weread-skills
Skill0 starsChanged 2 months agoMITView on GitHub
微信读书助手 — 搜索书籍、管理书架、查看笔记划线、浏览书评、阅读统计、发现推荐好书
- Reads credentials
- Sends data out
5 other projects use a version of this, 4 of them edited.
Adopted by
Most recently taken up by
- gandli/weread-skillsedited, first seen Oct 13, 2026
- Jansen611/Agent-Skillsedited, first seen Oct 9, 2026
- uvwt/agentdock-skillstheir own version, first seen Aug 30, 2026
- lcy362/personal-skills-manageredited, first seen Jun 4, 2026
- HK-hub/AgentSkillsedited, first seen Mar 2, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 4
- gandli/weread-skills★ 1268% same
- HK-hub/AgentSkills★ 650% same
- Jansen611/Agent-Skills★ 281% same
- lcy362/personal-skills-manager★ 152% same
Wrote their own version · 1
- uvwt/agentdock-skills★ 6same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- adversarial-debateSkill
- agent-mail-readinessSkill
- crazy-wechat-autoSkill
- feishu-note-appenderSkill
- github-auto-releaseSkill
- leaderSkill
- neat-freakSkill
- qweatherSkill
- self-improving-agentSkill
- web-searchSkill
The file
Files
WeRead — 微信读书助手
来源与改动(Apache-2.0 §4 要求标注修改):本 skill 复制自 Tencent/WeChatReading v1.0.4,Copyright © 2026 Tencent, Apache-2.0 License(完整文本见
LICENSE)。 本文件相对原版有改动:① 内部文档引用路径*.md→references/*.md(对齐 kuang-skills 仓约定); ② 「鉴权」节补充 API key 从~/.claude/.secrets/weread.env读取的约定(对齐本仓 web-search skill)。 其余内容、接口规范、字段说明均为 Tencent 原文,未改动。
通过 Agent API Gateway 调用微信读书接口,提供搜索、书架、笔记、书评等能力。
支持的能力
| 能力 | 说明 | 用户示例 | 详细说明 |
| 搜索书籍 | 在书城搜索 | "帮我搜一下三体" | references/search.md |
| 书籍信息 | 查看书籍详情、章节目录、阅读进度 | "这本书有多少章" "我读到哪了" | references/book.md |
| 书架管理 | 查看书架 | "看看我的书架" | references/shelf.md |
| 阅读统计 | 阅读时长、天数、偏好分析、阅读统计摘要 | "我这个月读了多久" "今年读了几本书" | references/readdata.md |
| 笔记划线 | 查看个人笔记数量与内容,包括划线、想法/点评、书签数量 | "看看我在三体里的笔记" "导出我的划线" "在这本书有多少笔记" | references/notes.md |
| 章节热门划线 | 查看书籍/章节热门划线、划线热度及划线下想法 | "看看这章有什么热门划线" "这段话下面有什么想法" | references/notes.md |
| 书籍点评 | 查看书籍的公开点评 | "三体这本书有什么点评?" "看看推荐的点评" | references/review.md |
| 推荐好书 | 个性化推荐/相似推荐 | "给我推荐几本书" | references/discover.md |
根据用户意图参考对应说明文件了解接口参数、回包结构和工作流。
接口调用规范
统一入口
POST https://i.weread.qq.com/api/agent/gateway鉴权
- Header:
Authorization: Bearer $WEREAD_API_KEY WEREAD_API_KEY自动从~/.claude/.secrets/weread.env读取(本仓不含真 key,.env.example为占位符模板);文件不存在时回退到同名 shell 环境变量- key 格式
wrk-xxxxxxxx,获取地址 https://weread.qq.com/r/weread-skills - curl 不像会自动加载 key——先
set -a; source ~/.claude/.secrets/weread.env; set +a(set -a让赋值自动 export 给子进程) - 未配置时不抛 traceback,报
WEREAD_API_KEY missing — set in ~/.claude/.secrets/weread.env or WEREAD_API_KEY env var - API Key 绑定用户身份(vid),需要用户身份的接口会自动注入,无需手动传 vid
请求格式
- Method:POST
- Content-Type:application/json
- Body:JSON,
api_name指定接口,其余为接口参数,每次请求必须带skill_version
curl -X POST "https://i.weread.qq.com/api/agent/gateway" \
-H "Authorization: Bearer $WEREAD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"api_name": "/store/search", "keyword": "三体", "count": 10, "skill_version": "1.0.4"}'请求 few-shot
正确:业务参数平铺在 body 顶层。
{"api_name":"/user/notebooks","count":100,"skill_version":"1.0.4"}正确:下一页继续平铺 lastSort。
{"api_name":"/user/notebooks","count":100,"lastSort":1516907353,"skill_version":"1.0.4"}错误:不要把业务参数包在 params 内。
{"api_name":"/user/notebooks","params":{"count":100,"lastSort":1516907353},"skill_version":"1.0.4"}上面的错误写法会导致 count、lastSort 未被转发,后端按默认值返回第一页,看起来像分页失效。
响应格式
- JSON,回包经过字段裁剪,只返回核心字段
errcode非 0 时表示错误,给出中文提示- 发送
{"api_name": "/_list"}可查看所有可用接口及参数定义
通用规则
- 版本上报:每次请求 body 必须包含
"skill_version": "1.0.4"(取本文件顶部 version 字段的值),用于服务端检查版本更新。如果回包中出现upgrade_info字段,必须立即暂停当前操作,按照upgrade_info.message中的指引完成升级,升级完成后再重新执行用户请求,不得忽略该字段 - 参数平铺:业务参数必须和
api_name、skill_version放在同一层;不要包在params、data、body等对象里。只有接口文档明确声明的数组/对象字段(如/book/readreviews的reviews)才允许作为业务字段传入。 - 能力文档预检:调用任何接口前,必须先根据「支持的能力」表阅读对应说明文件(如阅读统计先读
references/readdata.md,书架先读references/shelf.md),确认接口参数、字段含义、单位、计数口径和工作流;禁止仅凭字段名或经验猜测含义。 - 字段解释优先级:解释接口回包时,以对应说明文件中的字段说明为准;如果回包字段名和直觉含义冲突,必须服从说明文件,不得直接翻译字段名。
- bookId 解析:用户输入书名时,先调
/store/search获取 bookId,再执行后续操作 - 书架数量:使用
/shelf/sync回答“书架有多少本书/多少条目”时,必须按books.length + albums.length + (mp 非空 ? 1 : 0)计算;albums[]是专辑/有声书,也属于书架里的书,详细规则见references/shelf.md - 结果展示:列表用编号展示方便选择;搜索结果重点展示书名、作者、评分;展示接口回包信息时,字段禁止直接翻译,应该参考文件中的说明内容提供
- 上下文衔接:对话中记住已查询的 bookId,后续操作无需用户重复提供
- 深度链接:优先使用接口回包中的
deepLink字段作为跳转链接,展示为[打开阅读]({deepLink});若回包没有deepLink,不要自行拼接weread://链接 - 数据展示规范:
- 时间戳:所有 Unix 时间戳字段(如
updateTime、createTime、finishTime、readUpdateTime等),展示时须转为 YYYY-MM-DD 格式(如1748563200展示为"2025-05-30"),不得直接展示原始数字 - 阅读时长:单位为秒,展示时转为"X小时Y分钟"格式
深度链接
在展示书籍、章节、划线、想法等内容时,如果回包中有 deepLink 字段,直接使用该字段值作为跳转链接。
- 跳转链接展示为 Markdown 超链接格式:
[打开阅读]({deepLink})。 - 各接口回包中可能包含
deepLink字段,如有则直接使用。 - 若回包中没有
deepLink字段,不要尝试手动拼接weread://链接。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

