Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add alchaincyf/huashu-weread --skill huashu-wereadgit clone --depth 1 https://github.com/alchaincyf/huashu-wereadWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alchaincyf/huashu-weread/huashu-weread)<a href="https://agentmods.dev/skills/alchaincyf/huashu-weread/huashu-weread"><img src="https://agentmods.dev/badge/skills/alchaincyf/huashu-weread/huashu-weread/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alchaincyf/huashu-weread/huashu-weread"><img src="https://agentmods.dev/badge/skills/alchaincyf/huashu-weread/huashu-weread.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00240 | $0.02974 |
| Opus 5.5 | $0.00096 | $0.01190 |
| Sonnet 5.5 | $0.00048 | $0.00595 |
| Haiku 4.5 | $0.00024 | $0.00297 |
Grade A, and why
huashu-weread-advisor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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） |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 143 lines · 240 tokens per session scan A 580c3b5f1892
huashu-weread-advisor is a skill published in the GitHub repository alchaincyf/huashu-weread (159 stars, last pushed 2mo ago), licensed MIT. It adds 240 tokens to every session and 2,974 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.