← Back to Skills Marketplace
Fandeng
by
mikeclaw007
· GitHub ↗
· v0.1.0
· MIT-0
162
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install fandeng
Description
Provides summaries and key details of public courses, books, and topics from the 樊登读书 site without accessing paid content.
README (SKILL.md)
樊登读书
用途与边界
- 面向公开课程/书目页的信息检索与内容摘要
- 不提供下载、付费内容绕过或接口逆向能力
- 仅处理公开页面的信息整理
关键入口
- 主页：https://www.dushu.io/
- 课程/书目：站点频道
- 搜索入口：站内搜索
常见任务
- 指定主题的课程清单摘要（讲师、课时、发布时间）
- 书目页面的要点提炼（作者、出版社、核心观点）
- 专题页目录与摘要集合
数据字段
- 课程名称、讲师、课时、发布时间、简介、链接
- 书名、作者、出版社、出版时间、核心观点摘要、链接
- 专题名称、条目列表、采集时间、来源链接
自动化要点
- 页面可能包含动态加载，需等待完成后解析
- 不处理付费内容与下载相关操作
- 频率控制，尊重平台访问限制
示例流程
- 课程摘要：访问课程页 → 抽取讲师/课时/发布时间 → 输出摘要
- 书目要点：访问书目页 → 抽取作者/出版社/观点 → 输出卡片
- 专题汇总：访问专题页 → 抽取目录 → 输出摘要集合
合规提示
- 遵守平台规则，不绕过付费或版权限制
- 结果仅用于内部分析与提醒
Usage Guidance
This skill appears coherent and low-risk: it only contains runtime instructions for summarizing public pages on dushu.io and doesn't request credentials or install code. Before enabling, consider: (1) confirm you are comfortable with the agent visiting that site and that the agent will respect robots.txt and rate limits; (2) ensure the agent is configured not to attempt paid-content access or credential probing; and (3) if the skill later gains code files or an install step, re-evaluate because that would increase risk. If you need extra assurance, ask the publisher for a homepage or source repository to review implementation details.
Capability Analysis
Type: OpenClaw Skill
Name: fandeng
Version: 0.1.0
The skill bundle contains metadata and instructions for an AI agent to perform information retrieval and summarization of public content from the '樊登读书' (dushu.io) website. The SKILL.md file explicitly limits the scope to public data, prohibits bypassing paywalls, and lacks any indicators of malicious intent, data exfiltration, or harmful execution.
Capability Assessment
Purpose & Capability
Name and description match the instructions: the SKILL.md describes extracting public course/book/topic metadata from https://www.dushu.io/ and does not request unrelated capabilities (no credentials, no unrelated binaries).
Instruction Scope
Instructions are narrowly scoped to visiting public pages, waiting for dynamic loading, extracting listed fields, and respecting rate limits; they explicitly prohibit accessing paid content or bypassing protections. They do not instruct reading unrelated files, env vars, or sending data to external endpoints.
Install Mechanism
No install spec or code files are present (instruction-only), so nothing will be written to disk or downloaded during install.
Credentials
The skill requests no environment variables, credentials, or config paths; this is proportionate for a public-page summarization helper.
Persistence & Privilege
The skill is not marked always:true and is user-invocable. Autonomous invocation is allowed by platform default but is not combined with other red flags here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install fandeng - After installation, invoke the skill by name or use
/fandeng - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
fandeng-hot-trend skill v0.1.0
- Initial release for extracting and summarizing public course and book information from 樊登读书 (dushu.io).
- Supports tasks like course/lesson summaries, extracting key points from book pages, and compiling topic directories.
- Handles only publicly available content; no access to paid or download-restricted material.
- Emphasizes compliance with platform rules and rate limits.
Metadata
Frequently Asked Questions
What is Fandeng?
Provides summaries and key details of public courses, books, and topics from the 樊登读书 site without accessing paid content. It is an AI Agent Skill for Claude Code / OpenClaw, with 162 downloads so far.
How do I install Fandeng?
Run "/install fandeng" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Fandeng free?
Yes, Fandeng is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Fandeng support?
Fandeng is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Fandeng?
It is built and maintained by mikeclaw007 (@mikeclaw007); the current version is v0.1.0.
More Skills