本仓库用于集中维护本地 skills/，并一键软链到常用编码代理目录（cc/codex/gemini）。
- 技能目录：
./skills - 映射文件：
./skills-map.txt - 同步脚本：
./scripts/sync-skills.js - Agent memory：
./memory/AGENTS.md - Claude Code 脚手架：
./.claude/
# 1) 按映射同步远程 skills 到本地 ./skills
npm run sync:skills
# 2) 一键把本仓库 skills 软链到 cc + codex + gemini
npm run link:skills
# 3) 仅链接 Gemini CLI
npm run link:gemini
# 4) 同步仓库级 agent memory 到 Claude/Codex/Gemini
npm run sync:memory
# 5) 运行当前仓库最小质量门
npm run validate:repo# 1) 按映射同步远程 skills 到本地 ./skills
node ./scripts/sync-skills.js
# 2) 一键把本仓库 skills 软链到 cc + codex + gemini
node ./scripts/link-skills.js
# 3) 仅链接 Gemini CLI
node ./scripts/link-skills.js gemini
# 4) 同步仓库级 agent memory 到 Claude/Codex/Gemini
node ./scripts/sync-agent-memory.js
# 5) 运行当前仓库最小质量门
node ./scripts/validate-repo.js💡 跨平台使用：仓库自维护脚本已统一为 Node.js，执行这些命令不再依赖本机 Python。
sync:memory现在会直接创建文件链接，修改源memory/AGENTS.md后目标文件会同步反映。
memory/AGENTS.md是仓库级 agent memory 的单一事实来源；需要同步到本机的 Claude Code、Codex、Gemini CLI 时，统一执行npm run sync:memory。该命令会直接创建文件链接，而不是复制内容。.claude/提供了从tele-backend提炼并适配后的轻量 Claude Code 脚手架，包括：settings.example.json：项目级权限与 hook 示例hooks/：通用风险拦截与 prompt 提示commands/repo-validate.md：把仓库验证流程固化为 Claude Code 命令
- 详细说明见
.claude/README.md。
以下表格对齐 vercel-labs/skills 的 Agent 目录约定（来源见文末链接）。
| Agent | --agent |
Project Path | Global Path |
|---|---|---|---|
| Amp, Kimi Code CLI, Replit, Universal | amp, kimi-cli, replit, universal |
.agents/skills/ |
~/.config/agents/skills/ |
| Antigravity | antigravity |
.agent/skills/ |
~/.gemini/antigravity/skills/ |
| Augment | augment |
.augment/skills/ |
~/.augment/skills/ |
| Claude Code | claude-code |
.claude/skills/ |
~/.claude/skills/ |
| OpenClaw | openclaw |
skills/ |
~/.openclaw/skills/ |
| Cline | cline |
.agents/skills/ |
~/.agents/skills/ |
| CodeBuddy | codebuddy |
.codebuddy/skills/ |
~/.codebuddy/skills/ |
| Codex | codex |
.agents/skills/ |
~/.codex/skills/ |
| Command Code | command-code |
.commandcode/skills/ |
~/.commandcode/skills/ |
| Continue | continue |
.continue/skills/ |
~/.continue/skills/ |
| Cortex Code | cortex |
.cortex/skills/ |
~/.snowflake/cortex/skills/ |
| Crush | crush |
.crush/skills/ |
~/.config/crush/skills/ |
| Cursor | cursor |
.agents/skills/ |
~/.cursor/skills/ |
| Droid | droid |
.factory/skills/ |
~/.factory/skills/ |
| Gemini CLI | gemini-cli |
.agents/skills/ |
~/.gemini/skills/ |
| GitHub Copilot | github-copilot |
.agents/skills/ |
~/.copilot/skills/ |
| Goose | goose |
.goose/skills/ |
~/.config/goose/skills/ |
| Junie | junie |
.junie/skills/ |
~/.junie/skills/ |
| iFlow CLI | iflow-cli |
.iflow/skills/ |
~/.iflow/skills/ |
| Kilo Code | kilo |
.kilocode/skills/ |
~/.kilocode/skills/ |
| Kiro CLI | kiro-cli |
.kiro/skills/ |
~/.kiro/skills/ |
| Kode | kode |
.kode/skills/ |
~/.kode/skills/ |
| MCPJam | mcpjam |
.mcpjam/skills/ |
~/.mcpjam/skills/ |
| Mistral Vibe | mistral-vibe |
.vibe/skills/ |
~/.vibe/skills/ |
| Mux | mux |
.mux/skills/ |
~/.mux/skills/ |
| OpenCode | opencode |
.agents/skills/ |
~/.config/opencode/skills/ |
| OpenHands | openhands |
.openhands/skills/ |
~/.openhands/skills/ |
| Pi | pi |
.pi/skills/ |
~/.pi/agent/skills/ |
| Qoder | qoder |
.qoder/skills/ |
~/.qoder/skills/ |
| Qwen Code | qwen-code |
.qwen/skills/ |
~/.qwen/skills/ |
| Roo Code | roo |
.roo/skills/ |
~/.roo/skills/ |
| Trae | trae |
.trae/skills/ |
~/.trae/skills/ |
| Trae CN | trae-cn |
.trae/skills/ |
~/.trae-cn/skills/ |
| Windsurf | windsurf |
.windsurf/skills/ |
~/.codeium/windsurf/skills/ |
| Zencoder | zencoder |
.zencoder/skills/ |
~/.zencoder/skills/ |
| Neovate | neovate |
.neovate/skills/ |
~/.neovate/skills/ |
| Pochi | pochi |
.pochi/skills/ |
~/.pochi/skills/ |
| AdaL | adal |
.adal/skills/ |
~/.adal/skills/ |
以下清单按仓库中实际存在的公共 skills/*/SKILL.md 整理，不包含 .system 内置 skill。名称可直接跳转到对应说明文件。
| 名称 | 作用简介 |
|---|---|
| active-directory-attacks | This skill should be used when the user asks to "attack Active Directory", "e...。 |
| ad-creative | 批量生成和迭代付费广告文案素材。 |
| agile-product-owner | 编写用户故事、验收标准与迭代计划的敏捷产品管理。 |
| analytics-tracking | 搭建、审计和排查 GA4/GTM 等埋点与转化追踪。 |
| android-accessibility | 审核并修复 Android 尤其是 Jetpack Compose 的无障碍问题。 |
| android-architecture | 设计基于 Clean Architecture 与 Hilt 的现代 Android 架构。 |
| android-coroutines | 在 Android 中落地高质量 Kotlin 协程与结构化并发。 |
| android-design-guidelines | Material Design 3 and Android platform guidelines。 |
| android-emulator-skill | 用于 Android 构建、测试、自动化和模拟器管理的脚本集。 |
| android-testing | 为 Android 应用建立单测、集成、Hilt 与截图测试策略。 |
| anti-reversing-techniques | 分析反调试、混淆与软件保护技术。 |
| api-fuzzing-bug-bounty | This skill should be used when the user asks to "test API security", "fuzz AP...。 |
| apktool | Android APK unpacking and resource extraction tool for reverse engineering。 |
| app-store-changelog | Create user-facing App Store release notes by collecting and summarizing all...。 |
| app-store-optimization | 进行 ASO 关键词研究、元数据优化与商店表现提升。 |
| apple-appstore-reviewer | 从 App Store 优化与拒审风险角度审查代码库。 |
| apple-notes | 通过 memo CLI 管理 macOS Apple Notes。 |
| apple-reminders | 通过 remindctl 管理 Apple Reminders 任务。 |
| arch-linux-triage | 排查和处理 Arch Linux 上的 pacman、systemd 等问题。 |
| architecture-blueprint-generator | 自动分析代码库并生成架构蓝图与文档。 |
| architecture-diagram | Generate detailed layered architecture diagrams as self-contained HTML artifa...。 |
| architecture-reviewer | Architecture reviews across 7 dimensions: structural integrity, scalability,...。 |
| arthas-cpu-high | 排查 JVM / 应用 CPU 飙高（线程定位 + 代码路径分析）。 |
| arthas-springcontext-issues-resolve | 排查 Spring ApplicationContext / Bean / 配置注入等问题。 |
| async-python-patterns | 构建高性能 Python asyncio 并发与异步模式。 |
| attack-tree-construction | 构建攻击树以梳理威胁路径与防御缺口。 |
| author-contributions | 追踪某作者在分支上的文件贡献及重命名历史。 |
| backend-to-frontend-handoff-docs | Create API handoff documentation for frontend developers。 |
| baoyu-article-illustrator | 为文章识别配图点并生成插图方案。 |
| baoyu-compress-image | 压缩图片并转换为 WebP/PNG。 |
| benchmark-runner | Designs structured benchmarks for comparing algorithms, models, or implementa...。 |
| binary-analysis-patterns | 进行反汇编、反编译和控制流等二进制静态分析。 |
| blue-ocean-strategy | Create uncontested market space using value innovation instead of competing h...。 |
| branch-naming-helper | Configure with branch naming helper operations. Auto-activating skill for Dev...。 |
| broken-authentication | This skill should be used when the user asks to "test for broken authenticati...。 |
| browser-use | Automates browser interactions for web testing, form filling, screenshots, an...。 |
| brutal-honesty-review | Unvarnished technical criticism combining Linus Torvalds' precision, Gordon R...。 |
| business-model | 生成包含九宫格要素的商业模式画布。 |
| campaign-analytics | 分析营销活动归因、漏斗和 ROI。 |
| canvas-design | 生成原创静态视觉设计、海报或艺术作品。 |
| centos-linux-triage | 处理 CentOS/RHEL 兼容环境下的系统问题。 |
| chipsec | Static analysis of UEFI/BIOS firmware dumps using Intel's chipsec framework....。 |
| chrome-devtools | 通过 Chrome DevTools MCP 做浏览器自动化、调试与性能分析。 |
| code-refiner | Deep code simplification, refactoring, and quality refinement. Analyzes struc...。 |
| competitive-ads-extractor | Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn,...。 |
| competitive-intelligence | Research your competitors and build an interactive battlecard. Outputs an HTM...。 |
| competitive-teardown | 产出竞品拆解、对比矩阵、SWOT 与定位分析。 |
| competitor-alternatives | 编写竞品对比页与替代页，用于 SEO 和销售辅助。 |
| concept-to-image | Turn any concept, idea, or description into a polished static HTML visual, th...。 |
| concept-to-video | Turn any concept into an animated explainer video using Manim (Python). Use w...。 |
| consciousness-council | 以多角色视角对复杂问题进行委员会式讨论。 |
| consulting-analysis | 先搭分析框架再生成咨询级研究报告。 |
| content-humanizer | 把 AI 文案改写得更自然、更像真人表达。 |
| content-strategy | 规划内容策略、主题集群与内容路线图。 |
| context-map | 改动前梳理与任务相关的文件地图。 |
| copy-editing | 对现有营销文案做多轮编辑、润色与校对。 |
| core-web-vitals | Optimize Core Web Vitals (LCP, INP, CLS) for better page experience and searc...。 |
| create-github-action-workflow-specification | Create a formal specification for an existing GitHub Actions CI/CD workflow,...。 |
| create-prd | 用 8 部分模板编写产品需求文档。 |
| creating-financial-models | 构建 DCF、敏感性分析与情景模拟等财务模型。 |
| cro-methodology | Audit websites and landing pages for conversion issues and design evidence-ba...。 |
| cross-pollination-engine | 借鉴不同行业的方法，为问题寻找跨界解法。 |
| crossing-the-chasm | Navigate the technology adoption lifecycle from early adopters to mainstream...。 |
| customer-journey-map | 绘制用户旅程，梳理触点、情绪与机会点。 |
| data-analysis | 分析 Excel/CSV 数据，支持汇总、透视、SQL 和导出。 |
| data-storytelling | 把数据结果组织成面向管理层的叙事和呈现。 |
| data-visualization | Create effective data visualizations with Python (matplotlib, seaborn, plotly)。 |
| ddia-systems | Design data systems by understanding storage engines, replication, partitioni...。 |
| debian-linux-triage | 排查 Debian 上的 apt、systemd 和 AppArmor 问题。 |
| debug-investigator | Hypothesis-driven debugging methodology: ranked hypotheses with confirming/re...。 |
| debug-lldb | Capture and analyze thread backtraces with LLDB/GDB to debug hangs, deadlocks...。 |
| deep-research | 在联网任务中做多轮深度研究，而不是浅层搜索。 |
| design-system-patterns | 设计和实现可扩展的设计系统、token 与主题机制。 |
| designing-growth-loops | Help users design and optimize growth loops。 |
| designing-surveys | Help users design effective surveys。 |
| detox-mobile-test | Эксперт Detox тестирования. Используй для React Native E2E tests и mobile aut...。 |
| dhdna-profiler | 从文本中提取认知风格与思维特征。 |
| disk-cleanup | Use when disk space is low, the user wants to free space, or needs to find wh...。 |
| doc-coauthoring | 引导用户协作式编写文档、提案和技术说明。 |
| docker-essentials | 提供常用 Docker 容器、镜像与排障工作流。 |
| doctrine-batch-processing | Evolve Symfony Doctrine models and schema safely with integrity, performance,...。 |
| docx | 读取、创建和编辑 Word .docx 文档。 |
| domain-name-brainstormer | 生成域名创意并检查多种后缀可用性。 |
| douyin-video-summary | Summarize Douyin (TikTok China) videos by extracting audio, transcribing with...。 |
| douyin-viral-content | 抖音爆款文案智能生成器。当用户说"生成新文案"、"创作抖音内容"、"写短视频文案"时自动触发。自动执行：(1) 读取历史数据分析 (2) 应用9大爆款要素...。 |
| embedding-strategies | 为语义检索/RAG 选择并优化向量嵌入方案。 |
| employment-contract-templates | 编写雇佣合同、offer 和 HR 政策模板。 |
| engineering-retro | Git-based engineering retrospective analyzing commit history, PR patterns, an...。 |
| enterprise-proposal | Create comprehensive, BCG/McKinsey-style enterprise proposals with profession...。 |
| error-handling-patterns | Master error handling patterns across languages including exceptions, Result...。 |
| estimate-calibrator | Produces calibrated three-point estimates (best/likely/worst case) with expli...。 |
| ethical-hacking-methodology | This skill should be used when the user asks to "learn ethical hacking", "und...。 |
| evaluating-new-technology | Help users evaluate emerging technologies。 |
| exhaustive-systems-analysis | Perform comprehensive, deep analysis of a system and its subsystems to identi...。 |
| fan-operations | Use when growing Xiaohongshu following, engaging with audience, building comm...。 |
| feature-dev | Feature Development Workflow - 7-phase structured approach for building featu...。 |
| figma-implement-design | 按 Figma 设计上下文高保真实现页面或组件。 |
| file-path-traversal | This skill should be used when the user asks to "test for directory traversal...。 |
| financial-analyst | 做财务比率、估值、预算偏差和滚动预测分析。 |
| find-skills | Helps users discover and install agent skills when they ask questions like "h...。 |
| first-principles-decomposer | 用第一性原理拆解问题并重建方案。 |
| frontend-design-review | 审查或设计高质量前端界面，兼顾美感、可用性与设计系统。 |
| fundraise-advisor | Use this skill when users need to raise funding, create a pitch deck, prepare...。 |
| funnel-architect | Use this skill when users need to design a sales funnel, map a value ladder,...。 |
| gdpr-data-handling | 实现 GDPR 合规的数据处理、同意与权利响应。 |
| gh-address-comments | Help address review/issue comments on the open GitHub PR for the current bran...。 |
| gh-fix-ci | Use when a user asks to debug or fix failing GitHub PR checks that run in Git...。 |
| git-advanced-workflows | Master advanced Git workflows including rebasing, cherry-picking, bisect, wor...。 |
| github-actions-templates | Create production-ready GitHub Actions workflows for automated testing, build...。 |
| github-deep-research | 对 GitHub 仓库做多轮深度研究和时间线分析。 |
| github-repo-search | 帮助用户搜索和筛选 GitHub 开源项目，输出结构化推荐报告。当用户说"帮我找开源项目"、"搜一下GitHub上有什么"、"找找XX方向的仓库"、"开源...。 |
| gitlab-ci-patterns | Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distrib...。 |
| go-concurrency-patterns | 编写和调试 Go 的 goroutine、channel 与并发模式。 |
| godot-gdscript-patterns | Master Godot 4 GDScript patterns including signals, scenes, state machines, a...。 |
| graalvm-native-image | Provides expert guidance for building GraalVM Native Image executables from J...。 |
| gradle-build-performance | 诊断并优化 Android/Gradle 构建性能。 |
| grill-me | Interview the user relentlessly about a plan or design until reaching shared...。 |
| helm-chart-scaffolding | 搭建可复用、可验证的 Helm Chart。 |
| hierarchical-matching-systems | Expertise in architecting, implementing, reviewing, and debugging hierarchica...。 |
| hooks-development | Claude Code hooks development guide. TRIGGERS - create hook, PostToolUse, Pre...。 |
| i18n-localization | Internationalization and localization patterns. Detecting hardcoded strings,...。 |
| icon-retrieval | 检索图标库并返回可直接使用的 SVG。 |
| idea-validator | Validate startup ideas using Hexa's Opportunity Memo framework and Perceived...。 |
| incident-triage | Use when a user reports something isn't working, a service is down, or an err...。 |
| influence-psychology | Apply the six principles of ethical persuasion (reciprocity, commitment, soci...。 |
| interaction-design | 设计并实现微交互、动效和反馈体验。 |
| inversion-strategist | 从“如何失败”反推风险，得到更稳的决策。 |
| ios-hig-design | Design native iOS interfaces following Apple Human Interface Guidelines。 |
| ios-simulator-skill | 21 production-ready scripts for iOS app testing, building, and automation. Pr...。 |
| jadx | Android APK decompiler that converts DEX bytecode to readable Java source code。 |
| java-expert | Java and Spring Boot expert including REST APIs, JPA, and microservices。 |
| java-junit | 提供 JUnit 5 与数据驱动测试最佳实践。 |
| javascript-typescript-jest | 编写 JavaScript/TypeScript 的 Jest 测试与 mock 策略。 |
| k8s-manifest-generator | 生成生产可用的 Kubernetes 资源清单。 |
| k8s-security-policies | 为 Kubernetes 实施网络隔离、RBAC 与安全策略。 |
| knowledge-synthesis | Combines search results from multiple sources into coherent, deduplicated ans...。 |
| laravel-patterns | Laravel架构模式、路由/控制器、Eloquent ORM、服务层、队列、事件、缓存以及用于生产应用的API资源。 |
| laravel-security | Laravel 安全最佳实践，涵盖认证/授权、验证、CSRF、批量赋值、文件上传、密钥管理、速率限制和安全部署。 |
| laravel-specialist | Build and configure Laravel 10+ applications, including creating Eloquent mod...。 |
| laravel-tdd | 使用 PHPUnit 和 Pest、工厂、数据库测试、模拟以及覆盖率目标进行 Laravel 的测试驱动开发。 |
| laravel-verification | Verification loop for Laravel projects: env checks, linting, static analysis,...。 |
| lead-channel-optimizer | Use this skill when users need to optimize lead generation channels, identify...。 |
| lead-research-assistant | Identifies high-quality leads for your product or service by analyzing your b...。 |
| leads-researcher | This skill should be used when users need to research leads, find company inf...。 |
| legal-risk-assessment | Assess and classify legal risks using a severity-by-likelihood framework with...。 |
| lesson-learned | Analyze recent code changes via git history and extract software engineering...。 |
| linux-privilege-escalation | This skill should be used when the user asks to "escalate privileges on Linux...。 |
| linux-shell-scripting | This skill should be used when the user asks to "create bash scripts", "autom...。 |
| liquid-glass-design | iOS 26 液态玻璃设计系统 — 适用于 SwiftUI、UIKit 和 WidgetKit 的动态玻璃材质，具有模糊、反射和交互式变形效果。 |
| llm-evaluation | 为 LLM 应用建立自动化与人工结合的评测体系。 |
| log-analyzer | Use when the user needs to investigate logs, find errors, trace issues across...。 |
| macos-design-guidelines | Apple Human Interface Guidelines for Mac。 |
| made-to-stick | Craft messages that are understood, remembered, and drive action using the SU...。 |
| managing-tech-debt | Help users manage technical debt strategically。 |
| markdown-mermaid-writing | 用 Markdown 和 Mermaid 统一写作与图表表达。 |
| markdown-token-optimizer | Analyzes markdown files for token efficiency. TRIGGERS: optimize markdown, re...。 |
| market-sizing-analysis | 估算 TAM、SAM、SOM 等市场规模。 |
| marketing-psychology | 用行为科学与心理学原理优化营销。 |
| markitdown | 将文档、网页、媒体等多种格式转换为 Markdown。 |
| md-to-pdf | Convert Markdown files to professionally styled PDF documents with full suppo...。 |
| meeting-insights-analyzer | Analyzes meeting transcripts and recordings to uncover behavioral patterns, c...。 |
| meeting-minutes | 生成包含决策和行动项的会议纪要。 |
| meeting-notes-and-actions | Turn meeting transcripts or rough notes into crisp summaries with decisions,...。 |
| memory-forensics | 使用内存取证方法分析进程、恶意行为和证据。 |
| memory-safety-patterns | 在 Rust/C++/C 中落实资源管理与内存安全模式。 |
| microsoft-code-reference | 查询微软 API/SDK 正确用法与官方代码示例。 |
| microsoft-docs | 从微软官方文档获取 Azure、.NET 等技术信息。 |
| miniprogram-development | WeChat Mini Program development skill for building, debugging, previewing, te...。 |
| model-first-reasoning | Apply Model-First Reasoning (MFR) to code generation tasks。 |
| modern-javascript-patterns | 采用 ES6+ 现代 JavaScript 语法与模式。 |
| mom-test | Talk to customers without leading them using Mom Test rules: discuss their li...。 |
| mysql-best-practices | MySQL development best practices for schema design, query optimization, and d...。 |
| narrative-text-visualization | Generate structured narrative text visualizations from data using T8 Syntax。 |
| nestjs-expert | Creates and configures NestJS modules, controllers, services, DTOs, guards, a...。 |
| network-troubleshooter | Use when the user has connectivity issues, DNS problems, can't reach a servic...。 |
| nextjs-developer | Use when building Next.js 14+ applications with App Router, server components...。 |
| nginx-config-optimizer | Optimizes Nginx configurations for performance, security, caching, and load b...。 |
| nmap | Professional network reconnaissance and port scanning using nmap. Supports va...。 |
| obsidian-bases | 创建和编辑 Obsidian Bases 数据视图。 |
| obsidian-cli | 通过 CLI 读写 Obsidian 笔记、任务与插件状态。 |
| obviously-awesome | Define product positioning by mapping competitive alternatives, unique attrib...。 |
| openapi-spec-generation | 生成并维护 OpenAPI 3.1 规范。 |
| opportunity-solution-tree | 用 OST 梳理目标、机会、方案和实验。 |
| paid-ads | 制定 Google/Meta/LinkedIn 等付费投放策略。 |
| 读取、拆分、合并、OCR 和生成 PDF 文档。 | |
| performance-optimizer | Use when the user wants to speed up their system, free resources, or resolve...。 |
| personal-branding-advanced | 高级个人品牌建设 - 从内容创作者到行业意见领袖的系统性品牌架构。 |
| php-doc | Invoke BEFORE writing phpDoc。 |
| php-pro | Use when building PHP applications with modern PHP 8.3+ features, Laravel, or...。 |
| phpunit-best-practices | PHPUnit testing best practices and conventions guide。 |
| pitch-deck-reviewer | Review and critique VC pitch decks using the ABC Framework and Inevitable Sto...。 |
| plan-review | Pre-implementation plan audit that stress-tests scope, assumptions, risks, an...。 |
| planning-under-uncertainty | Help users plan products and strategy when outcomes are unpredictable。 |
| plantuml-ascii | 用 PlantUML 生成终端友好的 ASCII 图。 |
| popup-cro | 优化弹窗、浮层、通知条等转化组件。 |
| porters-five-forces | 开展波特五力行业竞争分析。 |
| postgresql-table-design | 设计符合 PostgreSQL 最佳实践的表结构。 |
| pptx | 读取、创建、编辑和拆分 .pptx 演示文稿。 |
| pragmatic-programmer | Apply meta-principles of software craftsmanship: DRY, orthogonality, tracer b...。 |
| pre-landing-review | Gate-oriented safety audit for code changes before landing, using a structure...。 |
| pre-mortem-analyst | 假设项目已失败，倒推致因并识别风险。 |
| pricing-strategy | 设计定价、套餐和变现策略。 |
| priority-judge | 优先级判断助手 - 帮用户从混沌的待办事项中判断优先级，确定现在该做什么。当用户说"我有很多事要做"、"帮我理一下"、"排个优先级"、"今天该做什么"时触发。 |
| private-domain | Use when driving Xiaohongshu followers to private domains like WeChat, buildi...。 |
| prlctl-vm-control | 通过 prlctl 控制 Parallels 虚拟机并执行命令。 |
| process-optimization | Analyze and improve business processes。 |
| product-name | 生成产品命名方案及命名理由。 |
| product-naming | 产品命名协作流程。当用户想给产品/项目/模块起名字时使用。通过"灵魂挖掘 → 约束提取 → 路线发散 → 方向选择 → 竞品验证 → 最终确认"的结构化流...。 |
| prompt-engineering-patterns | 设计高可靠、可控的高级提示工程方案。 |
| prompt-lab | Systematic LLM prompt engineering: analyzes existing prompts for failure mode...。 |
| proposal-review | Facilitate methodical review of proposals (technical designs, product specs,...。 |
| protocol-reverse-engineering | 逆向网络协议、报文结构和通信流程。 |
| pua | Forces high-agency exhaustive problem-solving with corporate PUA pressure esc...。 |
| python-background-jobs | 实现 Python 后台任务、队列和事件驱动处理。 |
| python-design-patterns | 用 Python 设计模式改善结构、职责和组合方式。 |
| python-error-handling | 设计 Python 输入校验、异常体系与部分失败处理。 |
| python-observability | 为 Python 应用补充日志、指标和链路追踪。 |
| python-performance-optimization | 对 Python 代码做性能剖析和优化。 |
| python-testing-patterns | 用 pytest、fixture 和 mock 建立测试体系。 |
| python-type-safety | 为 Python 引入类型标注、泛型和严格类型检查。 |
| rag-auditor | Evaluates RAG (Retrieval-Augmented Generation) pipeline quality across retrie...。 |
| react-hooks | React Hooks patterns, rules, and custom hook development. Covers all built-in...。 |
| react-native-best-practices | 优化 React Native/Expo 的性能、动画和渲染。 |
| react-native-design | 设计 React Native 的样式、导航和 Reanimated 动画。 |
| react-performance | React performance optimization techniques and best practices. Covers memoizat...。 |
| react-server-components | React Server Components (RSC) for server-side rendering without client JS. Co...。 |
| readme-blueprint-generator | 分析仓库后生成结构化 README。 |
| redesign-my-landingpage | Build, critique, and iterate high-converting marketing or product landing pag...。 |
| redis-best-practices | Redis development best practices for caching, data structures, and high-perfo...。 |
| refactoring-patterns | Apply named refactoring transformations to improve code structure without cha...。 |
| refactoring-ui | Audit and fix visual hierarchy, spacing, color, and depth in web UIs。 |
| referral-program | 设计推荐裂变、联盟与口碑增长机制。 |
| responsive-design | 用现代 CSS 实现响应式与自适应布局。 |
| risk-metrics-calculation | Calculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and dr...。 |
| root-cause-finder | Performs root-cause-first debugging and review by tracing expected behavior t...。 |
| running-decision-processes | Help users run effective decision-making processes。 |
| rust-async-patterns | 实践 Rust/Tokio 异步编程与并发模式。 |
| rust-best-practices | Guide for writing idiomatic Rust code based on Apollo GraphQL's best practice...。 |
| scientific-brainstorming | 为科研问题做开放式创意发散和假设探索。 |
| scoping-cutting | Help users scope projects and cut features effectively。 |
| screenshot | 在桌面或系统层面抓取屏幕截图。 |
| seam-ripper | Ruthlessly analyze architectural seams—the interfaces, boundaries, and contra...。 |
| security-ownership-map | Analyze git repositories to build a security ownership topology (people-to-fi...。 |
| security-requirement-extraction | 从威胁模型和业务上下文中提炼安全需求。 |
| security-threat-model | Repository-grounded threat modeling that enumerates trust boundaries, assets,...。 |
| seo | Optimize for search engine visibility and ranking。 |
| service-monitor | Use when the user wants to check if services are running, verify endpoints ar...。 |
| session-handoff | Creates comprehensive handoff documents for seamless AI agent session transfe...。 |
| shadcn-ui | Expert guidance for integrating and building applications with shadcn/ui comp...。 |
| similarity-search-patterns | 构建向量数据库语义检索与近邻搜索方案。 |
| site-analyze | 网站机房溯源全维度分析工具。当用户要求分析某个网站的机房位置、CDN、IP归属、路由链路、响应延迟、SSL证书、子域名等信息时使用。支持通过 DNS ov...。 |
| site-architecture | 规划网站结构、导航、URL 与内链体系。 |
| six-thinking-hats | Apply Edward de Bono's Six Thinking Hats methodology to software testing for...。 |
| skill-creator | Create new skills, modify and improve existing skills, and measure skill perf...。 |
| skill-judge | Evaluate Agent Skill design quality against official specifications and best...。 |
| skills-prune-and-sync-readme | 遍历当前仓库的 skills/ 目录，依据证据定位低质量、重复或触发冲突的 skill，按明确名单删除目标目录，并重建 README.md 中的...。 |
| slash-command-bridge | 在不原生支持 Claude Code slash command 的环境中桥接并执行命令。用户输入以 / 开头，且当前运行时不会自动解析 `.clau...。 |
| social-platform-safety | 主动识别、屏蔽和过滤社交平台（特别是Moltbook）中的诱导性内容、垃圾信息、广告和有害内容。提供安全的内容交互指导，防止提示词污染和AI被误导。 |
| software-design-philosophy | Manage software complexity through deep modules, information hiding, and stra...。 |
| speckit.checker | Run static analysis tools and aggregate results。 |
| speckit.checklist | Generate a custom checklist for the current feature based on user requirements。 |
| speckit.diff | Compare two versions of a spec or plan to highlight changes。 |
| speckit.implement | Execute the implementation plan by processing and executing all tasks defined...。 |
| speckit.plan | Execute the implementation planning workflow using the plan template to gener...。 |
| speckit.quizme | Challenge the specification with Socratic questioning to identify logical gap...。 |
| speckit.reviewer | Perform code review with actionable feedback and suggestions。 |
| speckit.status | Display a dashboard showing feature status, completion percentage, and blockers。 |
| speckit.taskstoissues | Convert existing tasks into actionable, dependency-ordered GitHub issues for...。 |
| speckit.tester | Execute tests, measure coverage, and report results。 |
| speckit.validate | Validate that implementation matches specification requirements。 |
| sql-code-review | 对通用 SQL 做安全性、可维护性和规范审查。 |
| sql-optimization | 跨数据库优化 SQL 查询、索引和分页性能。 |
| startup-icp-definer | Use this skill when users need to define their ideal customer profile, identi...。 |
| statistical-analysis | Apply statistical methods including descriptive stats, trend analysis, outlie...。 |
| stride-analysis-patterns | 用 STRIDE 方法系统识别安全威胁。 |
| surprise-me | 组合现有 skill 生成意外但完整的创意成果。 |
| swift-concurrency-expert | Swift Concurrency review and remediation for Swift 6.2+。 |
| swiftui-performance-audit | Audit and improve SwiftUI runtime performance from code review and architectu...。 |
| swiftui-ui-patterns | Best practices and example-driven guidance for building SwiftUI views and com...。 |
| swiftui-view-refactor | Refactor and review SwiftUI view files for consistent structure, dependency i...。 |
| swot-analysis | 产出 SWOT 分析及对应行动建议。 |
| symfony-messenger | Implement resilient Symfony async workflows with idempotency, retries, and op...。 |
| symfony-ux | 在 Symfony 中组合 Stimulus、Turbo、LiveComponent 等 UX 工具。 |
| symfony-voters | Strengthen Symfony authorization and validation boundaries with explicit, tes...。 |
| system-design | Design systems, services, and architectures。 |
| system-diagnostics | Use when the user reports system slowness, wants a health check, or needs to...。 |
| systems-thinking | Help users think in systems and understand complex dynamics。 |
| tailwind-design-system | 基于 Tailwind CSS v4 构建设计系统。 |
| task-decomposer | Produces structured phased task boards from feature requests: dependency-mapp...。 |
| tauri-v2 | Tauri v2 cross-platform app development with Rust backend。 |
| team-composition-analysis | 规划团队结构、招聘、薪酬与股权配置。 |
| tech-debt | Identify, categorize, and prioritize technical debt。 |
| technology-search | Search tech blogs, developer forums, and IT media (TechCrunch, Hacker News, 3...。 |
| terraform-module-builder | Creates reusable Terraform modules with proper structure, variables, outputs,...。 |
| test-driven-development | 先写失败测试，再实现功能或修复。 |
| test-strategy | Production-grade test strategy skill with risk-based testing, coverage analys...。 |
| testing-strategy | Design test strategies and test plans。 |
| thinking-partner | 思考拍档 - 陪你从混沌中理清局面，锁定核心问题，拆解卡点，共创解法，落地行动。 |
| threat-mitigation-mapping | 把已识别威胁映射到具体控制措施。 |
| top-web-vulnerabilities | This skill should be used when the user asks to "identify web application vul...。 |
| twig-components | Apply production-grade Symfony architecture and execution workflows with cont...。 |
| typescript-advanced-types | 运用 TypeScript 高级类型构建强类型抽象。 |
| typescript-magician | Designs complex generic types, refactors any types to strict alternatives,...。 |
| update-markdown-file-index | 更新 Markdown 文件中的目录或文件索引区块。 |
| upgrading-react-native | Upgrades React Native apps to newer versions by applying rn-diff-purge templa...。 |
| uv-package-manager | 用 uv 管理 Python 依赖、虚拟环境和项目工作流。 |
| ux-heuristics | Evaluate and improve interface usability using heuristic analysis。 |
| ux-researcher-designer | 支持用户研究、画像、旅程图与可用性验证。 |
| vector-index-tuning | 调优向量索引的延迟、召回和内存占用。 |
| vercel-react-best-practices | 采用 Vercel 推荐的 React/Next.js 性能最佳实践。 |
| verification-before-completion | 宣称完成前先跑验证并用结果说话。 |
| version-planner | 帮助用户把产品需求拆解成渐进式版本规划。当用户说"拆版本"、"版本规划"、"MVP怎么做"、"分阶段实现"时触发。 |
| visual-design-foundations | 用字体、色彩、间距和图标基础提升视觉一致性。 |
| vue-expert-js | Creates Vue 3 components, builds vanilla JS composables, configures Vite proj...。 |
| web-content-fetcher | Extract article content from any URL as clean Markdown. Uses Scrapling script...。 |
| web-design-guidelines | Web platform design and accessibility guidelines。 |
| web-quality-audit | Comprehensive web quality audit covering performance, accessibility, SEO, and...。 |
| webapp-testing | 用 Playwright 测试本地 Web 应用并采集日志/截图。 |
| webman-best-practices | MUST be used for Webman framework projects. Covers DDD architecture with cont...。 |
| what-if-oracle | 对不确定情境做多分支 What-if 情景推演。 |
| wiki-researcher | 对代码库主题做多轮、深入、跨文件研究。 |
| windows-kernel-security | Guide for Windows kernel internals and security mechanisms used in game prote...。 |
| wireshark-analysis | This skill should be used when the user asks to "analyze network traffic with...。 |
| xhs-graphic-generator | 小红书图文帖子生成器。将主题或文章转化为5-18张精美的小红书图文卡片。 使用场景：当用户需要生成小红书图文、制作小红书笔记、创建红书帖子时。 关键词：小...。 |
| xiaohongshu-commercial-growth | 小红书商业增长与变现实战技能，覆盖入局判断、账号定位、内容生产、推荐与搜索流量、店铺/直播/买手/知识付费变现，以及薯条、ARK、蒲公英、聚光等投放与种草...。 |
| xlsx | 读取、清洗、编辑和生成 Excel/CSV 等电子表格。 |
| youtube-analysis | Extract YouTube video transcripts and produce structured concept analysis wit...。 |
| youtube-search | Search YouTube by keyword and return structured video metadata (title, URL, c...。 |