Huashu Weread — Productivity skill for Claude Code
微信读书高阶顾问 · 在官方 weread skill 之上加一层「读书顾问的工作流」· 书架+笔记交叉分析 · 4 个 workflow (advisor/path/alchemy/review) · Made by 花叔.
How to install Huashu Weread
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open alchaincyf/huashu-weread and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Huashu Weread does
微信读书高阶顾问 · 在官方 weread skill 之上加一层「读书顾问的工作流」· 书架+笔记交叉分析 · 4 个 workflow (advisor/path/alchemy/review) · Made by 花叔.
Alternatives in Productivity
- Reviews Plans — Review all active architecture plans relevant to the current task 15.6k ★
- C-level Advisor — Executive advisory skills for C-level decisions 5.3k ★
- Trio — Force a trio review of the task that follows — pm, designer, and engineer weigh in in parallel before any acti 324 ★
README
huashu-weread
*「不是查数据。是 AI 把你忘掉的那些时刻还给你。」*
[](LICENSE) [](https://skills.sh) [](https://skills.sh)
**微信读书高阶顾问 · 在官方 weread skill 之上加一层「读书顾问的工作流」**
微信读书前几天上了一个官方 AI skill([weread.qq.com/r/weread-skills](https://weread.qq.com/r/weread-skills)),把书架、笔记、阅读统计、推荐 6 件事开放给 AI。能力很强,但它只是「自然语言包装的搜索接口」——你让它推荐书,它不会去看你已经读过什么,常把你笔记 68 条的书又当新书推回来给你。
本 skill 在官方 8 个 API 之上,加一层「**读书顾问的工作流**」。核心方法是「**书架 + 笔记交叉分析**」——书架揭示你「主动归类的兴趣」,笔记揭示你「真读过的书」。只看书架会漏信号,只看笔记会错过兴趣方向。
npx skills add alchaincyf/huashu-weread
跨 agent 通用——Claude Code、Cursor、Codex、OpenClaw、Hermes 都能装。
[看效果对比](#看效果对比) · [装上就能用](#装上就能用) · [4 个 workflow](#4-个-workflow) · [核心方法](#核心方法书架--笔记交叉)
看效果对比
同样一个问题:「**推荐下产品经理方向的书**」。
**裸 weread skill 答:14 本通识书单**
按入门到进阶分了 6 个梯队,推《俞军产品方法论》《幕后产品》《硅谷增长黑客实战笔记》……都是好书,但:
- 《俞军产品方法论》我做了 68 条笔记
- 《幕后产品》在我书架上躺着两年
- 《硅谷增长黑客》我做了 34 条笔记
它根本没看我的笔记和书架,只是一个用自然语言包装的搜索接口。把读过的书又当新书推回来。
**huashu-weread 答:5 本针对你的拼图建议**
| 推荐 | 理由(基于你的实际阅读数据) |
|---|---|
| 《转型启示录》Marty Cagan | 你读了俞军、苏杰这一脉中国 PM 经典,但完全没碰 Cagan |
| 《设计心理学》诺曼 | 你方法论书一堆但 UX 根基缺 |
| 《AI Product Manager's Handbook》 | 你在做 AI 产品但 AI PM 书架空白 |
| 《重来》Jason Fried | 你是独立开发者但读的 PM 书大多是大公司视角 |
| 《重来 3》 | 你之前加了《小而美》没读完,这本是同一谱系更系统 |
最后还给「如果只读一本:X」和「如果想真正再上一个台阶:Y+Z」两个明确建议。
差距:**裸 weread 给的是「合格的通识书单」,huashu-weread 给的是「针对你这个人的拼图建议」**。
装上就能用
**前置依赖**:必须先装官方 weread skill([weread.qq.com/r/weread-skills](https://weread.qq.com/r/weread-skills)),按页面指引走两步配置(复制安装指令 + 登录拿 API Key),全程不超过 1 分钟。
装完官方后,再装本 skill:
npx skills add alchaincyf/huashu-weread
跑起来:
"推荐下一本读啥" → 自动走 advisor
"想系统搞懂行为经济学" → 自动走 path
"整理下我在《掌控习惯》里的笔记" → 自动走 alchemy
"写一篇我今年的读书复盘" → 自动走 review
"我现在在读哪本" → 轻量直答,一句话给进度
模糊的需求也认:「不知道读啥」「有相
Related Skills
Kg Review
Knowledge-graph-aware task review — first pull relevant prior decisions, then at the end capture any decisions
Wb Context Review
Load directions via mcpwork-buddywb_run("agent_docs", {"path": "context/context-review-directions", "depth": "
Cc Navigator
[Claude Code Skill] Workflow advisor — recommends the right skill, agent, or workflow for any task. Install: n
Think Twice
Run the think-twice checklist before implementing a task — stops at the first question that reveals a cheaper
Wb Chrome Triage
Load directions via mcpwork-buddywb_run("agent_docs", {"path": "browser/chrome-triage-directions", "depth": "f
V Dispatch
Execute a Compound-V-ready plan, manifest, or run-id on Engine C — the native Workflow dispatch engine. Accept
Related Agents
Docs Drift Review
Given a session's commits or diff, finds the docs that the change made wrong — stale paths and symbols, checkl
Docs Impact Agent
Finds repository documentation made false by a change and missing documentation required to use or operate a n
Docs Staleness Detector
Use this agent when a core change has been made to the repository and you need to verify that related document