awesome-wereadSAFE
基于微信读书官方 Agent Skill 的二创项目精选 · Curated projects built on WeRead's official Agent Skill (released 2026-05-17)
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
精选「微信读书」官方 Agent Skill,以及一切基于它的二创项目。
语言: 简体中文 · English
最后更新: 2026-06-01 (UTC+08:00)
2026 年 5 月 17 日,微信读书发布了官方 Agent Skill —— 一个用个人 API Key(wrk-...)即可访问的 Agent Gateway,提供书架、阅读统计、划线、想法、书籍搜索等能力。48 小时内,社区已经在它之上长出一波二创项目。
这个清单收录的就是它们。
收录标准。 项目必须基于 2026-05-17 发布的官方 Agent Gateway / API Key。依赖 cookie 抓取、浏览器自动化或其他非官方接口的项目不在范围内 —— 这些大多早于官方 Skill 出现,有自己独立的生态。
目录
- 官方资源
- Skill 安装包
- 工作流与助手
- 命令行与 SDK
- MCP 服务
- 第三方同步
- 桌面挂件与可视化
- 体验归档
- 贡献指南
- 许可
官方资源
Skill 安装包
可以直接装进 Skill-aware Agent 的 Skill 包 —— 一次安装,到处可用。
6a15965c73fcOBSERVED · 2026-10-10Install
Commands as the repository documents them. They are shown, not run.
git clone --depth 1 https://github.com/viewer12/weread-mirror.git /tmp/weread-mirror-run
git clone https://github.com/kejixiaoliang/read-persona /tmp/read-persona-run
git clone --depth 1 https://github.com/AstrophelXD/WeReadAura /tmp/wereadaura-run-20260525150759
npm install --no-audit --no-fund
git clone --depth 1 https://github.com/Kalmaegi/weread-analyzer /tmp/awesome-weread-runs.AuGRSv/Kalmaegi-weread-analyzer
git clone --depth 1 https://github.com/SpaceTrave1/weread-deep-insights /tmp/awesome-weread-runs.aY4IvX/SpaceTrave1-weread-deep-i
Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned | |
| claude-desktop | mentioned | |
| codex | mentioned | |
| copilot | mentioned | |
| cursor | mentioned | |
| openclaw | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: weread-essay-skill description: 微信读书读后感写作助手。帮助用户基于某本书或某个章节,生成一篇带有个人见解的读后感,正文严格控制原文摘抄,附录完整保留所有划线内容及即时感想。底层依赖 weread-skills(微信读书原子 API)和 huashu-weread-advisor(微信读书高阶顾问工作流)。当用户说「写一篇读后感」「帮我整理笔记写感想」「这本书/这章我想写篇公众号文章」时触发。 version: 1.0.0 tags: [] --- # weread-essay-skill 微信读书读后感写作助手。把你在微信读书里的划线和想法,变成一篇真正值得发的文章。 > ⚠️ **飞书文档链接已知限制**:`feishu_doc_read` 需从飞书评论等特定上下文触发,当前独立会话不可用;`web_extract` 对 `my.feishu.cn` 返回 400(有登录验证)。**两者均失败时,直接请用户粘贴文档正文**——这是最可靠的方式。 ## 定位 底层有两个 skill 提供数据: - **weread-skills**(`~/.hermes/skills/weread-skills/SKILL.md`):微信读书原子 API,接口文档和参数说明 - **huashu-weread-advisor**(`~/.hermes/skills/huashu-weread-advisor/SKILL.md`):工作流编排规则和数据解读规范 本 skill 在这两个 skill 之上,编排「读后感写作」这一特定工作流:先拉取用户的微信读书划线笔记,再结合用户提供的背景材料,最后生成一篇正文+附录结构的读后感。 ## 核心能力 | 输出 | 说明 | |------|------| | 读后感正文 | 文学性+理性分析+情感抒发,2-4个核心论点,正文摘抄≤3处 | | 附录 | 完整保留所有划线原文,每条附即时感想/反思 | ## 触发条件 典型话术: - 「写一篇读后感」 - 「帮我整理笔记,写篇感想」 - 「这本书/这章我想写篇公众号文章」 - 「想把我的划线整理成一篇读书笔记」 ## 前置依赖 - `WEREAD_API_KEY` 环境变量(已通过 weread-skills 配置) - 微信读书账号中已有该书的划线记录 ## 工作流 详见 `workflows/essay.md` ## 输出语言 正文和附录**全部使用中文**,不加标题或段落混入英文。除非用户原始输入是英文,否则不用英文写作。
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (3 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (9)
getnote-save-payload.json
http://127.0.0.1:8128/weread-report.html
http://127.0.0.1:8128/reading-persona.html
@google/genai
| [KevinChen1994/weread2notion](https://github.com/KevinChen1994/weread2notion) | Notion | WeRead → Notion sync tool, authenticated with a wrk- API Key. | [Summary](docs/promo/runs/2026-05-26/KevinChe
| [Kalmaegi/weread-analyzer](https://github.com/Kalmaegi/weread-analyzer) | Web | Reading-profile analyzer built on the official WeRead API Key. | [Summary](docs/promo/runs/2026-05-25/Kalmaegi-weread-
| [Kalmaegi/weread-analyzer](https://github.com/Kalmaegi/weread-analyzer) | Web | 基于微信读书官方 API Key 的阅读画像分析项目。 | [记录](docs/promo/runs/2026-05-25/Kalmaegi-weread-analyzer/summary.md) · [截图](docs/promo/r
docs/promo/runs/2026-05-25/SpaceTrave1-weread-deep-insights/artifacts/weread_deep_report-screenshot.jpg
README.md:9:This skill gives your OpenClaw agent full access to your WeRead (微信读书) data:
Gates applied: no_behavioural_pass.
6a15965c73fcfull audit observations/trust-audit/skill/benzema216__awesome-weread.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 6a15965c73fc | SAFE | B | 89 | first audit |
Questions
What does the awesome-weread skill do?
基于微信读书官方 Agent Skill 的二创项目精选 · Curated projects built on WeRead's official Agent Skill (released 2026-05-17)
Is awesome-weread safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can awesome-weread access on my machine?
The audit observed that it reaches the network and runs shell commands. Each of those is consistent with what it says it does. Secrets in the source: none found.
Which assistants does awesome-weread work with?
Its documentation mentions claude-code, claude-desktop, codex, copilot, cursor and openclaw. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (6a15965c73fc), read on 2026-10-10. The repository is watched, and a new audit runs when it changes — this is the first audit.