skills.rest
u9401066
u9401066COMMUNITY
Explore all skills by this author →
GitHub

pdf-asset-extractor

Extract text, figures, and tables from PDFs into a knowledge graph.

2|Updated Dec 26, 2025
Search Tags:#pdf#markdown#knowledge-graph#base64#asset-extraction#section-navigation
One-click install
npx skills add https://github.com/u9401066/asset-aware-mcp --skill pdf-asset-extractor
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf-asset-extractor
Source: https://github.com/u9401066/asset-aware-mcp/tree/main/.claude/skills/pdf-asset-extractor
Command: npx skills add https://github.com/u9401066/asset-aware-mcp --skill pdf-asset-extractor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Decomposing PDFs into queryable assets (images, tables, and text) and constructing a cross-document knowledge graph to enable AI agents to access precise information across documents.

Core Features & Use Cases

  • Ingest PDFs with dual-engine extraction (PyMuPDF for speed and Marker for high-precision structure) to output figures, tables, and sections.
  • Build a knowledge graph and Mermaid diagrams for cross-document reasoning and visualization.
  • Retrieve assets on demand (images as base64, tables as Markdown, sections and full text) to support RAG-enabled workflows.
  • Use Case: Automate extraction from a batch of research papers to populate a searchable knowledge base and enable cross-document queries.

Quick Start

Ingest a PDF to extract figures, tables, and text and build a knowledge graph for cross-document reasoning.

Frequently Asked Questions about pdf-asset-extractor

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

FAQPage Schema
How do I extract figures and tables from PDF for a knowledge graph?▼

PDF asset extraction outputs tables as Markdown, images as base64, and text as sections, converting documents into queryable assets like blocks.json and Mermaid diagrams to support RAG-enabled AI workflows.

Can I use extracted PDF assets for RAG workflows?▼

PyMuPDF and Marker differ in PDF extraction by offering a dual-engine approach: PyMuPDF prioritizes extraction speed, while Marker delivers high-precision document structure for accurately decomposing figures and tables.

How to convert PDF tables to Markdown for AI agents?▼

PDF asset extraction handles large base64 assets by coordinating optional outputs like manifests and blocks.json, ensuring safe handling and retrieval of large images without breaking downstream AI workflows.

Does the Skill support cross-document reasoning for research papers?▼

You do not need any dependencies to extract PDF assets, as the Skill operates with an empty dependency list and uses built-in dual-engine extraction logic to process documents independently.

Related Skills

Explore More Data & Analytics Skills→
breakcafebreakcafe
1

add-pdf-reader

Extract text and metadata from PDFs via a Bash CLI.

Official
Advanced
thistleknotthistleknot

kg_ontology

Resolve extracted surface spans into canonical knowledge-graph node identities using WordNet synsets and hypernym context.

Community
Advanced
zMynxxzMynxx

graphify

Transform codebases and document collections into queryable knowledge graphs.

Community
Advanced
Simon-Copilot-StudioSimon-Copilot-Studio

ocr-and-documents

Extracts text from PDFs and scanned images using OCR tools like marker-pdf and pymupdf.

Community
Intermediate