Skip to main content
在 Manus 中运行任何 Skill
一键导入

defuddle

星标1
分支0
更新时间2026年7月9日 07:11

Extract clean markdown content from web pages using Defuddle CLI, attach a unified Obsidian frontmatter, auto-translate English content into academic Chinese, download images to the local 附件/ folder (rewriting references to Obsidian ![[file]] embeds), and save to the 网页裁剪/ directory. Always dedupes first — before fetching any URL it greps the 网页裁剪/ directory's frontmatter 来源 field to check whether that page was already clipped; if so it reuses the existing note as-is (never re-fetches or alters it) and only builds a wikilink to it. Use instead of WebFetch when the user provides a URL to read, clip, archive, or to batch-clip the sub-links of an index/trail page — for online documentation, articles, blog posts, GitHub READMEs, or any standard web page. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly.

安装

用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。

文件资源管理器
6 个文件
SKILL.md
readonly