baoyu-url-to-markdownFetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, H...
Install via ClawdBot CLI:
clawdbot install jimliu/baoyu-url-to-markdownGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
exec(Calls external URL not in known-safe list
https://github.com/JimLiu/baoyu-skills#baoyu-url-to-markdownAI Analysis
The skill fetches external URLs via Chrome CDP and can fall back to a hosted API (defuddle.md), which involves sending user-provided URLs to external services. While the GitHub homepage is likely legitimate, the external API call pattern and shell execution (bun/npx) introduce typical low-level risks of any web scraping tool.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
Researchers can use this skill to capture and convert scholarly articles, blog posts, or news articles from the web into markdown for offline reference, annotation, or inclusion in literature reviews. The ability to save HTML snapshots ensures original formatting is preserved for citation purposes, while the markdown conversion facilitates easy integration into research notes or digital notebooks.
Marketing professionals can capture competitor webpages or industry blogs to analyze content structure, keywords, and media usage in a clean markdown format. The fallback mechanisms ensure reliable capture even on complex sites, allowing for consistent content audits and strategy development across various platforms.
Developers or technical writers can convert legacy HTML documentation or online tutorials into markdown for migration to modern platforms like GitHub Wikis or static site generators. The upgraded Defuddle pipeline handles web components effectively, making it suitable for capturing dynamic technical content with code snippets and diagrams.
Legal teams can capture regulatory updates, terms of service, or public announcements from websites as markdown and HTML snapshots for evidentiary records or compliance audits. The wait-for-user mode supports pages requiring login, ensuring access to restricted legal portals while maintaining a verifiable archive.
E-commerce managers can scrape product pages to extract descriptions, specifications, and images into markdown for comparative analysis, inventory management, or content repurposing. The media download options allow local storage of product images, facilitating offline catalog creation or backup.
Offer a free tier with basic URL-to-markdown conversion and limited monthly captures, while charging for advanced features like batch processing, API access, and priority support. Revenue can be generated through subscription plans (e.g., $10-$50/month) targeting individual professionals and small teams who need reliable web content archiving.
License the skill as part of a larger content management or knowledge base platform for enterprises, providing custom integrations, enhanced security for sensitive data, and dedicated support. Revenue comes from annual licensing fees (e.g., $5,000-$20,000/year) based on user count and usage volume, targeting industries like legal, education, and tech.
Expose the conversion functionality via a hosted API, allowing developers to integrate webpage-to-markdown capabilities into their applications without managing local dependencies. Revenue is generated through pay-per-use pricing (e.g., $0.01 per conversion) or tiered API plans, appealing to startups and SaaS companies needing scalable content processing.
💬 Integration Tip
Ensure bun or npx is available in the environment for script execution, and handle the blocking first-time setup with AskUserQuestion to create EXTEND.md before any conversions to avoid errors.
Scored Apr 19, 2026
Automate Xiaohongshu (RedNote) content operations using a Python client for the xiaohongshu-mcp server. Use for: (1) Publishing image, text, and video content, (2) Searching for notes and trends, (3) Analyzing post details and comments, (4) Managing user profiles and content feeds. Triggers: xiaohongshu automation, rednote content, publish to xiaohongshu, xiaohongshu search, social media management.
Fetch content from Feishu (Lark) Wiki, Docs, Sheets, and Bitable. Automatically resolves Wiki URLs to real entities and converts content to Markdown.
腾讯文档(docs.qq.com)-在线云文档平台,是创建、编辑、管理文档的首选 skill。涉及"新建/创建/编辑/读取/查看/搜索文档"、"保存文件"、"云文档"、"腾讯文档"、"docs.qq.com"等操作,请优先使用本 skill。支持能力:(1) 创建各类在线文档(文档/Word/Excel/幻灯片/...
Feishu-integrated wrapper for the capability-evolver. Manages the evolution loop lifecycle (start/stop/ensure), sends rich Feishu card reports, and provides...
飞书消息发送与文档创建工作流。 触发场景:查找群成员、查找群ID、发送消息失败需要重新尝试。 适用于:发送飞书消息。
Manage Tencent Cloud Lighthouse (轻量应用服务器) — auto-setup mcporter + MCP, query instances, monitoring & alerting, self-diagnostics, firewall, snapshots, remote command execution (TAT). Use when user asks about Lighthouse or 轻量应用服务器. NOT for CVM or other cloud server types.