Agent skill

Huashu Weread Advisor

by alchaincyf in alchaincyf/huashu-weread

微信读书高阶顾问。在底层 weread skill 的原子 API 之上，提供四类工作流：基于已读做个性化进阶推荐（advisor）、给方向规划入门到前沿的阶梯书单（path）、把零散划线想法提炼成读书笔记总结（alchemy）、做季度/年度阅读复盘并生成可发朋友圈/公众号的文章（review）。核心方法是「书架 +…

MITAuto-check passed

Install Huashu Weread Advisor

skills CLI

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

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install alchaincyf/huashu-weread huashu-weread-advisor --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "huashu-weread-advisor" agent skill from https://github.com/alchaincyf/huashu-weread/tree/main into .claude/skills/huashu-weread-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-weread-advisor", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add alchaincyf/huashu-weread --skill huashu-weread-advisor -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install alchaincyf/huashu-weread huashu-weread-advisor --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "huashu-weread-advisor" agent skill from https://github.com/alchaincyf/huashu-weread/tree/main into .agents/skills/huashu-weread-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-weread-advisor", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add alchaincyf/huashu-weread --skill huashu-weread-advisor -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install alchaincyf/huashu-weread huashu-weread-advisor --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "huashu-weread-advisor" agent skill from https://github.com/alchaincyf/huashu-weread/tree/main into .cursor/skills/huashu-weread-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-weread-advisor", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add alchaincyf/huashu-weread --skill huashu-weread-advisor -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install alchaincyf/huashu-weread huashu-weread-advisor --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "huashu-weread-advisor" agent skill from https://github.com/alchaincyf/huashu-weread/tree/main into .gemini/skills/huashu-weread-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-weread-advisor", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install alchaincyf/huashu-weread huashu-weread-advisor

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add alchaincyf/huashu-weread --skill huashu-weread-advisor -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "huashu-weread-advisor" agent skill from https://github.com/alchaincyf/huashu-weread/tree/main into .github/skills/huashu-weread-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-weread-advisor", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add alchaincyf/huashu-weread --skill huashu-weread-advisor -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install alchaincyf/huashu-weread huashu-weread-advisor --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "huashu-weread-advisor" agent skill from https://github.com/alchaincyf/huashu-weread/tree/main into .opencode/skills/huashu-weread-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-weread-advisor", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: huashu-weread-advisor
GitHub stars: 152
Token cost: ~1.4k tokens
SKILL.md length: 401 words
Files: 12
Skills in repo: 1
Repo updated: Aug 25, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Works in 5 steps: 书架和笔记是两个数据源，必须交叉 → 「最近读什么」≠「书架主题」 → 推荐必附 weread:// 深度链接 → …
SKILL.md covers 定位, 前置依赖, 核心方法论（所有 workflow 共享） and 检查点设计原则, plus 7 more sections
Calls git; reaches i.weread.qq.com; needs WEREAD_API_KEY

What it does

Huashu Weread Advisor is an agent skill from alchaincyf/huashu-weread. 微信读书高阶顾问。在底层 weread skill 的原子 API 之上，提供四类工作流：基于已读做个性化进阶推荐（advisor）、给方向规划入门到前沿的阶梯书单（path）、把零散划线想法提炼成读书笔记总结（alchemy）、做季度/年度阅读复盘并生成可发朋友圈/公众号的文章（review）。核心方法是「书架 + 笔记交叉分析」——书架揭示用户主动分类的兴趣，笔记数据揭示「真读过的」vs「只放着的」。当用户说「推荐书」「下一本读啥」「该读什么」「想搞懂 X 这个领域」「整理我的笔记」「这本书我记住了啥」「我今年读了什么」「读书复盘」「年度盘点」时触发。即使用户只是说「不知道读啥」「有没有相关的书」「帮我看看这本读完了吗」「这个领域我入门了吗」也应触发。

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files (for example `README.md`, `examples/advisor-neuroscience.md` and `shared/knowledge-map.md`).

The repository describes itself as: 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. The licence is MIT.

Example prompts

“/huashu-weread-advisor”

Requirements

Python 3
A credential in WEREAD_API_KEY

Workflow steps

5 steps, taken from the step headings in SKILL.md.

书架和笔记是两个数据源，必须交叉
「最近读什么」≠「书架主题」
推荐必附 weread:// 深度链接
推荐前必须验证微信读书是否上架
输出走花叔语言风格

What it can do on your machine

Read from SKILL.md and the folder at commit 00be7ae. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- git
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- i.weread.qq.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- WEREAD_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Huashu Weread Advisor loads about 1.4k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 401 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~89
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from alchaincyf/huashu-weread at commit 00be7ae, republished under its MIT licence (© alchaincyf). 401 words, ~1,351 tokens.

Download SKILL.mdSave it as .claude/skills/huashu-weread-advisor/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.

name: huashu-weread-advisor
description: 微信读书高阶顾问。在底层 weread skill 的原子 API 之上，提供四类工作流：基于已读做个性化进阶推荐（advisor）、给方向规划入门到前沿的阶梯书单（path）、把零散划线想法提炼成读书笔记总结（alchemy）、做季度/年度阅读复盘并生成可发朋友圈/公众号的文章（review）。核心方法是「书架 + 笔记交叉分析」——书架揭示用户主动分类的兴趣，笔记数据揭示「真读过的」vs「只放着的」。当用户说「推荐书」「下一本读啥」「该读什么」「想搞懂 X 这个领域」「整理我的笔记」「这本书我记住了啥」「我今年读了什么」「读书复盘」「年度盘点」时触发。即使用户只是说「不知道读啥」「有没有相关的书」「帮我看看这本读完了吗」「这个领域我入门了吗」也应触发。

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

用 /store/search 搜确认。上架的附 weread:// 链接，不上架的明确告诉用户合法替代路径（购买纸质/英文版/作者公开课/图书馆）。绝不推盗版资源。

5. 输出走花叔语言风格

不堆砌、不破折号（全文 ≤ 2 处）、人味重
用「」不用""
不用「首先/其次/综上」这类 AI 结构词
不用「说白了/简单来说/换句话说」
markdown 不过度加粗
详见 /04-写作参考/SHARED-RULES.md

检查点设计原则

所有 workflow 必须在「分叉影响输出本质」的地方插入用户确认 gate，防止 AI 默认值跑偏：

推荐数量分叉：advisor 推 3 本 vs 8 本完全不同的体验，不要默认 5 本，先问
平台语气分叉：复盘文章发朋友圈/公众号/小红书/视频脚本语气差很多，写前必须确认
段位判断分叉：path workflow 把「我以为你是入门」的判断给用户看，让他确认或纠正
数据量分叉：alchemy 跨主题模式拉出 50+ 划线时，先汇总议题让用户选子集，不要默认全聚
未上架处理分叉：推荐里要不要包含未上架的书（用户可能只想要点开就能读的）

检查点不是「每步都问」。日常小决策（哪本放第一梯队、用什么动词）AI 自己定，不要打扰用户。规则是：只在选项影响输出本质时问。

如果用户原始 prompt 已经明确指定（「推 3 本上架的发公众号」），所有相关检查点都跳过。

子命令路由

用户说什么	走哪个 workflow
推荐书 / 下一本读啥 / 不知道读啥 / 想读 X 方向	advisor.md
想搞懂 X 这个领域 / 系统学习 X / 从零入门 X	path.md
整理我的笔记 / 这本书我记住了啥 / 提炼这个主题的划线	alchemy.md
我今年读了什么 / 季度复盘 / 年度盘点 / 写一篇复盘	review.md
我现在在读哪本 / 最近在读啥	轻量直答（见下方）

轻量直答：「我现在在读哪本」

不走 workflow，直接：

/shelf/sync 拿全书架
按 readUpdateTime 倒序取 top 5
用最新那本调 /book/getprogress 拿章节/进度/累计时长
一句话回复「你正在读 X，已到第 N 章，进度 X%，累计读了 X 小时」，附 weread:// 链接
顺带说一句最近一周在读的其他几本，看出主题倾向

共享子模块

shared/knowledge-map.md：怎么读懂一个人的知识地图（三个数据源 × 三种交叉信号）
shared/shelf-cross-notes.md：书架 + 笔记交叉分析的 Python 代码模板和主题关键词组

示例

examples/advisor-neuroscience.md：花叔「神经科学如何更进一步」案例的完整复盘，含步骤、输出、为什么这样推

Show full SKILL.md (198 more words)Show less

异常与边界条件

实操常遇异常。以下为全局通用 fallback，所有 workflow 共享。workflow 各自的特殊异常在各自文档末尾。

场景	触发条件	处理动作
`WEREAD_API_KEY` 未设置	环境变量不存在或不是 `wrk-` 开头	报错：「请先 export WEREAD_API_KEY=<你的apikey>，从微信读书后台获取」，终止
API 返回 `errcode != 0`	接口报错	显示中文错误信息，重试 1 次；仍失败告知用户并停止当前 workflow
接口返回 `upgrade_info`	服务端要求 skill 版本升级	暂停当前操作，按 `upgrade_info.message` 完成升级后重试，不得忽略
`/store/search` 响应解析	解析返回 JSON	顶层不是 `books[]`！实际结构是 `results[]`，按 section 分类。取上架：`results[?title=='电子书'].books[].bookInfo`；取未上架：`title=='待上架'`。每本书的 bookId 在 `bookInfo.bookId`。别用 `res.get('books', [])`，会全部 0 结果*
`/store/search` 多候选	同关键词返回 ≥ 3 本候选	默认取 `readingCount` 最高且作者完全匹配的（作者错位视同零结果，避免「Co-Intelligence」误命中「Collaborative Intelligence」类似的坑），明确告知用户「我用了《X》这本 by Y，bookId=Z，如果不对告诉我」
`/store/search` 零结果	完全搜不到 + 关键词调整 + 作者过滤后仍零	标记为「未上架」，按 advisor 的「合法替代路径」规则处理，绝不推盗版
notebooks 完全空	新用户 / 从未做笔记	退化：仅用 `/shelf/sync` 推断，但明确告知用户「你没做过笔记，我只能用书架猜兴趣，准度会差一些」
书架完全空	全新用户	不走 advisor / review / alchemy，建议先读几本；或直接进 path workflow 从零规划
接口分页未拉完	`/user/notebooks` 有 `hasMore`	用 `lastSort` 继续翻页（参数平铺，不要包在 `params` 里）；累计 > 500 本时给用户警告
`readUpdateTime` = 0	加入书架但从未打开	当作「未读」，不纳入「最近活跃」排序，但仍计入「书架有但没动」
用户给的书名搜不到	alchemy / 任何指名书的场景	先模糊搜（去标点/去副标题）；仍不到给候选清单让用户选
主题词过宽或过窄	「商业」「人文」太宽；冷门词太窄	过宽：请用户细化方向；过窄：告知微信读书覆盖薄，建议组合纸质/Kindle

原则：异常先告知用户，再按规则处理；绝不静默跳过或静默失败；接口报错的具体含义看底层 weread skill 的 references/ 文档。

数据展示规范（强制）

所有 workflow 输出给用户时遵守：

Unix 时间戳（readUpdateTime / finishTime / createTime 等）→ 转 YYYY-MM-DD，禁止直接展示数字
阅读时长字段单位是秒 → 转「X 小时 Y 分钟」，零小时时只写分钟
进度字段展示为 X%
bookId 在用户面前不出现裸数字，要么变成 weread:// 链接，要么藏在 markdown 链接里

调用约定

无论走哪个 workflow，第一步都是先读 SKILL.md 本文件 + 对应 workflow 文件 + shared/knowledge-map.md，然后才开始调 API。不要凭印象做推荐，所有推荐必须有数据支撑。

版本自检（静默）

本节给 AI agent：每次使用本 skill 前，先做一个不联网的判断——读本 skill 目录（SKILL.md 所在目录）下的 .last-update-check 文件（内容为一行日期 YYYY-MM-DD）。文件存在且距今不足 30 天，跳过本节直接干活，不向用户提任何更新相关的话。

到期或文件不存在时，且仅在此时：

本目录不是 git 克隆（无 .git 或无 origin）→ 写入今天日期后跳过本节
对比版本：git -C <本目录> rev-parse HEAD 与 git -C <本目录> ls-remote origin HEAD
无论结果如何，把今天日期写入 .last-update-check
两者一致 → 什么都不说；确认落后 → 先完成用户当前任务，结束后附一句「本 skill 有新版本，可用 git -C <本目录> pull --ff-only 更新」。是否更新由用户决定，不要主动执行更新

Files

SKILL.md and 11 other files in the repository root of alchaincyf/huashu-weread.

SKILL.md
.gitignore
LICENSE
README.md
examples/advisor-neuroscience.md
shared/knowledge-map.md
shared/shelf-cross-notes.md
test-prompts.json
workflows/advisor.md
workflows/alchemy.md
workflows/path.md
workflows/review.md

Open the folder on GitHubat commit 00be7ae

Compare with similar skills

Huashu Weread Advisor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Huashu Weread Advisor compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Huashu Weread Advisor this skillalchaincyf/huashu-weread	152	—	~1.4k	Automated safety check: Pass	MIT	1 mo ago
Advisor Modecursor/plugins	11k	—	~2.6k	Automated safety check: Notes	None	today
Odoo Upgrade Advisorsickn33/agentic-awesome-skills	47k	2 repos	~1.3k	Automated safety check: Pass	MIT	2 days ago
Token Budget Advisoraffaan-m/ECC	276k	—	~910	Automated safety check: Pass	MIT	yesterday
Token Budget Advisoraffaan-m/ECC	276k	—	~927	Automated safety check: Pass	MIT	yesterday
Weread Year In Review Video Templatenexu-io/open-design	100k	—	~784	Automated safety check: Pass	Apache-2.0	yesterday

Similar skills

Advisor Mode
cursor/plugins
Official
Adds a second, stronger model that the main agent consults before major decisions, when stuck and before finishing, controlled by /advisor commands.
11k GitHub stars~2.6k tokensUpdated today
Agent WorkflowsAuto-check: notes
Odoo Upgrade Advisor
sickn33/agentic-awesome-skills
Step-by-step Odoo version upgrade advisor: pre-upgrade checklist, community vs enterprise upgrade path, OCA module compatibility, and post-upgrade validation.
47k GitHub starsUsed in 2 repos~1.3k tokens
DevelopmentAuto-check passed
Token Budget Advisor
affaan-m/ECC
回答する前に、どれだけの回答深度を消費するかについてユーザーに情報に基づいた選択を提供する。ユーザーが回答の長さ、深さ、またはトークンバジェットを明示的に制御したい場合にこのスキルを使用する。トリガー条件："token budget", "token count", "token usage", "token limit", "response length", "answer depth"…
276k GitHub stars~910 tokensUpdated yesterday
AI & LLM EngineeringAuto-check passed
Token Budget Advisor
affaan-m/ECC
在回答前，为用户提供关于消耗多少响应深度的知情选择。当用户明确希望控制响应长度、深度或令牌预算时使用此技能。触发条件："token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed…
276k GitHub stars~927 tokensUpdated yesterday
AI & LLM EngineeringAuto-check passed
Weread Year In Review Video Template
nexu-io/open-design
WeRead-inspired HyperFrames video template for vertical annual reading reports, personal reading dashboards, book-note recaps, and shareable year-in-review stories.
100k GitHub stars~784 tokensUpdated yesterday
Frontend & DesignAuto-check passed
Business Investment Advisor
alirezarezvani/claude-skills
Business investment analysis and capital allocation advisor.
28k GitHub stars~2.5k tokensUpdated 1 mo ago
Business, Finance & HRAuto-check passed

Questions about Huashu Weread Advisor

What does Huashu Weread Advisor do?

How do I install Huashu Weread Advisor in Claude Code?

Run `npx skills add alchaincyf/huashu-weread --skill huashu-weread-advisor -a claude-code`. Or copy the skill folder (the alchaincyf/huashu-weread repository) into .claude/skills/huashu-weread-advisor in your project. Claude Code loads it when a task matches its description.

How do I install Huashu Weread Advisor in Codex?

Run `npx skills add alchaincyf/huashu-weread --skill huashu-weread-advisor -a codex`. Or copy the skill folder (the alchaincyf/huashu-weread repository) into .agents/skills/huashu-weread-advisor in your project. Codex loads it when a task matches its description.

Can I use Huashu Weread Advisor in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alchaincyf/huashu-weread --skill huashu-weread-advisor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/huashu-weread-advisor, .gemini/skills/huashu-weread-advisor, .github/skills/huashu-weread-advisor and .opencode/skills/huashu-weread-advisor in your project.

What does Huashu Weread Advisor need to run?

Going by SKILL.md and its folder, Huashu Weread Advisor needs the command-line tools its instructions call (git) and credentials named WEREAD_API_KEY. Our summary lists: Python 3; A credential in WEREAD_API_KEY.

Does Huashu Weread Advisor access the network?

SKILL.md names 1 domain. In commands or code: i.weread.qq.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Huashu Weread Advisor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Huashu Weread Advisor use?

Huashu Weread Advisor is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Huashu Weread Advisor use?

About 1.4k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Huashu Weread Advisor?

Skills that share tags, products or a category with Huashu Weread Advisor: Advisor Mode (cursor/plugins, 11k stars), Odoo Upgrade Advisor (sickn33/agentic-awesome-skills, 47k stars), Token Budget Advisor (affaan-m/ECC, 276k stars) and Token Budget Advisor (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Huashu Weread Advisor?

alchaincyf (a GitHub user) maintains it in alchaincyf/huashu-weread, which has 152 GitHub stars. The repository was last updated on August 25, 2026.

Source: alchaincyf/huashu-weread on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Huashu Weread Advisor

Facts

At a glance

What it does

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

huashu-weread-advisor

定位

前置依赖

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

2. 「最近读什么」≠「书架主题」

3. 推荐必附 weread:// 深度链接

4. 推荐前必须验证微信读书是否上架

5. 输出走花叔语言风格

检查点设计原则

子命令路由

轻量直答：「我现在在读哪本」

共享子模块

示例

异常与边界条件

数据展示规范（强制）

调用约定

版本自检（静默）

Files

Compare with similar skills

Similar skills

Advisor Mode

Odoo Upgrade Advisor

Token Budget Advisor

Token Budget Advisor

Weread Year In Review Video Template

Business Investment Advisor

Questions about Huashu Weread Advisor