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. 79 600 files from 1 763 authors, of which 61 947 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.
>- Draft, audit, or revise point-by-point reviewer response letters for Nature-family manuscript revisions. Use when the user provides reviewer comments, editor decision letters, revision notes, response drafts, or asks how to respond to major/minor revision requests, rebuttal letters, response to reviewers, peer-review reports, 审稿意见回复, 逐点回复, 修回信, 大修回复, 小修回复, or 如何回复 reviewer. Also trigger on general peer-review response needs during academic writing/revision even without the word "Nature", such as replying to reviewers for any journal, writing a rebuttal/response letter, handling revision comments, and Chinese phrasings like 回复审稿人、审稿回复、返修、 修改稿回复、写rebuttal、回应审稿意见、应对审稿.
>- Simulate a Nature-style reviewer assessment from the referee perspective rather than an author rebuttal. Use when the user wants a pre-submission review, reviewer report, peer-review style critique, novelty/significance/technical soundness assessment, reviewer-style manuscript evaluation, 审稿人视角评估, 预审稿意见, or Nature reviewer report. Return 3 reviewer reports plus a cross-review synthesis, grounded only in the local Nature reviewer source basis. Also trigger on general pre-submission review requests during academic writing even without the word "Nature", such as getting a mock peer review for any journal, critiquing a draft as a reviewer would, assessing novelty/rigor before submission, and Chinese phrasings like 审稿人视角、模拟审稿、预审、帮我审一下论文、投稿前自审、审稿意见模拟、找论文问题.
Draft, restructure, or plan Nature-style manuscript sections from author-provided claims, results, figures, notes, or Chinese drafts. Use when the user wants to write or rebuild an abstract, introduction, related-work, method, experiments, discussion, conclusion, title, or full manuscript argument rather than only polish finished prose. Also trigger on general academic-writing requests even without the word "Nature", such as writing a paper from scratch, drafting a manuscript/section, structuring a paper, and Chinese phrasings like 学术写作、科研写作、论文写作、写论文、写paper、SCI写作、帮我写论文、搭论文框架、起草论文、写引言/摘要/讨论.
Codex adaptation of the OpenClaw Medical Skills library. Use for biomedical, clinical, healthcare AI, genomics, bioinformatics, drug discovery, pharmacovigilance, clinical trials, medical imaging, public health, medical device, regulatory, scientific data analysis, lab automation, and medical research workflows; also use when the user mentions OpenClaw Medical Skills, medical skill library, or any named capability preserved in the OpenClaw capability index.
Use this skill when the user wants to find customer leads from short-video comments, generate customer-discovery keywords, review lead intent, query a customer pool, or prepare outreach scripts with PPXC.
> Build webpages with vanilla HTML/CSS/JS — no frameworks, no build steps. vanilla JS, design tokens, accessibility, responsive design.
| 分析 Amazon Ads search term report（SP / SB / SD），识别候选 ASIN、报告类型、低效词、放量词、属性词、场景词和趋势变化。 使用时机：用户上传广告搜索词报告，想判断哪些 search term 应该观察、控 bid、否定候选、继续放量，或想把搜索词里的用户需求反馈到 Listing 与投放策略时调用。 触发词：/zach-search-term-report-analyzer
获取ZAKER按行业分类的热门新闻（娱乐、科技、财经等）。Use when the user asks about 科技新闻, 财经新闻, 体育新闻, 娱乐新闻, 行业新闻, 互联网动态, 汽车新闻、国内新闻、国际新闻、军事新闻、finance news, tech news, sports news, industry updates.
获取ZAKER聚合权威媒体的最新头条新闻与热点资讯。Use when the user asks about 新闻, 头条, 最新新闻, 今日新闻, 热点新闻, 突发新闻, 国内外大事, 最近发生了什么, 有什么新鲜事, trending news, latest news, headlines, breaking news, what’s happening.
基于ZAKER权威资讯库进行关键词新闻检索，支持指定时间范围（30天内）。Use when the user asks about 搜索新闻, 某事件新闻, 某人物新闻, 某关键词相关新闻, 查新闻, 新闻检索, 相关新闻, 某时间段新闻.
Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth preserving, and when the environment can either persist it through `write_task_memory` or emit a structured memory candidate for later save.
Integrate applications with RouterBase, the OpenAI-compatible model gateway at https://routerbase.com/v1. Use when migrating OpenAI SDK calls to RouterBase, configuring RouterBase API keys, implementing chat completions, streaming, tool calling, JSON mode, vision inputs, request validation, error handling, or documenting RouterBase setup for Python, JavaScript, curl, LangChain, LlamaIndex, Vercel AI SDK, Cursor, Continue, or other OpenAI-compatible clients.
Build image, video, and audio generation workflows on RouterBase. Use when calling RouterBase image, video, audio, speech, or media APIs; selecting media model IDs; handling synchronous image responses; polling asynchronous video or audio tasks; using callback URLs; storing generated media before retention expiry; or migrating OpenAI-compatible image generation calls to RouterBase.
Choose RouterBase model IDs and routing strategies for chat, image, video, audio, and embeddings workloads. Use when comparing providers, selecting GPT, Claude, Gemini, image, video, or audio models on RouterBase, designing fallback paths, checking pricing or availability, planning cost/latency/quality tradeoffs, querying the RouterBase Models API, or documenting how an app should route model requests through RouterBase.
Look up and cite verifiable GPU/compute rental reference prices (H100, A100, H200, and more; spot, on-demand, or DePIN markets) from the public FLOPS Index — no API key required. Use when the user asks what a GPU or accelerator costs to rent, wants the cheapest option for a given chip, wants to compare spot vs on-demand vs decentralized compute rates, or wants to fact-check / cite a compute price with a source they can independently verify. Keywords: GPU price, H100 cost, A100 rental, compute pricing, spot price, on-demand, DePIN, GPU-hour, accelerator rental, FLOPS index.
API文档自动生成 — 代码→OpenAPI 3.0规范文档+请求示例+Postman集合
自动代码审查 — PR代码→安全扫描+性能分析+最佳实践建议+评审报告
竞品自动分析 — 输入竞品名单→自动采集数据+SWOT分析+差距报告
数据清洗自动化 — 脏数据→去重/补全/格式统一/异常检测→干净数据集
邮件营销文案生成 — 产品信息→标题5选1+正文+CTA+A/B测试方案
Excel公式大师 — 描述需求→自动生成公式+VBA宏+数据透视表方案
发票/账单自动整理 — 截图/PDF上传→OCR识别→分类→Excel表格
行业客户名单爬取 — 地区+行业→企业名称/联系人/电话/地址CSV
会议纪要自动整理 — 录音/文字记录→结构化纪要+待办事项+责任人追踪
简历优化专家 — 输入简历→JD匹配分析+优化建议+面试问题预测
社媒内容日历 — 输入主题→30天内容规划+各平台适配+发布时间建议
SQL查询生成器 — 自然语言描述→SQL语句+执行计划分析+优化建议
周报/月报自动生成 — 输入工作日志→结构化周报+数据图表+下月计划
小红书爆款文案自动生成器 — 输入产品/卖点，3篇完整笔记+标题+标签+封面
Write verifiable Loop Engineering specs for Codex, Claude Code, OpenClaw, and AI coding agents.
Create a topic-specific GitHub awesome-list repository scaffold with a polished README, concise contribution rules, AI-agent instructions, URL verification, license, and reusable templates. Use when the user wants to generate a new awesome repo, awesome list, curated repository, or topic resource catalog from a topic plus optional taxonomy, inclusion criteria, and researched entries.
Convert a finished raster image, especially a generated poster or visual resume, into an image-based PDF with an additional selectable, copyable, searchable text layer. Use when the image is the final visual layout, when recreating that layout in PPT, HTML, or LaTeX would be fragile, and when the user needs both a final invisible-text PDF and a visible inspection PDF for checking OCR or text-layer placement.
Work with a user's Semantic Scholar account to read Research Feeds, inspect private Library folders, add papers to folders, and resolve Semantic Scholar paper records from identifiers such as arXiv IDs.
Publish, submit, and verify local skills across public skill marketplaces, directories, and registries. Use when an agent needs to take a skill folder or skill repository, confirm current submission paths, prepare cross-market metadata, run verified live adapters, or generate manual submission bundles for markets such as AgentSkill.sh, Skillstore, SkillNet, agent-skills.md, SkillsMD, SkillHub, SkillHQ, and related registries.
Find papers and preprints that cite a given URL, especially blogs, docs pages, project pages, or other web content that standard citation indexes often miss. Use when the user provides a URL and wants confirmed citing works, evidence from PDF or HTML references, DOI or arXiv links, BibTeX, or a deduplicated citation report.
架构文档生成 — 生成架构设计说明书、技术方案文档、API设计文档、部署架构文档
技术选型评估 — 多维度技术对比、POC方案设计、风险评估，输出结构化评估报告
后端开发工程师 Agent — 覆盖 API 开发、数据库设计、系统架构、性能优化、安全防护、CI/CD、部署运维等全栈后端工作流
BI/数据分析工程师 Agent — 覆盖数据采集、ETL、指标体系建设、可视化看板、专题分析、数据产品全流程。支持SQL查询、Python分析、BI工具集成、自动化报表、A/B测试分析。
数据工程师 Agent — 覆盖数据管道开发、数据仓库/数据湖建设、ETL/ELT 开发、实时流处理、数据质量保障、数据治理、大数据框架运维等全领域数据工程工作。能动手搭建数据基础设施，不只是出方案。
DevOps/SRE 工程师 Agent — 覆盖 CI/CD 流水线、容器化与 K8s、基础设施即代码、可观测性、SLO/SLI/Error Budget、容量规划、混沌工程、事故响应与复盘、成本优化等全领域工作。能动手执行，不只是出方案。
前端开发工程师Agent — 从零搭建前端项目、开发UI组件、对接API、状态管理、构建配置、调试优化、测试编写。覆盖前端开发全流程。
移动端工程师 Agent — 覆盖 iOS/Android/跨平台应用开发、架构设计、UI实现、网络与数据层、性能优化、安全加固、测试与CI/CD、发布运维全流程。支持Flutter、React Native、Swift、Kotlin等主流技术栈。
运维工程师 Agent — 覆盖基础设施管理、容器与K8s、CI/CD、监控告警、故障排查、自动化脚本、安全运维、备份灾备等全领域运维工作。能动手执行，不只是出方案。
支付工程师 Agent — 覆盖支付系统架构设计、渠道对接、交易核心开发、对账清算、风控安全、性能优化全流程。支持 Java/Go/Python 技术栈，深度使用分布式中间件。
覆盖性能测试（压测、监控、调优、容量规划）与全栈开发（前后端、API、数据库、DevOps）的复合工程师技能。支持从需求分析到压测执行到瓶颈定位到调优建议的全流程。
风控工程师（反欺诈/反作弊）Agent — 覆盖风险策略制定、特征工程、模型开发、实时风控系统建设、黑产对抗、数据监控全流程。支持规则引擎设计、异常检测、团伙欺诈挖掘、策略回测与迭代。
搜索工程师 Agent — 覆盖搜索引擎搭建、索引构建、检索排序、查询理解、语义搜索、RAG系统、性能优化、质量评估全流程。支持Elasticsearch/Solr/Milvus等主流引擎。
安全工程师 Agent — 覆盖渗透测试、安全架构评审、DevSecOps、漏洞管理、安全监控与应急响应、合规审计、代码安全审查等全领域安全工作。能动手执行扫描、分析、加固、报告，不只是出方案。
软件架构师Agent — 系统架构设计、技术选型评估、架构文档编写、代码库架构分析、C4模型图生成。覆盖架构师全工作流。
测试工程师 Agent — 动手执行测试全流程：编写并运行自动化测试脚本、执行接口/性能/安全测试、搭建CI流水线、分析缺陷、生成测试报告。覆盖主流测试工具链（pytest/Selenium/Playwright/JMeter/k6/Postman等）。
爬虫/数据采集工程师 Agent — 覆盖网页数据采集、API抓取、动态内容渲染、反爬对抗、数据清洗存储、分布式爬虫架构、App抓包逆向等全领域数据采集工作。能动手搭建完整爬虫系统，不只是出方案。
【老房改造业主必看】你家的房子是老房、旧房、二手房吗？担心拆除被坑、水电要不要全换、承重墙不敢动、费用比新房贵太多？这个Skill内置装修课堂知识库，直接回答你的问题——问拆除、问水电、问费用、问结构安全、问厨卫翻新、问精装房怎么改，全部覆盖。适合正在考虑老房翻新、二手房装修、精装房改造的业主。
【全屋定制业主必看】你正在做全屋定制吗？不知道板材怎么选、怕被套餐套路、担心增项加钱、不知道怎么验收？这个Skill内置装修课堂知识库，直接回答你的问题——问板材、问计价、问套餐、问商家选择、问安装验收，全部覆盖。适合正在做全屋定制功课、准备签约或已经下定的业主。
【儿童房装修必看】家里有小孩、正准备要孩子、或想给儿童房做环保安全装修？这个 Skill 内置装修课堂知识库，专门讲"适童化"——儿童是最易受甲醛伤害的人群，儿童房必须实木/ENF/控总量。问儿童房怎么装环保、问儿童房墙面地面用什么、问儿童家具选实木还是人造板、问孩子学习/游戏专区怎么规划、问有娃家庭怎么防磕碰防污染，全部覆盖。适合家里有娃、备孕婚房、想装出健康儿童房的业主。
【拿到报价单必看】你拿到装修报价单了吗？看不懂、怕被坑、不知道价格合不合理？这个Skill内置装修课堂知识库，直接帮你审核报价单——问报价单怎么看、问预算陷阱、问单价猫腻、问隐形消费、问水电估价、问半包全包区别、问厨卫费用，全部覆盖。适合拿到报价单不知怎么看、比较多家报价不知怎么选、被低价吸引担心有坑的业主。
【装修小白必看】你是第一次装修的小白吗？什么都不知道、不知道问什么、怕被坑又不知道坑在哪？这个Skill覆盖装修全流程——问找公司、问签合同、问施工、问选材、问设计、问布局、问家具家电，一站式解答你的装修疑问。适合装修小白、第一次装修、不知道从哪下手的业主。
【装修翻车必看】你家装修翻车了吗？瓷砖空鼓、墙面开裂、漏水、尺寸错了、插座不够、灯偏了？这个Skill内置装修课堂知识库，直接教你怎么补救——问翻车怎么办、问补救方法、问修复成本、问能不能自己搞定，全部覆盖。适合装修已经翻车、不知道怎么办、返工成本太高想找替代方案的业主。
【装修方案拿不准必看】你的装修方案合理吗？不知道布局对不对、收纳够不够、风格怎么选、户型能不能改？这个Skill内置装修课堂381篇文章，直接诊断你的方案——问设计布局、问户型改造、问收纳规划、问风格搭配、问翻车避坑、问设计师怎么选，全部覆盖。适合正在确认方案、担心布局不合理、想优化空间利用的业主。
本Skill内置从学到装｜装修课堂知识库，专门帮业主审核装修合同、识别预算陷阱、防范定金套路、避免增项偷项、看懂报价单、判断售后保障。适合准备签装修合同、拿到报价单不知怎么看、被要求交定金、遇到中途加钱的等场景使用。触发场景包括"装修合同怎么签""报价单怎么看""定金能退吗""套餐能签吗""装修增项怎么办""怎么选装修公司"等涉及装修合同审核的所有问题。
Claude Skills — questions
Answers built from the skills we actually parsed.