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. 79 354 files from 1 739 authors, of which 61 713 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.
This skill provides Python coding standards and is automatically loaded for Python projects. It includes naming conventions, best practices, and recommended tooling.
Build or edit Slidev (sli.dev) presentations for tech talks, workshops, conference sessions, and live-coding demos. Use when the user asks to create slides, a deck, a presentation, a workshop deck, a conference talk, or edit an existing slides.md.
Kotlin coding standards for modern applications. Includes naming conventions, coroutines, flows, modern Kotlin 2.3.0 features, and recommended tooling.
This skill provides Shell/Bash coding standards and is automatically loaded for shell projects. It includes defensive scripting patterns, best practices, and recommended tooling.
Guide users through creating, reviewing, and fixing custom skills for Claude — both command skills (invoked via /slash) and context skills (auto-loaded by tech stack). Use when the user asks to create a skill, build a skill, make a new slash command skill, add a coding standards skill, review an existing skill, update a skill, or fix a skill that doesn't trigger.
Java coding standards for enterprise applications. Includes naming conventions, modern Java features, design patterns, and recommended tooling.
Gradle build tool standards focusing on Kotlin DSL. Covers project configuration, dependency management, and custom plugin/task development with Gradle 9 LTS.
Download YouTube video transcripts with automatic frame extraction for visual references. Use when analyzing YouTube videos, tutorials, or conference talks.
This skill provides TypeScript coding standards and is automatically loaded for TypeScript projects. It includes naming conventions, best practices, and recommended tooling.
Write INVEST-compliant user stories with Given-When-Then acceptance criteria. Use when writing user stories, creating acceptance criteria, or during /design Step 4.
Use when installing or operating Univer CLI for .univer files, spreadsheets, documents, slides, Base databases, Board canvases, cross-Unit embedding, worktrees, Facade authoring, inspection, verification, import/export, screenshots, or viewer handoff.
Use when installing or operating the independent Univer Workspace CLI application (`univer-workspace-cli`) for remote Workspace files, Personal or Team Spaces, task Worktrees, Sheet/Doc/Slide Units, Facade authoring, inspection, verification, import/export, screenshots, or review handoff. Do not use for local targets handled by `univer`.
Proactively apply when creating design systems, component libraries, or any frontend application. Triggers on CSS Grid, Subgrid, Flexbox, Container Queries, :has(), @layer, @scope, CSS nesting, @property, @function, if(), oklch, color-mix, light-dark, relative color, @starting-style, scroll-driven animations, view transitions, anchor positioning, popover, customizable select, content-visibility, logical properties, text-wrap, interpolate-size, clamp, field-sizing, modern CSS, CSS architecture, responsive design, dark mode, theming, design tokens, cascade layers. Use when writing CSS for any web project, choosing layout approaches, building responsive components, implementing dark mode or theming, creating animations or transitions, styling form elements, or modernizing legacy stylesheets. Modern CSS features and best practices for building interfaces with pure native CSS.
Proactively apply when creating new features/components/pages or setting up frontend project structure. Triggers on FSD, feature slicing, Feature-Sliced Design, frontend architecture, layer structure, module boundaries, scalable frontend, slice organization, public API, barrel exports, import rules, Steiger. Use when restructuring React/Next.js/Vue/Remix projects, organizing frontend code, fixing import violations, deciding where code belongs (entity vs feature vs widget vs shared), or migrating legacy codebases. Feature-Sliced Design (FSD) architecture for frontend projects.
Proactively apply when creating web applications, Node.js services, or any JavaScript project. Triggers on JavaScript, ES6, ES2020, ES2022, ES2024, ES2025, ES2026, modern JS, refactor legacy, array methods, async/await, optional chaining, nullish coalescing, destructuring, spread, rest, template literals, arrow functions, toSorted, toReversed, at, groupBy, iterator helpers, Set union intersection difference, Promise, Promise.try, RegExp.escape, Array.fromAsync, using await using, Temporal, functional programming. Use when writing new JavaScript code, refactoring legacy code, modernizing codebases, implementing functional patterns, checking which ECMAScript edition or runtime supports a feature, or reviewing JS for performance and readability. Modern JavaScript (ES6-ES2026) patterns and best practices.
Proactively suggest diagrams when explaining complex systems. Triggers on diagrams, charts, visualizations, flowcharts, sequence diagrams, architecture diagrams, ER diagrams, state machines, Gantt charts, mindmaps, C4, class diagrams, git graphs, kanban boards, sankey, timelines, quadrant charts, XY charts, packet diagrams. Use when user asks for visual representations of code, systems, processes, data structures, database schemas, workflows, or API flows. Generate Mermaid diagrams in markdown.
Proactively apply when creating APIs, backends, or data models. Triggers on PostgreSQL, Postgres, Drizzle, drizzle-orm, drizzle-kit, database, schema, pgTable, tables, columns, indexes, queries, migrations, ORM, relations, relational queries, joins, transactions, SQL, connection pooling, PgBouncer, N+1, JSONB, RLS, full-text search, partitioning. Use when writing database schemas, queries, migrations, connection setup, or any database-related code. PostgreSQL and Drizzle ORM best practices.
Proactively apply when generating any Slack text content, chat.postMessage text fields, or text objects with type "mrkdwn". Triggers on mrkdwn, Slack formatting, Slack markdown, Slack bold, Slack italic, Slack link syntax, Slack mentions, Slack date formatting, Slack escaping, Slack text object, verbatim, plain_text, Slack mrkdwn vs markdown, markdown_text, Slack blockquote, Slack code block, Slack strikethrough, Slack user mention, Slack channel mention, Slack emoji, link_names, auto-parsing, unfurl_links, mrkdwn_in. Use when formatting Slack message text, writing mrkdwn strings, constructing text objects, escaping user content for Slack, adding mentions or date formatting to messages, streaming markdown to Slack, or debugging text rendering issues. Slack mrkdwn text formatting syntax for messages, text objects, and attachments.
Proactively apply when generating Slack API payloads with blocks, chat.postMessage calls with structured content, streaming AI responses, or views.open/views.publish calls. Triggers on Block Kit, Slack blocks, section block, actions block, header block, context block, alert block, card block, carousel block, container block, table block, data table block, data visualization block, Slack chart, markdown block, rich text block, image block, input block, video block, context_actions block, plan block, task_card block, chat.startStream, chat.appendStream, chat.stopStream, Slack modal, Slack App Home, Slack surfaces, Slack interactive elements, Slack button, select menu, overflow, datepicker, checkboxes, radio buttons, Work Objects, Slack link unfurl, views.open, views.update, views.push, views.publish, Slack composition objects. Use when building Block Kit payloads, blocks arrays, modals, App Home views, interactive elements, link unfurling, streaming agent output, or rich message layouts.
Proactively apply when designing APIs, microservices, or scalable backend structure. Triggers on DDD, Clean Architecture, Hexagonal, ports and adapters, entities, value objects, domain events, CQRS, event sourcing, repository pattern, use cases, onion architecture, outbox pattern, aggregate root, anti-corruption layer. Use when working with domain models, aggregates, repositories, or bounded contexts. Clean Architecture + DDD + Hexagonal patterns for backend services, language-agnostic (Go, Rust, Python, TypeScript, Java, C#).
Proactively apply when generating Microsoft Teams Adaptive Card JSON, Bot Framework card attachments, Teams SDK card responses, message extension cards, Microsoft Graph chatMessage Adaptive Card attachments, Incoming Webhook or Workflows webhook Adaptive Cards, notification cards, approval cards, form cards, Action.Submit, Action.Execute, Universal Actions, refresh, user-specific views, card mentions, msteams.entities, msteams.width, Teams responsive card layout, CodeBlock, Table, FactSet, ColumnSet, Input.ChoiceSet, People Picker, or debugging Teams card rendering. Use when constructing, validating, wrapping, or migrating Teams card payloads, including MessageCard-to-Adaptive-Card migrations.
Proactively apply when generating Microsoft Teams message text, Bot Framework activities, Teams SDK bot responses, Microsoft Graph chatMessage bodies, Teams Adaptive Card TextBlock or FactSet text, Workflows webhook messages, legacy connector MessageCard text, mentions, emoji, code blocks, links, date/time text, or escaping user content for Teams. Triggers on Teams markdown, Teams Markdown, Teams HTML, Teams bot textFormat, Teams message formatting, Teams mentions, at-mention tags, msteams.entities, Graph chatMessage, contentType html, Adaptive Card Markdown, TextBlock markdown, FactSet markdown, Workflows webhook, Incoming Webhook, MessageCard, connector card, tag mention, channel mention, Teams code block, Teams emoji, and Teams escaping. Use when writing or debugging any Microsoft Teams text rendering issue.
Analyze Apple Health export ZIP. Run local prepare to generate structured insights, then produce complementary health and training reports with long-term context.
Use when the user wants Agnes AI text, image, or video generation and should execute it through the agnes-ai-cli command line instead of hand-writing raw HTTP requests.
Create a consistent oil-style visual system in two modes: finished explanatory images with short accurate labels generated directly inside the scene, and transparent character illustrations produced with a bundled background-removal script. Use for concepts, mechanisms, comparisons, workflows, tradeoffs, hero artwork, editorial character scenes, and reusable layout illustrations featuring the glasses stick figure and warm-yellow Border Collie.
中国境内产品法务与产品合规 Skill。用于产品上线、功能合规、默认开启、客户 Logo/客户案例展示、PRD/页面流程/用户协议/隐私政策/帮助中心审查、产品材料合规审查、高合规行业产品深度评估、营销文案产品场景初筛等任务。适用于用户询问“这个功能能不能做”“能不能把客户 logo 放官网”“产品材料是否合法合规”“医疗/金融/教育/AI/平台类产品是否能上线”等问题。
系统化支持债权人会议的筹备、召开、表决、纪要全流程工作，覆盖管理人、债权人代理、债务人代理三角色。支持第一次及后续多次债权人会议。当用户发送客户编号并提及"债权人会议"、"召开会议"、"准备会议"、"会议通知"、"会议议程"、"会议纪要"等指令时触发使用。
将法条/规范文件（.txt/.docx/.pdf）转为 Markdown。适用于用户要求“法条转 markdown”“pdf/docx 转 markdown”。处理 .pdf/.docx 时先检查是否已安装 mineru-ocr skill；未安装先引导安装，安装后优先用 mineru-ocr；仅在用户明确同意时再用本地回退方案。
Chinese legal workflow skills for lawyers, legal counsel, litigation, criminal defense, labor disputes, bankruptcy, contract review, compliance, legal research, and legal document drafting.
刑事辩护侦查阶段工作Skill，涵盖会见全流程、案件法律分析与量刑预判、批捕时间节点管理、法律文书生成、执业风险防范等完整辩护工作规范
刑事辩护一审阶段工作Skill，覆盖法院审判阶段的委托衔接、补充阅卷、会见、庭前会议、调查取证、非法证据排除、法庭发问质证举证辩论、认罪认罚、庭后工作与上诉评估。当用户提及"一审阶段"、"刑事一审"、"开庭辩护"、"庭前会议"、"非法证据排除"、"刑事庭审"等关键词时触发使用。
刑事辩护二审阶段工作Skill，覆盖上诉审委托接案、一审材料衔接、阅卷审查、会见策略、争取开庭、书面辩护意见、二审庭审、不开庭审理沟通、裁判分析及发回重审衔接。当用户提及"二审"、"上诉"、"抗诉"、"争取开庭"、"发回重审"、"二审辩护"等关键词时触发使用。
破产债权管理全流程Skill，覆盖债权申报、审查、编制债权表全流程。适用于管理人（R1）、债权人代理（R2）、债务人代理（R3）三种角色。当用户发送客户编号并提及"债权申报"、"债权审查"、"编制债权表"、"申报债权"等指令时触发使用。
基于张海燕四步审查法+何力/常金光三观分析法，对合同进行深度审查。支持企业核验、多语言自动检测、Mermaid业务流程图、二段式审核意见、合同概览、客户可读合同编号、业务摘要、22类合同专项审查、续约提醒和 Word 修订模式审核红线稿。飞书正式交付物必须包含问题卡片列表和业务流程图；用户选择修订模式时，以原合同为只读来源，先生成 redline-plan.json，再运行 scripts/redline/apply_redline_plan.py 生成带真实修订痕迹和批注的 Word 审核修订稿，并完成红线 QA。其他记录保存为本地 Markdown。
| 刑事辩护专业流程编排 Skill，负责根据刑事诉讼阶段和特殊标签进行专业路由、 阶段转换提示、关键期限提示和下一步工作建议。当用户提及"刑事案件"、 "刑事辩护"、"刑辩"等关键词，或需要跨阶段协调刑事辩护工作时触发。 事项建档、路径、文件读取、来源披露、OCR 校正和缺口归档由「法律工作总控」统一处理。
基于"六来源体系"、请求权基础6步法与要件审判九步法融合框架，进行系统性法律分析，按总控当前事项记录和复盘台账衔接，生成法律服务建议书Word文档。当用户发送客户编号并提及"初步法律分析"、"法律分析"、"请求权分析"等指令时触发使用。
劳动争议案件证据管理专属Skill，覆盖举证责任倒置规则、按12类争议类型自动生成证据收集清单、证据效力三级评估、四类特殊保护自动检测、规章制度合法性审查三要件、劳动者代理证据完整性检查和用人单位争议/合规证据清单。输出举证责任分配表、证据收集清单、特殊保护检测报告、公司端事实与制度证据缺口表。当用户发送客户编号并提及"举证责任"、"劳动争议证据"、"证据清单"、"特殊保护"、"员工手册证据"、"公司端证据"等指令时触发使用。
合同起草、生成合同、拟定协议、写合同、根据交易安排形成合同文本、多轮修订和最终版归档的唯一入口。基于三观四步法与用户可选配置的本地合同模板库，支持有模板时定制化起草、无模板时独立起草；输出合同草案，并同步生成客户可读合同编号、合同概览、业务摘要、版本记录、修订历史和续约提醒信息。
劳动争议诉讼专业流程编排 Skill。整合17个子Skill：复用14个现有通用Skill + 3个劳动争议专属Skill（劳动争议仲裁程序管理、劳动关系认定与经济补偿计算、劳动争议证据体系）。用于判断劳动争议阶段（协商→调解→仲裁→一审→二审，L0-L15/LM系列）、识别W/E代理角色、区分劳动者代理、用人单位争议代理和用人单位日常劳动合规任务、推荐下一步子Skill、提示关键节点确认和期限；事项建档、路径、文件读取、来源披露、OCR 校正和缺口归档由「法律工作总控」统一处理。
劳动争议仲裁程序全流程管理Skill，覆盖仲裁前置强制检测、仲裁时效计算、一裁终局自动判断、仲裁申请书/答辩书生成（W/E双角色）、仲裁请求清单、仲裁→诉讼衔接路由（L9五分支）、仲裁策略报告和用人单位仲裁前风险敞口评估。当用户发送客户编号并提及"仲裁申请"、"仲裁答辩"、"仲裁策略"、"仲裁时效"、"公司仲裁风险"、"风险敞口"等指令时触发使用。
劳动争议案件核心分析工具，覆盖劳动关系三性从属分析、12类争议自动分类、工时制度定性、工资工时问答、经济补偿计算引擎（N/N+1/2N判断+月工资基数+三层封顶）、加班费三档计算、双倍工资计算。当用户发送客户编号并提及"劳动关系认定"、"经济补偿"、"补偿计算"、"加班费计算"、"工资工时"、"发薪日"、"特殊工时"等指令时触发使用。
协助律师完成委托合同签订和案件归档。签订阶段覆盖收费方式确认、授权范围确认、全套委托文书生成；归档阶段覆盖诉讼跟踪记录表生成和客户档案更新。当用户发送客户编号并提及"签订合同"、"案件建档"等指令时触发使用。
从已有案件材料（起诉状、答辩状、庭审纪要、法律分析等）中提取要素，生成法院内部审理报告Word文书初稿。按总控当前事项记录和复盘台账衔接。当用户发送客户编号并提及"审理报告"等指令时触发使用。
| 覆盖审查起诉阶段辩护律师全部工作职责的专业技能模块，包括阅卷权、会见权、调查取证权、 证据核实权、意见表达权、非法证据排除申请权、控告申诉权等七类核心权利的行使指导， 以及法律文书生成、量刑预判、与检察机关沟通策略等全流程工作规范。
广告合规审核技能，用于审核广告素材是否符合中国广告法及相关法规。适用场景：(1) 用户提交广告文案、广告素材要求合规审核时；(2) 用户提到"广告审核""广告合规""广告法审查"等关键词时；(3) 用户要求检查广告内容是否存在违法违规风险时；(4) 用户提交房地产、食品、医疗、药品、互联网等行业广告要求专项审核时。审核依据涵盖《广告法》《反不正当竞争法》及行业专项法规。
系统化支持庭审前检查提醒、庭审纪要记录、庭审复盘分析、庭后代理词撰写、补充材料管理、与当事人和法官沟通等全流程工作。当用户发送客户编号并提及"开庭"、"庭审"、"庭后"、"代理词"、"复盘"、"庭审纪要"、"法官沟通"等指令时触发使用。
庭前准备。基于起诉状、法律分析、诉讼可视化、案例汇编、质证意见等前置文档，自动归纳争议焦点，生成争点导向型庭审提纲、质证攻防矩阵、举证策略规划表、开庭陈述提纲、法庭辩论提纲、代理词和诉讼法律服务方案。当用户发送客户编号并提及"庭前准备"、"庭审提纲"、"代理词"、"诉讼方案"等指令时触发使用。
未成年人刑事案件专项辩护Skill，覆盖未成年人刑事案件的教育感化挽救原则、社会调查、不逮捕申请、附条件不起诉、犯罪记录封存、不公开审理、法定代理人到场和信息保护等工作。当用户提及"未成年人"、"少年犯"、"社会调查"、"附条件不起诉"、"犯罪记录封存"、"不公开审理"等关键词时触发使用。
将法律文本（法律条文或法律案例）转换为规范的 Markdown 格式，删除推广冗余信息。本技能应在用户需要处理法律条文（如民法典、刑法等）、整理法律案例（如最高法典型案例、裁判文书等）、或从粘贴文本中格式化法律文档时使用。注意：本技能只负责格式化和内容清理，不包含内容抓取能力。内容获取应由其他 skill（如 wechat-article-fetch）完成，AI 会自动判断技能协作顺序。
刑事辩护案件承接与委托Skill。协助律师完成刑事案件的初次接待、案件评估、风险告知、委托手续办理及案件信息采集，生成标准化委托文书并建立案件档案。当用户发送客户编号并提及"刑事案件承接"、"刑事委托"、"刑事接案"等指令时触发使用。
AI自动完成的深度案件分析工具，整合前序材料进行四维度自问自答分析、三方模拟法庭演练，最终生成案件提纲。当用户提及"案件讨论"、"案件提纲"、"案件分析"、"模拟法庭"、"案件研讨"等指令时触发使用。立案完成后主动提醒律师执行。
根据案件材料或沟通记录生成各类法律服务文档（诉讼方案、咨询报告、非诉方案、建议书、沟通报告等）。本技能应在用户需要将案件材料、咨询记录或沟通内容整理为专业法律文档时使用。
制作民商事诉讼案件沟通记录文档，依据《诉讼精细化》手册要求，采用对话式笔录格式记录与客户首次深度沟通的内容，最终生成Word格式的案件沟通记录。当用户发送客户编号并提及"案件沟通记录"、"制作沟通记录"或类似指令时触发使用。
民事一审诉讼与破产案件专业流程编排 Skill。整合25个子Skill：民事诉讼14个（法律咨询助手、案件沟通记录、初步法律分析、委托合同管理、法规案例检索、调查取证与证据管理、立案管理、诉讼可视化、案件讨论与提纲、诉讼文书起草、庭前准备、庭审与庭后工作、调解与和解、诉讼分析工具、结案归档）+ 破产案件10个（破产法律分析、破产申请与受理、管理人工作、财产调查与管理、债权申报与审查、债权人会议、重整程序、破产和解程序、破产清算、破产文书生成）。用于判断民事/破产案件阶段（S0-S16/SM/BP系列）、推荐下一步子Skill、提示关键节点确认和期限；事项建档、路径、文件读取、来源披露、OCR 校正和缺口归档由「法律工作总控」统一处理。
一审普通程序民事判决书生成工具。从已有案件材料（起诉状、答辩状、庭审纪要、法律分析等）提取要素，生成符合法院文书样式标准的Word判决书初稿。按总控当前事项记录和复盘台账衔接。当用户发送客户编号并提及"判决书"、"民事判决书"、"起草判决书"、"模拟判决书"等指令时触发使用。
死刑案件及死缓案件刑事辩护专项Skill，覆盖可能判处死刑案件识别、一审保命辩护、二审强制开庭、被害人和解、死刑复核辩护、死刑案件证据标准和被害人代理注意事项。当用户提及"死刑"、"死缓"、"死刑立即执行"、"死刑复核"、"核准死刑"等关键词时触发使用。
| 按罪名/领域/关键词检索 Wiki 知识页，返回知识卡片或全文内容。 支持刑事罪名知识、民事领域知识、案例知识页的查询与交叉引用跳转。 当用户提及"查Wiki"、"知识库查询"、"查罪名"、"查法律知识"、"wiki查询"等关键词时触发。
协助律师处理微信渠道法律咨询和线下咨询，提供口语化回复建议、智能反问引导、软性销售植入，并在用户明确要求或总控确认需要时更新复盘台账。支持客户编号识别、咨询入口路由、线下咨询事实补全等功能。
在法律业务 Skill 生成正文或要素式字段后、法律文书模板与导出生成本地 Word 前触发。用于审查 draft.html/preflight-meta.json 或 complaint-data.json/fill-plan.json、读取复查摘要、法规校验摘要、来源边界和用户确认记录，决定是否可以进入正式 DOCX 导出；发现问题后必须闭环推进到业务 Skill 整改、用户确认或材料读取流程。
legal 文件夹通用入口 Skill。用于法律咨询、案件办理、合同、产品法务、监管合规、诉讼、刑辩、劳动争议、破产、合规、文书、检索等任务的语义路由、案件隔离、来源披露、文件读取复查、法规/Wiki 校验、OCR 校正、缺口提示和合同偏好学习。用户提出任何法律工作请求、客户编号、案件材料处理、法律文书生成或需要自动匹配 legal 子 Skill 时触发。
Claude Skills — questions
Answers built from the skills we actually parsed.