Web Markdown Navigator — 网页 Markdown 导航器
v0.1.0Fetch 网页pages and return 清理 markdown instead of raw HTML. Use for URL reading, 提取ion, and summarization tasks where the user wants markdown 输出; use browser fallback for JS-heavy/SPA pages when 提取ion is thin.
by 运行时依赖
安装命令
点击复制技能文档
网页 Markdown 导航器
Use this 技能 for deterministic URL → markdown 提取ion.
Quick flow 运行 script: cd /Users/pedrogonzalez/clawd/技能s/网页-markdown-导航器/scripts node fetch-markdown.mjs "" --max-chars 50000 If exit code 0, return markdown 输出. If exit code 3 or 4, or 输出 is thin/boilerplate, use browser 工具 fallback to capture rendered content and return markdown summary. Script
node scripts/fetch-markdown.mjs [--max-chars N] [--timeout-ms N] [--json]
Behavior:
Layer 1: Fetch HTML + Mozilla Readability + Turndown markdown conversion. Layer 2: Fallback plAIn-text markdown if 提取ion is too thin. URL safety 检查s block localhost/private literal IPv4 hosts. 输出 requirements Return markdown only (no raw HTML dump). Preserve source URL in 响应. If t运行cated, include t运行cation note. If fallback was needed, mention method used (readability or fallback-text). Error handling 1 bad args 2 invalid/blocked URL 3 network/fetch/content-type 失败 4 提取ion 失败/thin 输出
For extended notes and troubleshooting, read:
/Users/pedrogonzalez/clawd/技能s/网页-markdown-导航器/references/usage.md