL.md and asking if it's ready to ship. The key signal is intent to create, validate, or improve a skill — not just mention one. Do NOT trigger for general Claude Code questions, hook debugging, or CLAUDE.md configuration.
Syncs Claude config between prime repo and target projects. Trigger on 'sync', 'prime-sync', 'push config', 'pull config', 'update prime', 'sync claude config'. Push mode deploys to targets; pull mode imports changes back.
Review code for quality, correctness, and fit. Use when the user wants judgment on code that already exists — their own changes, a teammate's patch, a PR, branch, commit, diff, staged changes, or one or more files to look over. Activate on requests like review, look over, sanity check, critique, code review, or 'is this good?' The key signal is that the user wants evaluation of existing code and its tradeoffs, not implementation, debugging, or explanation. This skill works independently, but when plans, specs, task artifacts, or prior discussion exist, use them to understand why the code exists before judging it.
>
Generates a Claude Code configuration tailored to a specific project. Use whenever the user wants to prime a project, set up claude for a repo, bootstrap claude config, or re-prime/refresh an already-primed project (for example after `/prime-sync` pulled new starter content). Triggers on 'prime', 'prime this project', 'optimus-prime', 're-prime', 'refresh claude config', 'regenerate CLAUDE.md', 'set up claude for this repo'. Deeply analyzes the real codebase and builds project-specific skills, rules, and CLAUDE.md — not generic boilerplate. For ongoing config health checks and proposal review, use `self-evolve` instead.
Use this skill for any Python backend work in this project: building FastAPI endpoints, writing service functions, defining Pydantic/SQLModel schemas, running Alembic migrations, or debugging 422 errors. Essential for authentication and authorization patterns — setting up get_current_user, is_superuser checks, admin-only guards, role-based access, and dependency injection chains like Depends(). Also covers middleware, background tasks, async SQLAlchemy sessions, ORM relationship loading, and request/response design. Activate whenever the question involves Python API code, FastAPI patterns, or backend architecture in this codebase. Not for frontend, Docker, CI/CD, or infrastructure.
ALWAYS activate when the user's query involves Docker in any way — even if it also matches other skills. If the words docker, Dockerfile, docker-compose, compose.yml, container, or image appear in the query, this skill MUST be used. Covers: writing or editing Dockerfiles and compose files, adding services (postgres, redis, etc.) to compose, volume mounts and data persistence, docker build failures (layer caching, npm install issues), healthchecks and service startup ordering (depends_on), environment variables in containers, port mapping, container crashes and exit codes (OOM/137), non-root users, multi-stage builds, image optimization, .dockerignore, and deploying to container runtimes. Takes priority over general implementation or debugging skills when Docker infrastructure is the subject.
Rewrite existing text so it stops sounding AI-generated. Triggers on "humanize this", "un-ChatGPT it", "doesn't scream LLM", "strip the AI voice", or naming specific AI tells (em dashes, "it's not just X it's Y", "stands as a testament", "thrilled to announce", emoji-headed bullets, LinkedIn cringe). Works on any draft — blog posts, memos, READMEs, essays, PR descriptions — inline or in files. Keeps facts; changes voice. Do NOT use for writing new content, summarizing, translating, or pure-explanation requests with no draft to rewrite.
Use this skill for ANY work involving React, Next.js, TypeScript, or Tailwind in the browser layer. This includes building components and pages, but equally covers debugging and fixing frontend issues: CSS/Tailwind classes not applying, form validation behavior, hydration mismatches between server and client renders, styling bugs, layout shifts, and rendering problems. Also use for refactoring components (e.g., splitting Server vs Client Components), data fetching patterns, state management, bundle optimization, and frontend tooling. If the problem involves what users see or interact with in a web browser — whether building, fixing, or refactoring — use this skill. Not for backend APIs, databases, infrastructure, or DevOps.
MUST use for ANY query mentioning packages, monorepo, workspace, catalog, turbo, turborepo, or pnpm in a multi-package context. MUST use when sharing config (ESLint, tsconfig, prettier) across packages, fixing build order between packages, adding new packages, scoping CI installs/caching to changed packages, or debugging pnpm catalog version resolution. This skill OWNS all cross-package coordination problems — even when they look like build, CI, config, or dependency issues. If two or more packages interact in the query, this skill applies. Takes priority over other skills when the problem spans package boundaries.
>- Review AI-generated or human-written code changes with fallow's graph-grounded review brief. Subtracts deterministic concerns (unused code, complexity, duplication, styling) from the loop, ranks what to look at by blast radius and risk, and surfaces the few consequential structural decisions (new public-API contracts, coupling/boundary crossings, new dependencies) as framed judgment questions anchored to verifiable signals. judgment, and have fallow post-validate it against the live graph (hallucinated or stale judgments are rejected). Use when asked to review a PR, review a branch, review a diff, do a code review, or check changed code before merge.
Codebase intelligence for TypeScript and JavaScript. Static analysis of code and styles reports changed-code risk, cleanup opportunities, duplication, circular dependencies, complexity hotspots, architecture boundaries, design-system drift, feature flags, and opt-in security candidates. Runtime coverage can merge production execution data for hot-path review, cold-path deletion confidence, and stale-flag evidence. 123 framework plugins, zero configuration, sub-second static analysis. Use when asked to audit PR risk, find unused code or dependencies, detect duplicates, check styling consistency, inspect architecture boundaries, merge runtime coverage, auto-fix supported issues, or run fallow.
Use only when explicitly invoked as lamina-init. Establish business evidence and canonical Product, Actor, and Persona resources in Lamina's transactional graph.
Define authoritative runtime product truth across actors and views. Use when modeling domain behavior, setting product density, specifying side effects, protecting invariants, choosing consistency guarantees, handling retries or concurrent actions, defining time semantics and prerequisites, drawing ownership boundaries, or keeping views coherent. Use lamina-systems for causal loops and change over time, and lamina-ux for interaction expression.
Reason about causal product systems and change over time. Use when mapping stocks, flows, delays, purposes, or interconnections; diagnosing reinforcing or balancing feedback; recognizing recurring traps; finding high-leverage interventions; or deciding how rules can evolve safely. Use lamina-product-behavior for one workflow's authoritative states, prerequisites, and consistency rules.
Judge product usability and evidence quality. Use when running Persona-based walkthroughs on a built product, planning an expert heuristic review, defining evidence-backed success metrics, or checking quantitative claims without inventing measurements. Use lamina-research to plan or synthesize evidence collection and lamina-ux to design interaction behavior.
Frame product problems and decide what to build. Use when establishing business context, aligning actors with conflicting goals, discovering or prioritizing features, defining traceable requirements, comparing consequential tradeoffs, or recording a product decision. Use lamina-ux for interaction details and lamina-product-behavior for authoritative runtime rules.
Shape intended product behavior in Lamina's transactional graph when explicitly invoked as lamina-design or when passive implementation preparation reports design gaps. Publish an implementation-ready graph version without editing application source.
Design understandable and accessible product interactions. Use when shaping workflows, information architecture, navigation, interface copy, forms, controls, empty states, onboarding, feedback, error recovery, progressive disclosure, discoverability, accessibility, trust, group dynamics, or interaction edge cases. Use lamina-product-behavior for authoritative state rules and lamina-evaluation to judge a built product.
Plan and synthesize evidence-grounded product research. Use when deciding what evidence is needed, designing actor walkthroughs, grounding claims in a repository or live product, analyzing user-provided references, modeling users and tasks, or communicating findings without inventing data. Use lamina-evaluation instead to judge a built product, and lamina-ux to design interaction behavior.
Verify graph-backed product Missions after ordinary implementation work or when explicitly invoked as lamina-verify. Run isolated Persona and live UI audits; explicit verification is source-read-only.
Route ordinary product implementation and explicit Lamina lifecycle requests. Use passively after initialization for changes to product behavior, flows, permissions, states, failures, or UI; skip purely mechanical maintenance.
Claude Skills — questions
Answers built from the skills we actually parsed.