← 返回 Skills 市场
184
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install weread-reading-recommender
功能描述
Use this skill when the user wants to export local WeRead records, normalize WeRead data, analyze reading preferences from WeRead history, or get book recomm...
安全使用建议
This skill appears coherent and local-first. Before installing or running it: (1) review the two Python scripts yourself (they are included) and run them in a safe environment; (2) only provide your WeRead cookie locally (prefer --cookie-file or an env var), and never paste it into public chat or remote storage; (3) note that the exporter makes HTTPS requests to weread.qq.com (expected) — if you are uncomfortable providing a live cookie, you can run the normalizer against the provided sample raw JSON instead; (4) verify outputs do not contain the cookie (SKILL.md states this and the scripts are written not to include it); and (5) run the scripts with network access blocked if you only want to test normalization on sample data.
功能分析
Type: OpenClaw Skill
Name: weread-reading-recommender
Version: 1.0.1
The skill is a local-first tool designed to export and normalize WeRead (微信读书) data for personalized book recommendations. The scripts (export_weread.py and normalize_weread.py) use standard libraries to interact with legitimate WeRead APIs and process data locally, with explicit safeguards in the code and SKILL.md instructions to prevent the leakage or storage of authentication cookies in logs or exported files.
能力评估
Purpose & Capability
Name/description match the delivered assets. The repo contains exporter and normalizer scripts that operate on a WeRead cookie and call weread.qq.com endpoints — exactly what a WeRead export/recommendation skill would need. There are no unrelated credentials or services requested.
Instruction Scope
SKILL.md instructs the agent to check for a local cookie, run the provided export and normalize scripts, and then reason from the normalized JSON. The scripts access only local cookie sources and the official weread.qq.com endpoints; they do not read other system files or send data to unexpected endpoints. The SKILL.md also contains explicit privacy rules (do not write or echo the cookie).
Install Mechanism
No install spec is provided (instruction-only plus two local scripts). Nothing will be downloaded or installed from third-party URLs, so there is low install-time risk.
Credentials
The only sensitive input the skill uses is a WeRead cookie (via --cookie, --cookie-file, or env var like WEREAD_COOKIE). No other secrets or unrelated environment variables are requested. The cookie request is proportional to the stated functionality, but users should recognize the cookie is an authentication credential and handle it cautiously.
Persistence & Privilege
Skill is not always-enabled, does not request elevated system persistence, and there is no code that modifies other skills or global agent configs. Autonomous invocation is allowed (platform default) but does not combine with other high-risk behaviors here.
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-reading-recommender - 安装完成后，直接呼叫该 Skill 的名称或使用
/weread-reading-recommender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
v1.0.1
- Added planning and reference documentation: PLAN.md, SPEC.md, TODO.md
- Removed default data files: data/weread-raw.json and data/weread-normalized.json
- No functional or workflow changes; updates focus on documentation and project organization.
v1.0.0
Initial release of WeRead Reading Recommender.
- Local-first tool to export, normalize, and analyze WeRead (微信读书) reading data.
- Recommends books based on reading history and/or current learning goals.
- Checks for existing local cookie/environment sources before prompting user for setup.
- Data privacy-focused: uses local cookies only, never echoes cookies, and avoids remote storage.
- Provides structured recommendations with rationale and profile analysis, supporting both safe and exploratory picks.
元数据
常见问题
Weread Reading Recommender 是什么？
Use this skill when the user wants to export local WeRead records, normalize WeRead data, analyze reading preferences from WeRead history, or get book recomm... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 184 次。
如何安装 Weread Reading Recommender？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install weread-reading-recommender」即可一键安装，无需额外配置。
Weread Reading Recommender 是免费的吗？
是的，Weread Reading Recommender 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Weread Reading Recommender 支持哪些平台？
Weread Reading Recommender 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 Reading Recommender？
由 CengSin（@cengsin）开发并维护，当前版本 v1.0.1。
推荐 Skills