pdf-analysis

Convert PDF content into structured markdown using a 3-tier extraction pipeline.

6|1|Updated Jan 2, 2026
One-click install
npx skills add https://github.com/1cFE/agentic-mbse --skill pdf-analysis-1cfe
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf-analysis
Source: https://github.com/1cFE/agentic-mbse/tree/main/claude/skills/pdf-analysis
Command: npx skills add https://github.com/1cFE/agentic-mbse --skill pdf-analysis-1cfe

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, pymupdf4llm, agentic_mbse, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill automates the extraction and analysis of content from PDF documents, turning dense files into structured data for downstream workflows (tables, text, and figures). It uses a memory-safe 3-tier pipeline (pymupdf4llm → Docling MCP → image fallback) to maximize accuracy while avoiding OOM issues.

Core Features & Use Cases

  • Tiered page extraction with adaptive backends to preserve tables and layout.
  • Page-level markdown conversion and single-page PDF export for downstream tooling.
  • Use Case: researchers extract key results from papers, analysts convert reports to markdown for knowledge bases, and engineers feed structured data into dashboards.

Quick Start

Ask me to extract and analyze content from a PDF using the 3-tier extraction pipeline.

Frequently Asked Questions about pdf-analysis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert a PDF to markdown without running out of memory?

To convert PDF to markdown safely, this extraction pipeline processes files page-by-page using a tiered fallback system (pymupdf4llm → Docling MCP → image fallback) to prevent out-of-memory errors while preserving layout and tables.

What is the best way to extract tables and text from research papers?

The best way to extract tables and text from papers is using a tiered extraction pipeline with adaptive backends, which preserves document layout and structures content into markdown-ready data for analysis.

Does PyMuPDF4LLM work well for converting PDFs to structured documentation?

PyMuPDF4LLM works for converting PDFs to structured documentation by serving as the primary extraction backend, reliably reading content and formatting it into markdown for downstream knowledge bases.

Can I process large PDF files page-by-page to avoid system crashes?

Yes, you can process large PDF files page-by-page to avoid crashes. The pipeline uses page-level markdown conversion and single-page exports to maximize fidelity while keeping memory usage strictly controlled.

What happens if pymupdf4llm fails to extract content from a PDF?

If pymupdf4llm fails to extract content, the pipeline automatically falls back to the Docling MCP backend, and ultimately to an image-based fallback tier, ensuring extraction completes without crashing.

Why does my PDF extraction tool lose table formatting and layout?

Table formatting and layout are lost when extraction lacks adaptive backends; this pipeline solves that by applying a 3-tier page-level extraction process that explicitly preserves structural fidelity for markdown conversion.