GitRank
EN
技能目录

找到适合任务的技能

按具体用途查找仓库内的技能文件。比较整个仓库的热度与增长，请查看技能插件榜。

浏览技能 · 185

brainstorming

obra/superpowers · skills/brainstorming/SKILL.md

obra/superpowers 的 brainstorming 技能：在任何创造性工作之前必须使用，包括开发功能、构建组件、添加功能、修改行为，或规划任何新事物，无论软件还是软件之外（演讲、商业、装修）。

MIT查看原始说明 ↗

diagnosing-superpowers

obra/superpowers · skills/diagnosing-superpowers/SKILL.md

当 superpowers 会话出问题、人类伙伴想查明原因时使用：重复工作、计划被忽略、失误、结果不佳、技能未触发、“耗时太长”、“为何这么贵”、“它在做什么”，或想为 superpowers 维护者构建缺陷报告，针对当前会话或由 id 或路径指定的过往会话，适用于任何 harness。

MIT查看原始说明 ↗

executing-plans

obra/superpowers · skills/executing-plans/SKILL.md

obra/superpowers 的 executing-plans 技能：当你在当前会话中亲自作为实现者执行实施计划时使用，适用于人类伙伴选择内联执行，或没有可用的子代理工具的情况。

MIT查看原始说明 ↗

finishing-a-development-branch

obra/superpowers · skills/finishing-a-development-branch/SKILL.md

obra/superpowers 的 finishing-a-development-branch 技能：当实现完成、所有测试通过，且需要决定如何整合这项工作时使用。

MIT查看原始说明 ↗

receiving-code-review

obra/superpowers · skills/receiving-code-review/SKILL.md

接收代码审查反馈时使用，在落实建议之前，尤其当反馈不清晰或技术上存疑时；要求技术严谨与验证，而非表面认同或盲目实施。

MIT查看原始说明 ↗

systematic-debugging

obra/superpowers · skills/systematic-debugging/SKILL.md

obra/superpowers 的系统化调试技能：遇到任何缺陷、测试失败或异常行为时，在提出修复方案之前使用。

MIT查看原始说明 ↗

test-driven-development

obra/superpowers · skills/test-driven-development/SKILL.md

obra/superpowers 的测试驱动开发技能：在实现任何功能或修复缺陷时使用，应在编写实现代码之前使用。

MIT查看原始说明 ↗

using-git-worktrees

obra/superpowers · skills/using-git-worktrees/SKILL.md

适用于需要与当前工作区隔离的功能开发，或在执行实施计划前使用；通过原生工具或 git worktree 回退确保存在隔离工作区。

MIT查看原始说明 ↗

using-superpowers

obra/superpowers · skills/using-superpowers/SKILL.md

适用于任何对话开始时，说明如何查找和使用技能，要求在做出任何回应（包括澄清提问）之前先调用技能。

MIT查看原始说明 ↗

verification-before-completion

obra/superpowers · skills/verification-before-completion/SKILL.md

在声称工作已完成、已修复或已通过，以及提交或创建 PR 之前使用；要求先运行验证命令并确认输出，再作成功声明，始终以证据为先。

MIT查看原始说明 ↗

academy-guide

anthropics/skills · skills/academy-guide/SKILL.md

在回答任何关于如何使用 Claude 或 Claude 产品的问题前，先检查此技能：它会推荐 Claude Academy（academy.claude.com，Anthropic 的学习中心）中匹配的课程、教程和用例。触发词包括“how do I”“how can I”“getting started with”“what can Claude do”“teach me”“learn to use”；涉及 artifacts、projects、skills、plugins、connectors、MCP 的问题；关于向团队、班级或组织推广 Claude 的请求；以及任何索取培训材料、入门内容或学习资源的请求。适用于用户正在学习如何使用某项功能或产品时。

Apache-2.0查看原始说明 ↗

algorithmic-art

anthropics/skills · skills/algorithmic-art/SKILL.md

使用p5.js创作算法艺术，支持种子随机与交互式参数探索。适用于用户要求用代码创作艺术、生成艺术、算法艺术、流场或粒子系统时。应创作原创算法艺术，而非复制现有艺术家作品，以避免版权侵权。

Apache-2.0查看原始说明 ↗

brand-guidelines

anthropics/skills · skills/brand-guidelines/SKILL.md

将 Anthropic 官方品牌配色与字体应用于任何需要体现 Anthropic 视觉风格的产物。当涉及品牌配色、风格指南、视觉排版或公司设计规范时使用。

Apache-2.0查看原始说明 ↗

canvas-design

anthropics/skills · skills/canvas-design/SKILL.md

使用设计理念在.png和.pdf文档中创作精美视觉艺术。当用户要求制作海报、艺术作品、设计或其他静态作品时使用此技能。创作原创视觉设计，不得复制现有艺术家作品以避免版权侵权。

Apache-2.0查看原始说明 ↗

claude-api

anthropics/skills · skills/claude-api/SKILL.md

Claude API 与 Anthropic SDK 参考：模型 ID、定价、参数、流式传输、工具调用、MCP、智能体、缓存、token 计数与模型迁移。触发条件：提示中任何形式提及 Claude/Anthropic，或用户询问 LLM 定价、模型选择、限制、缓存，或任务涉及未指明提供方的 LLM 场景时，应先阅读本参考，不要凭记忆回答。

Apache-2.0查看原始说明 ↗

discernment-nudge

anthropics/skills · skills/discernment-nudge/SKILL.md

在给出用户可能据以行动的实质性回答或草稿（如建议、目标、计划、提案、邮件、估算、数据分析或事实性论断）后、定稿前调用此技能，并视情况追加2至3个与内容具体相关的简短追问，帮助用户核查关键事实、检验推理与假设、发现缺失背景。每次对话最多一次；用户仅问简单操作时跳过。

Apache-2.0查看原始说明 ↗

frontend-design

anthropics/skills · skills/frontend-design/SKILL.md

用于构建新UI或重塑现有UI时提供独特且有意图的视觉设计指导，帮助把握美学方向、字体排版，避免呈现模板化默认风格。

Apache-2.0查看原始说明 ↗

internal-comms

anthropics/skills · skills/internal-comms/SKILL.md

一套用于撰写各类内部沟通材料的资源，采用公司偏好的格式。当被要求撰写状态报告、领导层更新、3P更新、公司通讯、FAQ、事故报告、项目更新等内部沟通内容时，Claude应使用此技能。

Apache-2.0查看原始说明 ↗

mcp-builder

anthropics/skills · skills/mcp-builder/SKILL.md

用于创建高质量 MCP（模型上下文协议）服务器的指南，使 LLM 能通过设计良好的工具与外部服务交互。适用于构建 MCP 服务器以集成外部 API 或服务，可使用 Python（FastMCP）或 Node/TypeScript（MCP SDK）。

Apache-2.0查看原始说明 ↗

skill-creator

anthropics/skills · skills/skill-creator/SKILL.md

创建新技能、修改和改进现有技能，并衡量技能表现。适用于用户想从零创建技能、编辑或优化现有技能、运行评估测试技能、通过方差分析对技能表现进行基准测试，或优化技能描述以提高触发准确性的场景。

Apache-2.0查看原始说明 ↗

slack-gif-creator

anthropics/skills · skills/slack-gif-creator/SKILL.md

用于创建适配 Slack 的动画 GIF 的知识与工具，提供约束、验证工具和动画概念。当用户请求为 Slack 制作动画 GIF 时使用。

Apache-2.0查看原始说明 ↗

theme-factory

anthropics/skills · skills/theme-factory/SKILL.md

用于为幻灯片、文档、报告、HTML落地页等制品设置主题样式的工具包。提供10个预设主题（含配色与字体），可应用于已创建的任意制品，也可即时生成新主题。

Apache-2.0查看原始说明 ↗

web-artifacts-builder

anthropics/skills · skills/web-artifacts-builder/SKILL.md

用于借助现代前端技术（React、Tailwind CSS、shadcn/ui）创建复杂多组件 claude.ai HTML 工件的工具套件，适用于需要状态管理、路由或 shadcn/ui 组件的复杂工件。

Apache-2.0查看原始说明 ↗

webapp-testing

anthropics/skills · skills/webapp-testing/SKILL.md

用于借助 Playwright 与本地 Web 应用交互并测试的工具包，支持验证前端功能、调试 UI 行为、截取浏览器截图和查看浏览器日志。

Apache-2.0查看原始说明 ↗

academic-cv

reactive-resume/reactive-resume · plugins/reactive-resume/skills/academic-cv/SKILL.md

Writes or updates academic CVs for research, postdoctoral, faculty and teaching appointments. Organizes publications, funding, teaching, mentoring and service with exact authorship and status; use a role resume skill for an industry resume rather than an academic record.

MIT查看原始说明 ↗

accomplishment-inventory

reactive-resume/reactive-resume · plugins/reactive-resume/skills/accomplishment-inventory/SKILL.md

通过访谈用户，建立可复用的真实成就、范围与证据库，供撰写简历使用。适用于用户记不清成就、绩效记录零散或缺少量化指标时；若任务已是改写具体简历条目，则改用 resume-bullet-writer。

MIT查看原始说明 ↗

application-answers

reactive-resume/reactive-resume · plugins/reactive-resume/skills/application-answers/SKILL.md

根据简历证据，在给定限制内起草求职申请短答、支持陈述和遴选标准回答，适用于“为何申请该职位”或“描述相关成就”等表单问题。

MIT查看原始说明 ↗

career-change-resume

reactive-resume/reactive-resume · plugins/reactive-resume/skills/career-change-resume/SKILL.md

为转行或跨行业求职撰写简历，涵盖军转民和重返职场转型。梳理可迁移证据，不重命名过往职位，不暗示未获得的专业能力；若需将已定位简历匹配单一职位，请使用 resume-tailor。

MIT查看原始说明 ↗

cover-letter-writer

reactive-resume/reactive-resume · plugins/reactive-resume/skills/cover-letter-writer/SKILL.md

根据用户经历和目标职位撰写或编辑求职信或申请邮件，适用于独立求职信，包括转行或重返职场的说明；若需同时定制简历和可选求职信，仍使用 resume-tailor 工作流。

MIT查看原始说明 ↗

customer-success-resume

reactive-resume/reactive-resume · plugins/reactive-resume/skills/customer-success-resume/SKILL.md

Writes customer success, implementation, onboarding and customer support resumes. Distinguishes adoption, renewals, expansion and support quality from sales claims, with honest portfolio and retention metrics.

MIT查看原始说明 ↗

data-resume

reactive-resume/reactive-resume · plugins/reactive-resume/skills/data-resume/SKILL.md

Writes data analyst, analytics engineer, data engineer, data scientist and machine-learning resumes. Connects methods and data products to decisions while distinguishing offline evaluation, experiments and production results; use academic-cv for an academic research record.

MIT查看原始说明 ↗

designer-resume

reactive-resume/reactive-resume · plugins/reactive-resume/skills/designer-resume/SKILL.md

Writes product design, UX/UI, user research, service design and visual design resumes. Connects research and craft to decisions and outcomes, with honest portfolio and accessibility claims; use portfolio-case-study for the longer project narrative.

MIT查看原始说明 ↗

educator-resume

reactive-resume/reactive-resume · plugins/reactive-resume/skills/educator-resume/SKILL.md

Writes school teaching, educational leadership, instructional design and learning-and-development resumes. Connects curriculum, facilitation and assessment to supported outcomes while preserving credential status and learner privacy; use academic-cv for faculty scholarship records.

MIT查看原始说明 ↗

entry-level-resume

reactive-resume/reactive-resume · plugins/reactive-resume/skills/entry-level-resume/SKILL.md

为首次求职者、学生、实习生、学徒和应届毕业生撰写简历，内容基于教育、项目、实习、志愿服务和兼职经历。适用于正式工作经验有限的情况；不得虚构工作经历、资质或项目成果。

MIT查看原始说明 ↗

executive-resume

reactive-resume/reactive-resume · plugins/reactive-resume/skills/executive-resume/SKILL.md

Writes director, VP, C-suite and board-candidate resumes from leadership scope, decisions and results. Distinguishes enterprise outcomes from personal ownership and operating roles from board service; use offer-negotiation for compensation rather than resume positioning.

MIT查看原始说明 ↗

fill-translations

reactive-resume/reactive-resume · .agents/skills/fill-translations/SKILL.md

使用并行子代理为 Reactive Resume 所有已配置的 Web 和移动端语言环境补全缺失翻译，并验证翻译目录完整性。适用于“填充翻译”“补全翻译”、缺失语言字符串，或发布前确保翻译完整的请求。除用户明确缩小范围外，应覆盖与当前任务无关的既有缺口。不适用于普通文本翻译或禁止编辑的只读审计。

MIT查看原始说明 ↗

finance-resume

reactive-resume/reactive-resume · plugins/reactive-resume/skills/finance-resume/SKILL.md

为会计、审计、FP&A、资金管理、银行和投资领域撰写简历，准确呈现财务范围、分析、控制与交易，并注明归属、币种和资质状态；不提供投资或执照建议。

MIT查看原始说明 ↗

healthcare-resume

reactive-resume/reactive-resume · plugins/reactive-resume/skills/healthcare-resume/SKILL.md

撰写护理、联合健康、临床支持及医疗行政类简历，确保执照、实习安排、临床范围和质量成果准确，并保护患者隐私；学术或研究任职记录请使用 academic-cv。

MIT查看原始说明 ↗

interview-prep

reactive-resume/reactive-resume · plugins/reactive-resume/skills/interview-prep/SKILL.md

Prepares the user for a specific interview from their real experience. Builds a story bank in Situation/Task/Action/Result/Reflection form mapped to the competencies the role and company test (such as Amazon's Leadership Principles), writes a cited company and role brief from public sources, predicts questions per round, drafts opener, why-us, weakness and salary answers, prepares questions to ask and a logistics checklist, and runs a post-interview debrief. Use when the user says "help me prepare for my interview", "I have an interview tomorrow" or "in 2 hours", "build my story bank", "STAR stories", "interviewing as a career changer", "what

MIT查看原始说明 ↗

job-application-manager

reactive-resume/reactive-resume · plugins/reactive-resume/skills/job-application-manager/SKILL.md

运行求职流程：通过链接或粘贴的招聘信息添加职位，准确维护阶段和日期，设置跟进，执行每周回顾（停滞申请、下一步行动、漏斗统计），记录所发送简历的确切版本，并起草人脉、LinkedIn、推荐、招聘者回复、跟进、感谢、状态查询、加急和撤回消息但不发送。适用于用户说“把这个职位加到我的追踪器”“我申请了”“记录我的面试”“我被拒了”“我被已读不回”“记录我的录用”“追踪我的申请”“做我的每周回顾”“我该跟进什么”“写一封感谢信”“给这个招聘者发消息”等场景。

MIT查看原始说明 ↗

linkedin-profile-writer

reactive-resume/reactive-resume · plugins/reactive-resume/skills/linkedin-profile-writer/SKILL.md

根据已核实的职业事实撰写LinkedIn标题、About部分和工作经历描述，使公开资料与简历保持一致。仅用于资料内容与定位，不涉及发帖计划、外联自动化或招聘排名承诺。

MIT查看原始说明 ↗

marketing-resume

reactive-resume/reactive-resume · plugins/reactive-resume/skills/marketing-resume/SKILL.md

撰写增长、绩效、品牌、生命周期、内容与传播类简历，将受众和渠道选择与有据可查的成果关联并明确归因；产品文档请改用 technical-writer-resume，而非营销内容。

MIT查看原始说明 ↗

mock-interview

reactive-resume/reactive-resume · plugins/reactive-resume/skills/mock-interview/SKILL.md

Runs a mock interview for a specific job description. Plays the interviewer in a chosen round (recruiter screen, hiring manager, behavioral, coding, system design, case, product sense, panel), persona and difficulty; asks one question at a time, probes vague answers, and gives quote-backed rubric scores after each answer (coach mode) or at the end (realistic). Model answers use only the user's real experience. Use when the user says "mock interview me", "interview me for this job", "practice interview", "pretend you're the interviewer", "grill me for this role", "run a behavioral round", "quick recruiter screen", "hiring-manager mock", "syste

MIT查看原始说明 ↗

offer-negotiation

reactive-resume/reactive-resume · plugins/reactive-resume/skills/offer-negotiation/SKILL.md

Evaluates and negotiates job offers. Decodes base, bonus, equity, sign-on, level and terms with unknowns kept unknown and each offer in its own currency, benchmarks against checkable pay data, finds true leverage, drafts one counter as email and call script, role-plays the recruiter, and handles the salary-expectations number, deadlines and extensions, "best and final", competing offers, counteroffers and written acceptance or decline. Country-aware (India CTC, 13th-month pay, public-sector scales). Use when the user says "I got an offer of...", "is this offer good", "should I negotiate", "how do I counter", "compare my offers", "what is my e

MIT查看原始说明 ↗

operations-resume

reactive-resume/reactive-resume · plugins/reactive-resume/skills/operations-resume/SKILL.md

为运营、供应链、物流、制造、维护、零售和酒店业撰写简历，将流程与服务性工作关联到吞吐量、质量、成本和安全，不虚构节省、资质或全站点功劳。

MIT查看原始说明 ↗

portfolio-case-study

reactive-resume/reactive-resume · plugins/reactive-resume/skills/portfolio-case-study/SKILL.md

Turns a real project or resume achievement into a portfolio case study or work-sample narrative. Use for design, product, engineering, data, marketing or writing portfolios where decisions, individual contribution and evidence matter;

MIT查看原始说明 ↗

product-manager-resume

reactive-resume/reactive-resume · plugins/reactive-resume/skills/product-manager-resume/SKILL.md

Writes product management resumes for associate, growth, platform, technical and senior product roles. Shows customer problems, prioritization, decisions and outcomes with accurate attribution; use project-manager-resume for delivery governance rather than product direction.

MIT查看原始说明 ↗

project-manager-resume

reactive-resume/reactive-resume · plugins/reactive-resume/skills/project-manager-resume/SKILL.md

Writes project, program, delivery and PMO resumes using scope, dependencies, risk, schedule and outcomes. Use for delivery leadership and coordination; use product-manager-resume when the main evidence is product discovery, prioritization and customer outcomes.

MIT查看原始说明 ↗

resume-builder

reactive-resume/reactive-resume · plugins/reactive-resume/skills/resume-builder/SKILL.md

Builds a complete resume as Reactive Resume JSON that conforms to the schema and imports at https://rxresu.me. Asks for missing facts, then produces valid JSON with UUIDs, HTML descriptions, template and layout. Use when the user requests importable JSON, creation in Reactive Resume, or help with its schema, sections, templates or layout. Use resume-writer for a general text draft, resume-content-guide for a content audit, resume-bullet-writer for bullets and resume-tailor for one posting.

MIT查看原始说明 ↗

resume-bullet-writer

reactive-resume/reactive-resume · plugins/reactive-resume/skills/resume-bullet-writer/SKILL.md

Turns resume duties into truthful impact bullets, asking for real evidence and preserving estimates. Use for rewriting bullets, quantifying achievements or improving an experience section, including work without numeric outcomes. With Reactive Resume MCP, edits descriptions after approval. Use accomplishment-inventory for a reusable evidence bank, resume-writer for a complete text draft or summary, resume-content-guide for what belongs, resume-tailor for one posting and resume-builder for JSON.

MIT查看原始说明 ↗

resume-content-guide

reactive-resume/reactive-resume · plugins/reactive-resume/skills/resume-content-guide/SKILL.md

提供简历内容建议：应包含与应省略的内容、板块顺序、篇幅、空档期、个人信息及国家或行业惯例；可在无具体职位时审查现有内容，适用于照片、GPA、出生日期、摘要或职业情况等问题。新文本草稿请用 resume-writer 或角色技能，编辑清理用 resume-proofreader，要点用 resume-bullet-writer，针对单一职位用 resume-tailor，JSON 用 resume-builder。基于粘贴文本或 Reactive Resume MCP 工作。

MIT查看原始说明 ↗

resume-proofreader

reactive-resume/reactive-resume · plugins/reactive-resume/skills/resume-proofreader/SKILL.md

校对简历、CV和求职信草稿的语法、清晰度、一致性和无依据措辞，同时保留事实与语气。适用于最终编辑或有限措辞修改；章节选择用resume-content-guide，职位匹配用resume-tailor。

MIT查看原始说明 ↗

resume-tailor

reactive-resume/reactive-resume · plugins/reactive-resume/skills/resume-tailor/SKILL.md

Tailors one resume to one specific job posting. Builds a must-have/nice-to-have requirement table, an evidence map, gap questions instead of invention, a tailored copy (headline, summary, bullet order, skills), honest ATS guidance, and an optional cover letter for that posting. Use when the user says "tailor my resume to this job", "customize my CV for this posting", "match my resume to this job description", "what keywords am I missing", "make my resume ATS-friendly for this role", "will this get past the ATS", "the job asks for X and I don't have it", or pastes a job ad with a resume. Works from pasted text; uses Reactive Resume MCP tools w

MIT查看原始说明 ↗

resume-writer

reactive-resume/reactive-resume · plugins/reactive-resume/skills/resume-writer/SKILL.md

根据工作经历、笔记或现有草稿，撰写或重写完整简历，输出可直接复制的文本，也可单独撰写标题和摘要。适用于无特定职位招聘的通用简历草稿；如需Reactive Resume JSON请用resume-builder，针对单一职位请用resume-tailor。

MIT查看原始说明 ↗

sales-resume

reactive-resume/reactive-resume · plugins/reactive-resume/skills/sales-resume/SKILL.md

Writes SDR, BDR, account executive, account management, sales engineering and sales leadership resumes. Presents quota, pipeline, deals and customer outcomes with correct periods and ownership; use customer-success-resume for post-sale adoption and retention work.

MIT查看原始说明 ↗

software-engineer-resume

reactive-resume/reactive-resume · plugins/reactive-resume/skills/software-engineer-resume/SKILL.md

为前端、后端、全栈、移动、平台、DevOps、SRE 和安全工程岗位撰写软件工程简历，强调技术决策、交付系统与可辩护的影响；分析与模型类工作请用 data-resume，针对单一职位请用 resume-tailor。

MIT查看原始说明 ↗

technical-writer-resume

reactive-resume/reactive-resume · plugins/reactive-resume/skills/technical-writer-resume/SKILL.md

撰写技术写作、文档工程、API写作和知识管理类简历，展示受众分析、信息设计、技术准确性和可用作品样例；营销推广内容请用marketing-resume，完整写作样例叙述请用portfolio-case-study。

MIT查看原始说明 ↗

vercel-composition-patterns

vercel-labs/agent-skills · skills/composition-patterns/SKILL.md

React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.

MIT查看原始说明 ↗

vercel-react-best-practices

vercel-labs/agent-skills · skills/react-best-practices/SKILL.md

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

MIT查看原始说明 ↗

vercel-react-native-skills

vercel-labs/agent-skills · skills/react-native-skills/SKILL.md

React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.

MIT查看原始说明 ↗

vercel-react-view-transitions

vercel-labs/agent-skills · skills/react-view-transitions/SKILL.md

Guide for implementing smooth, native-feeling animations using React's View Transition API (`<ViewTransition>` component, `addTransitionType`, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter/exit of components, animate list reorder, implement directional (forward/back) navigation animations, or integrate view transitions in Next.js. Also use when the user mentions view transitions, `startViewTransition`, `ViewTransition`, transition types, or asks about animating between UI states in React without third-party animat

MIT查看原始说明 ↗

aspnet-core

openai/skills · skills/.curated/aspnet-core/SKILL.md

Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.

Apache-2.0查看原始说明 ↗

chatgpt-apps

openai/skills · skills/.curated/chatgpt-apps/SKILL.md

Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.

Apache-2.0查看原始说明 ↗

cli-creator

openai/skills · skills/.curated/cli-creator/SKILL.md

Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.

Apache-2.0查看原始说明 ↗

cloudflare-deploy

openai/skills · skills/.curated/cloudflare-deploy/SKILL.md

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.

Apache-2.0查看原始说明 ↗

define-goal

openai/skills · skills/.curated/define-goal/SKILL.md

Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refinement only; it does not manage durable snapshots, decision logs, or long-running execution artifacts.

Apache-2.0查看原始说明 ↗

gh-address-comments

openai/skills · skills/.curated/gh-address-comments/SKILL.md

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.

Apache-2.0查看原始说明 ↗

gh-fix-ci

openai/skills · skills/.curated/gh-fix-ci/SKILL.md

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

Apache-2.0查看原始说明 ↗

hatch-pet

openai/skills · skills/.curated/hatch-pet/SKILL.md

Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.

Apache-2.0查看原始说明 ↗

imagegen

openai/skills · skills/.system/imagegen/SKILL.md

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector.

Apache-2.0查看原始说明 ↗

jupyter-notebook

openai/skills · skills/.curated/jupyter-notebook/SKILL.md

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.

Apache-2.0查看原始说明 ↗

linear

openai/skills · skills/.curated/linear/SKILL.md

Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear.

Apache-2.0查看原始说明 ↗

migrate-to-codex

openai/skills · skills/.curated/migrate-to-codex/SKILL.md

Migrate supported instruction files, skills, agents, and MCP config into Codex project and global files.

Apache-2.0查看原始说明 ↗

netlify-deploy

openai/skills · skills/.curated/netlify-deploy/SKILL.md

Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys.

Apache-2.0查看原始说明 ↗

openai-docs

openai/skills · skills/.curated/openai-docs/SKILL.md

Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.

Apache-2.0查看原始说明 ↗

openai-docs

openai/skills · skills/.system/openai-docs/SKILL.md

Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.

Apache-2.0查看原始说明 ↗

pdf

openai/skills · skills/.curated/pdf/SKILL.md

Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks by rendering pages (Poppler) and use Python tools such as `reportlab`, `pdfplumber`, and `pypdf` for generation and extraction.

Apache-2.0查看原始说明 ↗

playwright

openai/skills · skills/.curated/playwright/SKILL.md

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.

Apache-2.0查看原始说明 ↗

plugin-creator

openai/skills · skills/.system/plugin-creator/SKILL.md

Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can edit before publishing or testing. Use when Codex needs to create a new local plugin, add optional plugin structure, or generate or update repo-root `.agents/plugins/marketplace.json` entries for plugin ordering and availability metadata.

Apache-2.0查看原始说明 ↗

render-deploy

openai/skills · skills/.curated/render-deploy/SKILL.md

Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Use when the user wants to deploy, host, publish, or set up their application on Render's cloud platform.

Apache-2.0查看原始说明 ↗

screenshot

openai/skills · skills/.curated/screenshot/SKILL.md

Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.

Apache-2.0查看原始说明 ↗

security-best-practices

openai/skills · skills/.curated/security-best-practices/SKILL.md

Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks.

Apache-2.0查看原始说明 ↗

security-ownership-map

openai/skills · skills/.curated/security-ownership-map/SKILL.md

Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for example: orphaned sensitive code, security maintainers, CODEOWNERS reality checks for risk, sensitive hotspots, or ownership clusters). Do not trigger for general maintainer lists or non-security ownership questions.

Apache-2.0查看原始说明 ↗

security-threat-model

openai/skills · skills/.curated/security-threat-model/SKILL.md

Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.

Apache-2.0查看原始说明 ↗

sentry

openai/skills · skills/.curated/sentry/SKILL.md

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry CLI; perform read-only queries using the `sentry` command.

Apache-2.0查看原始说明 ↗

skill-creator

openai/skills · skills/.system/skill-creator/SKILL.md

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Apache-2.0查看原始说明 ↗

skill-installer

openai/skills · skills/.system/skill-installer/SKILL.md

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Apache-2.0查看原始说明 ↗

speech

openai/skills · skills/.curated/speech/SKILL.md

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.

Apache-2.0查看原始说明 ↗

transcribe

openai/skills · skills/.curated/transcribe/SKILL.md

Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.

Apache-2.0查看原始说明 ↗

vercel-deploy

openai/skills · skills/.curated/vercel-deploy/SKILL.md

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

MIT查看原始说明 ↗

winui-app

openai/skills · skills/.curated/winui-app/SKILL.md

Bootstrap, develop, and design modern WinUI 3 desktop applications with C# and the Windows App SDK using official Microsoft guidance, WinUI Gallery patterns, Windows App SDK samples, and CommunityToolkit components. Use when creating a brand new app, preparing a machine for WinUI, reviewing, refactoring, planning, troubleshooting, environment-checking, or setting up WinUI 3 XAML, controls, navigation, windowing, theming, accessibility, responsiveness, performance, deployment, or related Windows app design and development work.

Apache-2.0查看原始说明 ↗

yeet

openai/skills · skills/.curated/yeet/SKILL.md

Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).

Apache-2.0查看原始说明 ↗

alert-mute-copilot

ccfos/nightingale · aiagent/skill/embedded/builtin/alert-mute-copilot/SKILL.md

One-stop assistant for creating, editing, and troubleshooting Nightingale (n9e) alert mute rules (alert_mute). Use it when the user asks to "create a mute rule / mute an alert / silence an alert / do-not-disturb during a maintenance window / set up periodic muting / mute every early morning / adjust or extend a mute / troubleshoot why a mute isn't working". Muting takes effect during the event evaluation stage (muted events are neither persisted nor notified); to configure "which events get notified to whom", use notification rules (→ notify-rule-copilot); to investigate "why didn't I get a notification", go to alert troubleshooting (→ alert-

Apache-2.0查看原始说明 ↗

alert-rule-troubleshoot

ccfos/nightingale · aiagent/skill/embedded/builtin/alert-rule-troubleshoot/SKILL.md

This skill should be used when the user reports that an alert rule is "not firing", "no alert was sent", "the rule didn't trigger", "the rule isn't working", "it should have alerted but didn't", "why didn't I get an alert", "alert rule not firing", or wants to diagnose why a specific alert rule failed to produce an event/notification. Use this skill to troubleshoot "why an alert rule did not fire as expected", as opposed to taking an existing alert and finding its root cause (for the latter, use ops-troubleshooting). Only supported on Release 22 and above.

Apache-2.0查看原始说明 ↗

alert-subscribe-copilot

ccfos/nightingale · aiagent/skill/embedded/builtin/alert-subscribe-copilot/SKILL.md

One-stop assistant for creating, editing, and troubleshooting Nightingale (n9e) alert subscription rules (alert_subscribe). Use when the user asks to "create a subscription rule / subscribe to alerts / forward alert events / CC another team / escalate alerts (notify someone else after N minutes unhandled) / receive alerts across business groups / troubleshoot a subscription not taking effect". A subscription is a "copy + secondary routing" of events at the notification stage; to configure "who an event directly notifies" use notification rules (→ notify-rule-copilot), and to stop receiving alerts use muting (→ alert-mute-copilot).

Apache-2.0查看原始说明 ↗

analyze-dashboard

ccfos/nightingale · aiagent/skill/embedded/builtin/analyze-dashboard/SKILL.md

Analyze the data health of a given dashboard on Nightingale (n9e) over a time window. Use when the user asks to "analyze what problems a dashboard has", "check whether the xx dashboard has been normal over the last 24 hours", "inspect this dashboard", or "does this dashboard have any anomalies". Distinct from modifying a dashboard (modify-dashboard) and creating a dashboard (create-dashboard).

Apache-2.0查看原始说明 ↗

categraf-deploy-guide

ccfos/nightingale · aiagent/skill/embedded/builtin/categraf-deploy-guide/SKILL.md

Answers "how do I deploy the categraf collector". Trigger scenarios: the user asks "how to install categraf / how to deploy categraf / run categraf with Docker / install categraf on Windows / how to register categraf as a system service / report categraf to Nightingale / how to write categraf config.toml / how to verify that categraf is collecting data". Covers binary + systemd, Docker, Windows, K8s tips, key configuration, and common verification commands. This skill is instructional/guidance-oriented, calls no tools, and outputs ready-to-paste commands and configuration snippets.

Apache-2.0查看原始说明 ↗

create-alert-rule

ccfos/nightingale · aiagent/skill/embedded/builtin/create-alert-rule/SKILL.md

**Create alert rules**. Prefer reusing the validated rules in integrations (standard components like Linux/MySQL/Redis/Kafka/PostgreSQL/Elasticsearch all ship ready-made rule packs); import as many rules as the user needs—one rule, a batch, or a whole pack. Only hand-write a custom rule when integrations has nothing that fits. Supports all data sources: Prometheus / Loki / ES / OpenSearch / MySQL / PG / TDengine / ClickHouse / Doris / VictoriaLogs / Host. ⚠️ **

Apache-2.0查看原始说明 ↗

create-dashboard

ccfos/nightingale · aiagent/skill/embedded/builtin/create-dashboard/SKILL.md

Create monitoring dashboards. Use this when the user asks to create a dashboard, a monitoring board, or a Dashboard.

Apache-2.0查看原始说明 ↗

doc-qa

ccfos/nightingale · aiagent/skill/embedded/builtin/doc-qa/SKILL.md

This skill should be used when the user asks "how-to" or factual questions about Nightingale (n9e) — UI/where-to-click, business groups/subscription rules/mute rules/edge mode, Token usage, notification pipeline, self-healing trigger conditions; OR about categraf input plugin field meanings, metric names, defaults, environment variables, config syntax (e.g. "how to write [[instances]]", "unit of ping_average_response_ms"); OR about the n9e / categraf / fe source code — this skill carries an embedded, searchable snapshot of the three repositories, so use it whenever the user asks "can you read the source code / the code directory", or asks how

Apache-2.0查看原始说明 ↗

explorer-query

ccfos/nightingale · aiagent/skill/embedded/builtin/explorer-query/SKILL.md

Use when the user wants to generate, repair, validate, or prepare a query for the current Nightingale Metrics Explorer or Log Explorer panel. Supports PromQL for Prometheus-compatible datasources, SQL for MySQL and Doris, and Doris log queries. Verify the statement against the selected datasource before returning it. Use query-datasource when the user only wants to view data rather than prepare a statement for an editor.

Apache-2.0查看原始说明 ↗

generate-message-template

ccfos/nightingale · aiagent/skill/embedded/builtin/generate-message-template/SKILL.md

Generate or modify Nightingale (n9e) alert notification message templates. Use when the user asks to write a notification template, change the message format, add hostname/recovery value/severity, or create DingTalk/Feishu/Lark/email/SMS/voice templates.

Apache-2.0查看原始说明 ↗

host-health-diagnose

ccfos/nightingale · aiagent/skill/embedded/builtin/host-health-diagnose/SKILL.md

Help the user determine whether a machine is truly down / the agent is hung / the network is flapping / it is under maintenance. Triggers this skill when the user asks "why is this machine unreachable", "is the host-unreachable alert a false positive", "is categraf stuck", "the heartbeat stopped but I can still ping it", etc. Core stance: **an unreachable agent != a down host**. Concluding "down" just because target_up==0 / BeatTime stopped is a common source of false positives.

Apache-2.0查看原始说明 ↗

host-onboard-diagnose

ccfos/nightingale · aiagent/skill/embedded/builtin/host-onboard-diagnose/SKILL.md

Diagnose onboarding failures where "categraf is installed/running but the host does not show up in the Nightingale host list, or shows unknown / has no metrics". Triggers when the user asks "why doesn't my newly installed host appear", "all the OS values in the host list are unknown", "I installed 3 collectors via Helm but only see 1", "the agent won't register", or "categraf is installed but the host doesn't show". **Mutually exclusive** with host-health-diagnose: that one handles "was onboarded before, now lost contact", while this skill handles "never got onboarded at all". Core stance: **a missing host is not a single cause, but rather on

Apache-2.0查看原始说明 ↗

import-prom-rule

ccfos/nightingale · aiagent/skill/embedded/builtin/import-prom-rule/SKILL.md

**Bulk import of a Prometheus alert rule YAML file** (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats `groups` / a plain `rules` array / a single rule. ⚠️ **

Apache-2.0查看原始说明 ↗

modify-dashboard

ccfos/nightingale · aiagent/skill/embedded/builtin/modify-dashboard/SKILL.md

Modify an existing monitoring dashboard on Nightingale (n9e). Use when the user asks to change a dashboard's variables, check and fix variables, modify charts/series (change PromQL, legend, unit, add/remove series), rename a chart, or change the chart type (e.g., turn a stat chart into a timeseries chart). Distinct from "creating a dashboard from scratch" (that is create-dashboard).

Apache-2.0查看原始说明 ↗

modify-task-tpl

ccfos/nightingale · aiagent/skill/embedded/builtin/modify-task-tpl/SKILL.md

Helps users generate, modify, or troubleshoot Nightingale (n9e) alert self-healing scripts (task_tpl / ibex scripts). Use when the user asks to "write a self-healing script for disk cleanup / restarting a service / cleaning logs / dumping a process / reloading nginx", or asks "how does a self-healing script get the parameters passed from the alert", "what format is stdin in", "what should I set timeout to", "why is is_recovered always false", "why can't my self-healing script get the k8s namespace", "what do I do when a script stays running forever". This skill focuses on the **script body layer**—if the user wants to change alert rules, reci

Apache-2.0查看原始说明 ↗

notify-channel-copilot

ccfos/nightingale · aiagent/skill/embedded/builtin/notify-channel-copilot/SKILL.md

Helps users modify, create, or troubleshoot Nightingale (n9e) notify channels (notify_channel). Use it when the user asks to change the URL, request body, signature, headers, proxy, TLS, @-mentions, or recipient fields of channels such as DingTalk/Feishu/WeCom/email/SMS/voice/Webhook, or asks "how do I integrate platform X" or "why can't it send / why am I getting 9499 / Bad Request". This skill focuses on **the channel-layer configuration**—if the user is changing "message content/fields/rendering", switch to generate-message-template instead.

Apache-2.0查看原始说明 ↗

notify-rule-copilot

ccfos/nightingale · aiagent/skill/embedded/builtin/notify-rule-copilot/SKILL.md

One-stop assistant for creating, editing, copying, and troubleshooting Nightingale (n9e) notify rules (notify_rule). Use it when the user asks to "create a notify rule / add a notification policy / configure how alerts are delivered / edit and adjust a notify rule / tiered notification / route by business group or label / take different actions during vs. outside working hours / don't call on recovery / fix a rule that isn't matching" — it is especially good at decomposing natural-language routing requirements into a correct NotifyConfig array. This skill focuses on the routing layer of notify rules: it does not touch the notification media t

Apache-2.0查看原始说明 ↗

ops-troubleshooting

ccfos/nightingale · aiagent/skill/embedded/builtin/ops-troubleshooting/SKILL.md

This skill should be used when the user asks to "troubleshoot", "diagnose", "debug alert", "investigate incident", "locate a fault", "investigate an alert", "diagnose a problem", "fix an issue", "check alerts", "analyze alerts", "root cause analysis", "check metrics", "check logs", or discusses monitoring/alerting/observability issues in the Nightingale (n9e) platform.

Apache-2.0查看原始说明 ↗

query-alert-events

ccfos/nightingale · aiagent/skill/embedded/builtin/query-alert-events/SKILL.md

Query alert events in a Nightingale (n9e) environment. Use this when the user asks to view alerts, query active alerts, search historical alerts, view alert details, or count alert events.

Apache-2.0查看原始说明 ↗

query-datasource

ccfos/nightingale · aiagent/skill/embedded/builtin/query-datasource/SKILL.md

Query data from various datasources in a Nightingale (n9e) environment. Supports Prometheus metric queries, Elasticsearch/Loki log queries, and SQL datasource queries such as ClickHouse/MySQL/PostgreSQL/TDengine/Doris. Use when the user asks to query metrics, view monitoring data, search logs, or run PromQL or SQL queries.

Apache-2.0查看原始说明 ↗

skill-creator

ccfos/nightingale · aiagent/skill/embedded/builtin/skill-creator/SKILL.md

Create/edit Nightingale AI Skills. Use when the user wants to create a new skill, codify a troubleshooting or operations workflow into a reusable skill, build a skill that can run scripts (Python/Bash), or modify/improve/optimize an existing self-built skill. Use this skill whenever the user says things like "make a skill", "save this workflow as a skill", "teach the AI a new trick", "tweak that skill of mine", "let the AI learn to troubleshoot following these steps", etc.

Apache-2.0查看原始说明 ↗

页面展示前 120 条。使用上方搜索查找完整目录。