weread-skills
Interface with WeChat Reading to manage your library, notes, and reading progress.
Install
mkdir -p .claude/skills/weread-skills && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10971" && unzip -o skill.zip -d .claude/skills/weread-skills && rm skill.zipInstalls to .claude/skills/weread-skills
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
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Key capabilities
- →Searches books
- →Manages bookshelves
- →Exports notes and highlights
- →Provides reading statistics
How it works
It interfaces with WeRead APIs to provide access to book data, user shelves, and reading statistics.
Inputs & outputs
When to use weread-skills
- →Searching for books
- →Viewing reading statistics
- →Exporting personal notes and highlights
About this skill
WeRead — 微信读书助手
通过 Agent API Gateway 调用微信读书接口,提供搜索、书架、笔记、书评和好书推荐等能力。
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" | 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" | book.md |
| 书架管理 | 查看书架 | "看看我的书架" | 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" | 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" | 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" | 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" | review.md |
| 推荐好书 | 个性化推荐/相似推荐 | "给我推荐几本书" | 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从环境变量获取,格式wrk-xxxxxxxx- 若未设置,提示用户:
export WEREAD_API_KEY=<你的apikey> - 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", "scope": 10, "context": "帮我搜一下三体", "skill_version": "1.0.6"}'
请求 few-shot
正确:业务参数平铺在 body 顶层。
{"api_name":"/user/notebooks","count":100,"skill_version":"1.0.6"}
正确:下一页继续平铺 lastSort。
{"api_name":"/user/notebooks","count":100,"lastSort":1516907353,"skill_version":"1.0.6"}
错误:不要把业务参数包在 params 内。
{"api_name":"/user/notebooks","params":{"count":100,"lastSort":1516907353},"skill_version":"1.0.6"}
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": "1.0.6"(取本文件顶部 version 字段的值),用于服务端提示版本更新。如果回包中出现upgrade_info,它只是非阻塞升级通知:先使用同一回包中的业务数据完成当前用户请求,再简要提示用户后续可升级。不要暂停、重试或重新执行当次请求,也不要未经用户授权下载或替换文件。 - 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
readdata.md,书架先读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
- 搜索与推荐上下文上报:调用
/store/search、/book/recommend或/book/similar时必须传context。单轮请求传用户触发本次调用的原始问题;依赖多轮对话时传“当前原话 + 必要上下文摘要”。只包含理解本次搜索或推荐所需的信息,不上传无关对话、系统提示、完整工具回包、API Key 或其他凭据。具体规则见search.md和discover.md - 书籍跳转链接:优先使用接口回包中的
readerLink作为直达阅读器链接,展示为[打开阅读]({readerLink});没有readerLink但有deepLink时,将deepLink展示为[查看详情]({deepLink});两个字段都没有时不要自行拼接链接 - 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
书籍跳转链接
在展示书籍、章节、划线、想法等内容时,直接使用接口回包中的链接字段,不要自行拼接 URL。
- 回包有
readerLink时,展示为[打开阅读]({readerLink})。 - 回包没有
readerLink但有deepLink时,展示为[查看详情]({deepLink})。 - 两个字段同时存在时,优先返回
readerLink;仅在用户需要书籍详情入口时额外展示deepLink。 - 两个字段都没有时,不要尝试手动拼接
weread://或https://weread.qq.com/链接。
When not to use it
- →When the user does not have a WeRead account
- →When the API key is missing
Prerequisites
Limitations
- →Requires API key
- →Limited to WeRead platform
How it compares
It provides a programmatic interface to WeRead features that are typically only available via the app.
Compared to similar skills
weread-skills side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| weread-skills (this skill) | 0 | 6mo | Review | Beginner |
| session-export | 0 | 5mo | No flags | Beginner |
| cc-history | 1 | 9mo | Review | Intermediate |
| vibe-sunsang-growth | 0 | 5mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
session-export
CauchyIO
Export a project's Claude Code sessions into a readable transcript dump (the input the project-timeline skill needs). Walks the user through choosing the project, scoping which sessions to include (date window, excluding meta/plugin runs), and warns about secrets before writing. Use when the user wa
cc-history
solatis
Reference documentation for analyzing Claude Code conversation history files
vibe-sunsang-growth
fivetaku
Growth report generator — analyzes AI-collaboration session data and produces a progression report using the v2 level system (6 axes × 7 levels, 0.5 increments). Korean triggers: "성장 리포트", "성장 분석", "얼마나 성장했는지", "레벨 체크", "성장 트래킹". English triggers: "growth report", "growth tracking", "level check".
q
DavidROliverBA
Fast SQLite-based vault search using FTS5 full-text search index
markitdown
K-Dense-AI
Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs/Office files, transcribing audio, performing OCR on images, extracting YouTube transcripts, or processing batches of files. Supports 20+ formats including DOCX, XLSX, PPTX, PDF, HTML, EPUB, CSV, JSON, images with OCR, and audio with transcription.
pdf-processing
Ming-Kai-LC
Comprehensive PDF processing techniques for handling large files that exceed Claude Code's reading limits, including chunking strategies, text/table extraction, and OCR for scanned documents. Use when working with PDFs larger than 10-15MB or more than 30-50 pages.