Axhub-Skills

Use when 需要在中国、海外或跨市场场景中开展客户研究、用户研究、VOC、ICP、JTBD、Persona、竞品口碑、购买或流失原因分析，或从访谈、问卷、工单、社区与评论中为需求分析和 PRD 建立客户证据。

面向不熟悉 Git 的产品经理、设计师、运营、文档作者等非技术用户，引导 GitHub/GitLab/Gitee/Bitbucket/自建 Git 平台的仓库初始化、授权、克隆、提交同步、冲突处理、版本恢复和协作交接。

Use when 需要把现有 React、Vite、Next.js、V0 或 AI Studio 页面转换为 Figma Make 可导入的 .fig 资产，或补齐、更新、验证已有 Figma Make 导出壳和 canvas.fig。

处理 Axhub Commentary 页面侧接入工作流，包括调整面板可编辑项、页面级属性聚合、多方案设计比稿与方案切换，以及页面资源上下文与定位信息补齐。当用户要让页面配合 Axhub Chrome 扩展或 Make 预览环境“能在调整面板改”、按页面统一整理可编辑项、先出多版方向再切换对比，或补页面定位信息以便调试时快速找到当前页和对应实现时使用。

Use when an Axhub prototype URL needs its PRD, directory, annotation context, source handoff, or optional review-report submission, especially for prototype-as-PRD review, agent context gathering, implementation planning, or design/requirements review with Playwright, Browser, Chrome, or an equivalent page evaluator.

Use when adding @axhub/annotation to standalone React apps, plain HTML pages, Vite prototypes, or other web hosts that need annotation markers, directories, Markdown notes, or state controls.

Use when an Axhub prototype URL needs its PRD, directory, or annotation context read from window.__AXHUB_ANNOTATION_SOURCE__, especially for prototype-as-PRD review, agent context gathering, or annotation extraction with Playwright, Browser, Chrome, or an equivalent page evaluator.

高精度克隆网页。使用 Playwright 渐进式采集页面数据（DOM 结构、样式、截图、资源）， 然后分阶段构建完整的 HTML/CSS 还原。支持快速还原和高精度还原两种模式。 当用户需要克隆、复刻、还原、仿制网页时使用此技能。 当用户提供 URL 并要求"做一个一样的页面"、"把这个页面克隆过来"、 "参考这个网站的设计"、"还原这个页面"时，务必使用此技能。

从网页中采集设计令牌并生成完整的 DESIGN.md 设计规范文档 + Tailwind CSS 主题文件。 当用户提供 URL 并要求"提取主题"、"生成设计规范"、"导出设计系统"、 "提取这个网站的设计令牌"、"帮我做一个主题"、"分析这个页面的设计风格"时使用。 产出包含 DESIGN.md（getdesign.md / DESIGN.md 9 段式标准）和 globals.css（Tailwind CSS v4）， 每个 token 类别均有推荐/允许/禁止三级规范，可直接放入项目根目录供 AI 编码工具使用。

Extract structured data from Axure prototypes using Playwright — screenshots, design tokens, interaction maps, annotations, and page text. Use this skill whenever the user wants to extract data from an Axure prototype, reconstruct or clone an Axure page, analyze Axure design tokens, export Axure content, or work with Axure prototype URLs (even if they don't say "Axure" explicitly — look for AxShare links, /start.html#p= URLs, or mentions of wireframes/prototypes hosted online).

Extract structured data from any web page using Playwright — screenshots, design tokens, page text as Markdown, interactive element maps, and full page data packs. Use this skill whenever the user wants to capture a web page screenshot (full page or element), extract CSS design tokens or theme information, convert page content to Markdown, collect links and interactive elements from a page, or export a complete page analysis package. Triggers on any URL that isn't an Axure prototype — for Axure URLs use extract-axure-data instead.

Install and configure MCP servers across desktop and CLI clients (Claude, Cline, Windsurf, Cursor, VSCode, Gemini CLI, Codex, Trae, Antigravity, etc.) on macOS/Windows/Linux, preferring @smithery/cli when supported and otherwise performing manual JSON config updates and path discovery.