document-converter

Name: document-converter
Rating: 5 (423 reviews)
Author: benbrastmckie

Convert between Markdown, DOCX, and PDF formats bidirectionally. Handles text extraction from PDF/DOCX, markdown to document conversion. Use when converting document formats or extracting structured content from Word or PDF files.

TL;DR

Bidirectional conversion between Markdown, DOCX, and PDF formats with quality-aware tool selection and fallbacks.

What Is It

Converts between Markdown, DOCX, and PDF formats bidirectionally.
Extracts text from PDF/DOCX files to Markdown.
Uses intelligent tool selection based on quality and availability.
Supports batch processing and concurrent execution.

Key Features

Automatic tool detection and selection
Cascading fallback mechanisms for failed conversions
Batch processing with concurrent execution
Image extraction and embedding
Filename sanitization (spaces to underscores)
Quality validation and reporting
Progress streaming with PROGRESS/FAILED markers
Conversion log generation with statistics

How to Use

1.Set GEMINI_API_KEY for enhanced PDF→Markdown quality (Gemini API).
2.Use --no-api or CONVERT_DOCS_OFFLINE=true for offline mode only local tools.
3.Run detect_tools to verify available conversion tools.
4.Use main_conversion with input/output paths for batch processing.
5.Review conversion.log for success/failure and quality issues.

Guardrails & Gotchas

Must not mix conversion directions in one batch.
Critical: Scanned PDFs depend on scan resolution (OCR quality).
Critical: Complex layouts degrade table and layout fidelity.
Critical: Embedded fonts affect text extraction accuracy.
Critical: Large images may cause timeout issues.
Must increase TIMEOUT_PDF_TO_MD for large PDFs (default 300s).

GitHub Stats

Author

@benbrastmckie

Repository

benbrastmckie/.config

Stars

423

Explore More Skills

move-code-quality

@davila7

Analyzes Move language packages against the official Move Book Code Quality Checklist. Use this skill when reviewing Move code, checking Move 2024 Edition compliance, or analyzing Move packages for best practices. Activates automatically when working with .move files or Move.toml manifests.

12.4k

1.1k

1w ago

document-converter

Explore More Skills

move-code-quality

e2e-testing-patterns

testing-anti-patterns