alchaincyf avatar

Huashu Weread Advisor

This is a sophisticated layer on top of WeRead's API that turns raw reading data into actionable workflows. Instead of just fetching your bookshelf or highlights, it cross-references what you've shelved versus what you've actually annotated to build a real knowledge map. Four main modes: personalized recommendations based on reading depth, structured learning paths for new domains, distilling scattered highlights into coherent notes, and generating shareable reading retrospectives. The interesting bit is how it catches the gap between books you've added and books you've genuinely engaged with, which matters more than you'd think for useful recommendations. Requires WEREAD_API_KEY and follows specific Chinese language style guidelines throughout.

skills.sh installs
447
GitHub stars
161
last updated
Aug 21, 2026

Install

$ npx -y skills add alchaincyf/huashu-weread --skill huashu-weread-advisor --agent claude-code

Installs into .claude/skills of the current project.

Files

huashu-weread-advisor

把原子的微信读书 API 变成一个真正读懂你的读书顾问。

定位

底层 weread skill 提供原子接口(搜索、书架、笔记、点评、推荐、阅读统计),本 skill 在其之上做工作流编排,把原始数据转成对用户有消费价值的产出。

前置依赖

  • 必须先有 WEREAD_API_KEY 环境变量(在用户 shell 中 export)
  • 所有 API 调用走 POST https://i.weread.qq.com/api/agent/gateway
  • 请求 body 必须带 skill_version 字段——值的权威来源:~/.claude/skills/weread/SKILL.md 顶部 frontmatter 的 version 字段(当前 1.0.3,会变;别从 prompt 或老模板里抄)
  • 接口文档和参数详情见底层 weread skill:~/.claude/skills/weread/SKILL.md

核心方法论(所有 workflow 共享)

1. 书架和笔记是两个数据源,必须交叉

数据源接口揭示什么
书架/shelf/sync用户主动分类的兴趣方向 + 加入了什么
笔记/user/notebooks用户真读过的书 + 读得多深(笔记条数)
进度/book/getprogress某本书读到哪、累计读了多久
统计/readdata/detail周/月/年阅读时长、天数、主题偏好

关键洞察:很多书在书架但没动,很多书没在书架(借/试读)但深读了。只看书架会漏掉重要信号。

实战例子:花叔的 Kandel《追寻记忆的痕迹》27 条笔记,书架的「心理学」分类里根本没列,但其实是他在神经科学领域读得最深的一本。如果只看书架做推荐,会误判他的真实知识地图。

2. 「最近读什么」≠「书架主题」

用户的当前兴趣可能和书架分类完全不一致。永远用 readUpdateTime 倒序看最近 30 天在动什么书,再做推荐。

3. 推荐必附 weread:// 深度链接

weread://reading?bId={bookId} 让用户一键打开。链接格式详见底层 weread skill 的「深度链接(URL Schema)」章节。

4. 推荐前必须验证微信读书是否上架

Sponsors

Details

Repository
github.com/alchaincyf/huashu-weread
Categories
Backend & APIs, Git & Pull Requests, Code Review & Quality
First seen
Jun 3, 2026
1jwynia avatarpwa-developmentjwynia/agent-skillsImplement Progressive Web App features for React and Svelte projects. This skill should be used when the user asks to 'make a PWA', 'add offline support', 'crea447skills.sh installs
2cacr92 avatarwechat-automationcacr92/wereply当用户要求"微信监听"、"消息提取"、"Agent 开发"、"wxauto"、"Accessibility API"、"UI 自动化"、"输入框控制"、"Platform Agent",或者提到"微信自动化"、"消息监控"、"WeChat monitoring"时使用此技能。用于开发 WeReply 的 Platfor445skills.sh installs
3majesteitbart avatarshadcn-ui-expertmajesteitbart/talentmatcherDevelop high-quality, accessible React components using shadcn-ui, Tailwind CSS, and Radix UI. Use when building forms, layouts, dialogs, tables, or any UI comp445skills.sh installs
4openclaudia avatarbacklink-auditopenclaudia/openclaudia-skillsAudit a domain's backlink profile using the SemRush API. Use when the user says "audit backlinks", "check my backlinks", "backlink analysis", "link profile", "t444skills.sh installs
5vm0-ai avatarinstagramvm0-ai/vm0-skillsInstagram API for posts and media. Use when user mentions "Instagram", "instagram.com", shares an IG link, "Instagram post", or asks about social media content.444skills.sh installs
6wot-ui avatarwot-uiwot-ui/wot-starterwot-ui uni-app 组件库开发指南。当用户询问 wot-ui 组件使用、配置、示例或 API 时使用此技能。442skills.sh installs