{
  "markdown": "[English](README.md) | [中文](README_CN.md)\n\n# Translate PDF Skill\n\nTranslate PDF documents to any language while preserving the original structure, layout, colors, and styling.\n\n## The Problem\n\nTranslating PDF documents is typically painful:\n- Copy-paste loses all formatting\n- Online tools mangle the layout\n- Professional translation services are expensive and slow\n- Technical diagrams and org charts are especially difficult\n\n## The Solution\n\nThis Claude Code skill translates PDF text **in place**, preserving:\n- ✅ Original layout and positions\n- ✅ Background colors (yellow boxes, blue headers, etc.)\n- ✅ Font sizes and text colors\n- ✅ Document structure\n\n**Translation time: ~1 minute** vs hours of manual work.\n\n## Requirements\n\n- Python 3.8+\n- pymupdf (`pip install pymupdf`)\n- Claude Code CLI\n\n## Installation\n\n### Method 1: Git Clone\n\n```bash\ngit clone https://github.com/wshuyi/translate-pdf-skill.git\ncp -r translate-pdf-skill/skills/translate-pdf ~/.claude/skills/\n```\n\n### Method 2: Plugin Marketplace\n\n```bash\n/plugin install translate-pdf@wshuyi/translate-pdf-skill\n```\n\n## Usage\n\nSimply tell Claude what you want:\n\n```\n\"Translate this PDF to Chinese\"\n\"把这个PDF翻译成英文\"\n\"Translate report.pdf to Japanese\"\n```\n\nClaude will:\n1. Extract all text from the PDF\n2. Translate to target language\n3. Replace text while preserving styling\n4. Output translated PDF\n\n## Supported Languages\n\n| Language | Font |\n|----------|------|\n| English, Spanish, Portuguese, French, German, etc. | helv |\n| Simplified Chinese | china-ss |\n| Traditional Chinese | china-ts |\n| Japanese | japan |\n| Korean | korea |\n\n## Example\n\n**Input**: Portuguese organizational chart (Suprimentos.pdf)\n\n**Command**: \"把这个PDF翻译成中文\"\n\n**Output**: Chinese version with identical layout and styling\n\n## How It Works\n\n1. **Extract**: Parses PDF to get all text spans with positions, fonts, and colors\n2. **Translate**: Claude translates each text string\n3. **Replace**: Uses PDF redaction (transparent fill) to remove original text\n4. **Insert**: Adds translated text at same positions with matching style\n\n## FAQ\n\n**Q: Does it work with scanned PDFs?**\nA: No, this skill works with text-based PDFs. Scanned documents need OCR first.\n\n**Q: Will it change my PDF layout?**\nA: No, the layout is preserved. Only the text content changes.\n\n**Q: What about images and charts?**\nA: Images are preserved. Text within the PDF is translated.\n\n## License\n\nMIT License - see [LICENSE](LICENSE)\n\n## Author\n\n[@wshuyi](https://github.com/wshuyi)\n\n---\n\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n",
  "bytes": 2569,
  "sha": "849b34a4c196d95ad928847bb8fc2e196e3456fbb619bb9fa4bc6e87e5133a21",
  "repo_slug": "wshuyi/translate-pdf-skill",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_wshuyi_translate_pdf_skill_translate_pdf_1c29684f/readme"
}