← 返回 Skills 市场
183
总下载
1
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install weread
功能描述
微信读书(WeRead)数据查询与笔记管理技能。获取书架、搜索书籍、查看阅读进度/时长、获取笔记划线、热门书评、章节信息、随机笔记抽取和批量导出。当用户提到"微信读书"、"WeRead"、"书架"、"读书进度"、"划线"、"笔记"、"书评"、"在读"、"读完"、"阅读时长"、"读书回顾"、"导出笔记"时使用。
安全使用建议
This skill needs your WeRead session cookie to access your account data — providing that cookie gives the skill the same access as your logged-in browser session (reads bookshelf, notes, highlights, etc.). The code appears to store everything locally under ~/.weread and only calls weread.qq.com. Before installing: (1) review the code yourself if you can (scripts are plain Python); (2) only run on a machine you trust and avoid pasting cookies on shared/remote hosts; (3) keep the cookie file permissions as 600 and remove the cookie file when you stop using the skill; (4) if you are concerned, create a disposable/new WeRead session and use that cookie (or revoke the session / rotate credentials after use). If you want extra assurance, run the scripts locally (inspect outputs) rather than granting the agent automated browser access to extract cookies.
功能分析
Type: OpenClaw Skill
Name: weread
Version: 1.0.0
The skill provides legitimate functionality for managing WeRead data but includes high-risk credential handling behaviors. Specifically, `weread_login.py` attempts to programmatically access and query the Chrome browser's local `Cookies` SQLite database to extract session tokens. Additionally, `SKILL.md` instructs the AI agent to extract cookies via `document.cookie` and write them to a local file (`~/.weread/cookie`). While these actions are aligned with the stated purpose of the skill and the cookie extraction is limited to the `weread.qq.com` domain, the direct access to sensitive browser profile data and the automated handling of authentication secrets represent significant security risks.
能力评估
Purpose & Capability
Name/description match the code and runtime instructions: all scripts call weread.qq.com endpoints and implement bookshelf, notes, highlights, progress, export, and random-review features described in SKILL.md/README. There are no unrelated services or credentials requested.
Instruction Scope
SKILL.md instructs the agent/user to provide a WeRead browser session cookie (document.cookie or Chrome cookies) and to run local Python scripts under ~/.openclaw/workspace/skills/weread/scripts/. Asking to extract and store the session cookie is sensitive but necessary for the stated functionality. The instructions do not ask the agent to read unrelated system files or transmit data to third-party endpoints.
Install Mechanism
No install spec (instruction-only install) and repository contains Python scripts only. Nothing is downloaded from arbitrary URLs. Scripts read/write only to ~/.weread and use standard library modules; the install mechanism is low-risk.
Credentials
No environment variables or external credentials are requested. The only sensitive input is the WeRead session cookie, which is appropriate for a tool that interacts with a web account. The cookie file is stored under ~/.weread/cookie and the code sets file mode to 600.
Persistence & Privilege
Skill is not always-enabled, does not request elevated privileges, and does not attempt to modify other skills or system-wide configuration. It persists user data under ~/.weread (expected behaviour for export/local cache).
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install weread - 安装完成后,直接呼叫该 Skill 的名称或使用
/weread触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release: bookshelf, notes, highlights, reading stats, random review picker, notes export, morning report integration
元数据
常见问题
WeRead (微信读书) 是什么?
微信读书(WeRead)数据查询与笔记管理技能。获取书架、搜索书籍、查看阅读进度/时长、获取笔记划线、热门书评、章节信息、随机笔记抽取和批量导出。当用户提到"微信读书"、"WeRead"、"书架"、"读书进度"、"划线"、"笔记"、"书评"、"在读"、"读完"、"阅读时长"、"读书回顾"、"导出笔记"时使用。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 183 次。
如何安装 WeRead (微信读书)?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install weread」即可一键安装,无需额外配置。
WeRead (微信读书) 是免费的吗?
是的,WeRead (微信读书) 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
WeRead (微信读书) 支持哪些平台?
WeRead (微信读书) 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 WeRead (微信读书)?
由 陈源泉(@chenyqthu)开发并维护,当前版本 v1.0.0。
推荐 Skills