Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.
安装
npx skills add kepano/obsidian-skills --skill defuddlenpx skills add kepano/obsidian-skills --skill defuddle -a claude-code -gnpx skills add kepano/obsidian-skills --skill defuddle -a codex -ggemini skills install https://github.com/kepano/obsidian-skills.git --path skills/defuddlegh skill install kepano/obsidian-skills defuddlegit clone --depth 1 https://github.com/kepano/obsidian-skills /tmp/kepano__obsidian-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/kepano__obsidian-skills/skills/defuddle ~/.claude/skills/defuddle # Claude Code
cp -R /tmp/kepano__obsidian-skills/skills/defuddle ~/.agents/skills/defuddle # Codex, Cursor, Gemini CLI, Copilot, OpenCode