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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/danielrosehill/document-to-markdown-plugin --skill setup命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | setup |
| description | Use when you need to initialize the document-to-markdown environment for the first time |
Initialize the plugin environment. Creates the data directory, sets up the Python virtual environment, installs extraction libraries, verifies system dependencies, and configures the default extractor.
${CLAUDE_USER_DATA:-${XDG_DATA_HOME:-$HOME/.local/share}/claude-plugins}/document-to-markdown/ if it does not exist, including subdirectories: venv/, cache/, state/.pdftotext --version, ocrmypdf --version, tesseract --version. If any are missing, print the installation command (sudo apt install poppler-utils ocrmypdf tesseract-ocr) but do not run sudo automatically.$CLAUDE_USER_DATA/document-to-markdown/venv/ using uv venv.marker-pdf pymupdf4llm camelot-py[cv] tabula-py pandas using uv pip install.docling (noted as heavy/slower).config.json to $CLAUDE_USER_DATA/document-to-markdown/ with contents: {"default_extractor": "marker"}.python -c "import marker_pdf; print('OK')").config.json written with default extractor set to markersudo apt install automatically; always show the command and ask the user to run it if tools are missing