Extract structured data (all available fields with values) from a page saved locally as an HTML file, optionally following a schema. Do not invoke when the user provides a URL. When invoking, pass the user's full request verbatim as args — do not pre-parse file paths and don't rephrase it.
安装
npx skills add zytedata/claude-skills --skill scrape-analyze-pagenpx skills add zytedata/claude-skills --skill scrape-analyze-page -a claude-code -gnpx skills add zytedata/claude-skills --skill scrape-analyze-page -a codex -ggemini skills install https://github.com/zytedata/claude-skills.git --path skills/scrape-analyze-pagegh skill install zytedata/claude-skills scrape-analyze-pagegit clone --depth 1 https://github.com/zytedata/claude-skills /tmp/zytedata__claude-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/zytedata__claude-skills/skills/scrape-analyze-page ~/.claude/skills/scrape-analyze-page # Claude Code
cp -R /tmp/zytedata__claude-skills/skills/scrape-analyze-page ~/.agents/skills/scrape-analyze-page # Codex, Cursor, Gemini CLI, Copilot, OpenCode