document-conversion skill
Converts complex PDFs and documents into structured formats using intelligent tool selection for tables, figures, and formulas.
- GitHub stars
- 21
- Files
- 1
- Last commit
- Nov 6, 2026
- License
- —
- Allowed tools
- —
What does the document-conversion skill do?
document-conversion converts complex PDFs and documents into structured formats using intelligent tool selection for tables, figures, and formulas.
Summary generated from the skill's SKILL.md.
About the document-conversion skill
Converting complex academic papers and PDFs into structured formats is the primary function of this skill. It is designed for researchers and developers who need to extract data from documents containing intricate elements like multi-column layouts, mathematical formulas, or merged table cells. The skill evaluates the complexity of a file to decide between using the MinerU tool or suggesting manual conversion methods.
When a MINERU_API_KEY is provided, the skill can utilize MinerU in VLM mode to achieve over 90% accuracy for difficult files. This mode specifically handles figure extraction, formula recognition, and complex table structures. For simpler text-based documents or when an API key is missing, the skill directs the user toward manual workflows using tools like Adobe Acrobat, Google Docs, or Tesseract OCR. It also identifies when audio files require external transcription services instead of document parsing.
What an agent can do with it
- 1Extracting academic paper dataConvert a complex research paper containing mathematical formulas and multi-column layouts into a structured format.
- 2Processing complex tablesParse a PDF that contains tables with merged cells to ensure the structure remains intact.
- 3Handling simple document conversionConvert a straightforward text-based PDF without using an API key.
- 4Batch processing multiple filesRun a batch process on a list of URLs to convert multiple documents at once using the VLM model.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the document-conversion skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the document-conversion skill in Plugin
/plugin marketplace add linxule/interpretive-orchestration /plugin install interpretive-orchestration@interpretive-orchestration
Install the document-conversion skill in Claude Code
~/.claude/skills/document-conversion/SKILL.md
$ npx degit linxule/interpretive-orchestration/plugin/skills/document-conversion ~/.claude/skills/document-conversionInstall the document-conversion skill in Claude Code (project)
.claude/skills/document-conversion/SKILL.md
$ npx degit linxule/interpretive-orchestration/plugin/skills/document-conversion .claude/skills/document-conversionInstall the document-conversion skill in Codex
~/.agents/skills/document-conversion/SKILL.md
$ npx degit linxule/interpretive-orchestration/plugin/skills/document-conversion ~/.agents/skills/document-conversionInstall the document-conversion skill in Gemini CLI
~/.gemini/skills/document-conversion/SKILL.md
$ npx degit linxule/interpretive-orchestration/plugin/skills/document-conversion ~/.gemini/skills/document-conversionInstall the document-conversion skill in Claude.ai
npx degit linxule/interpretive-orchestration/plugin/skills/document-conversion document-conversion && zip -r document-conversion.zip document-conversion # claude.ai → Customize → Skills → + → Create skill → Upload a skill → document-conversion.zip
Automated checks
Ran Nov 16, 2026Full report →Not verified yet. A skill needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablelinxule/interpretive-orchestration/plugin/skills/document-conversion is public and reachablegithub.com/linxule/interpretive-orchestration/tree/HEAD/plug ↗Pass
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit 2026-11-06github.com/linxule/interpretive-orchestration/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/linxule/interpretive-orchestration/blob/HEAD/plug ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/linxule/interpretive-orchestration/blob/HEAD/plug ↗Pass
- SKILL.md follows the Agent Skills formatthe description does not say when to use the skillgithub.com/linxule/interpretive-orchestration/blob/HEAD/plug ↗Finding
SKILL.md
View on GitHubdocument-conversion
Robust PDF and document conversion with intelligent tool selection. Chooses the best available conversion method based on document complexity and MCP availability.
When to Use
Use this skill when:
- User needs to convert PDFs, especially with tables or figures
- User mentions "convert", "PDF", "document processing"
- User has complex academic papers to import
- User asks about document conversion options
Conversion Options
| Feature | MinerU (Optional) | Manual Conversion |
|---|---|---|
| API Key Required | Yes (MINERU_API_KEY) | No |
| PDF Accuracy | 90%+ (VLM mode) | Varies |
| Table Extraction | Excellent | Manual cleanup |
| Figure Handling | Extracts + describes | Manual description |
| Formula Recognition | Yes | Limited |
| Multi-column | Excellent | Manual formatting |
| Cost | Pay per page | Free |
When to Use Which
Use MinerU When:
- PDF has complex tables with merged cells
- Document has multi-column layouts
- Figures/charts need extraction
- Mathematical formulas present
- Academic paper with structured formatting
- Accuracy is critical
Use Manual Conversion When:
- Simple text-based documents
- MinerU API key not available
- Cost is a concern
- Document is straightforward
Tool Selection Logic
Is the document a PDF with tables/figures?
├── Yes, complex tables
│ └── MinerU available?
│ ├── Yes → Use MinerU (vlm mode)
│ └── No → Manual conversion + review
├── Yes, simple formatting
│ └── Manual conversion or external tool
└── No, other format
└── Is it audio?
├── Yes → External transcription service
└── No → Manual conversion
Usage Examples
MinerU (Complex PDF)
Use mineru_parse to convert this academic paper:
- URL: https://example.com/paper.pdf
- Model: vlm (for 90% accuracy)
- Enable: formula, table recognition
Manual Conversion (Simple Document)
For simple PDFs without MinerU:
1. Use Adobe Acrobat to export to Word/text
2. Or open in Google Docs for auto-OCR
3. Review and clean up formatting
Batch Processing
For multiple PDFs:
1. Check which have complex tables (use MinerU if available)
2. Process simple ones with manual conversion
3. Queue complex ones for MinerU batch if API key available
MinerU Specific Features
VLM vs Pipeline Mode
- VLM Mode: Uses vision-language model, 90%+ accuracy, slower
- Pipeline Mode: Traditional parsing, faster, lower accuracy
Page Selection
Parse only specific pages:
mineru_parse({
url: "https://...",
pages: "1-10,15,20-25"
})
Batch Processing
Process multiple documents:
mineru_batch({
urls: ["url1", "url2", "url3"],
model: "vlm"
})
Output Quality Checklist
After conversion, verify:
- Text is accurately extracted
- Tables maintain structure
- Headers/sections are correct
- Figures have descriptions (if MinerU)
- Formulas are readable (if MinerU)
- No garbled text from OCR errors
Integration with Research Workflow
For Literature (Stream A)
- Identify papers to convert
- Complex papers → MinerU (if API key available)
- Simple papers → Manual conversion
- Store in stream-a-theoretical/papers/
For Data Documents (Stream B)
- Interview transcripts → External service (Otter.ai, Rev.com)
- PDF field notes → MinerU or manual conversion
- Store in appropriate stage folder
Fallback Options
If MinerU unavailable:
- Adobe Acrobat - Export to Word
- Google Docs - Open PDF for auto-OCR
- Tesseract OCR - Command-line tool
- Manual transcription - Last resort
Audio Transcription
For audio files, use external services:
- Otter.ai - Good transcription service
- Rev.com - Professional transcription
- YouTube - Upload as unlisted video for auto-captions
Related
- MCPs: MinerU (optional)
- Skills: interview-ingest for audio, literature-sweep for papers
- Configuration: .mcp.json defines MCP availability
Files in this skill
1document-conversion skill questions
How do I install the document-conversion skill in Claude Code?
Run npx degit linxule/interpretive-orchestration/plugin/skills/document-conversion ~/.claude/skills/document-conversion. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the document-conversion skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.