skills.rest
sgttomas
sgttomasCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

pdf2md-page-assets

Identify visible fig, tbl, and img assets on a rasterized PDF page and emit a JSON manifest.

Updated Aug 27, 2026
Search Tags:#pdf#assets#document-processing#data-extraction#page-assets#asset-records#pdf2md
One-click install
npx skills add https://github.com/sgttomas/chirality-piping --skill pdf2md-page-assets
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf2md-page-assets
Source: https://github.com/sgttomas/chirality-piping/tree/main/skills/pdf2md-page-assets
Command: npx skills add https://github.com/sgttomas/chirality-piping --skill pdf2md-page-assets

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The pdf2md-page-assets skill identifies visible assets on a single rasterized PDF page and emits a standardized JSON manifest of assets for downstream processing.

Core Features & Use Cases

  • Identify fig, tbl, and img assets visible on a page and describe them in a structured asset JSON.
  • Emit a deterministic page-level asset record at OUTPUT_PATH for reliable downstream materialization.
  • Use in OpenAI/PDF2MD workflows to surface auditable visual content from documents.

Quick Start

Run the pdf2md-page-assets skill on a single page using the provided IMAGE_PATH, PAGE_MD_PATH, and OUTPUT_PATH to generate the page_assets.json.

Frequently Asked Questions about pdf2md-page-assets

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

FAQPage Schema
How do I extract visible assets from a PDF page image?▼

To extract visible assets from a PDF page image, you input the rasterized page image and its cleaned Markdown to generate a structured JSON manifest of figures, tables, and images. This process outputs a deterministic page-level asset record for downstream processing.

What is a page-level asset JSON manifest in document processing?▼

A page-level asset JSON manifest is a structured catalog identifying visible assets like figures, tables, and images on a single PDF page. It provides deterministic asset records that ensure auditable visual content extraction for downstream workflows.

How do I generate an asset catalog from a rasterized PDF and Markdown?▼

Generate an asset catalog by providing the rasterized PDF page image path, the cleaned per-page Markdown path, and an output path. The system processes these inputs to write a single JSON file containing the structured asset descriptions.

Can I use extracted PDF page assets for downstream data materialization?▼

Yes, extracted PDF page assets are designed for downstream data materialization. The skill emits a deterministic JSON manifest of visual content that integrates into OpenAI and PDF2MD workflows to surface auditable asset records.

What are the input requirements for identifying figures and tables in a PDF?▼

Identifying figures and tables requires a rasterized PDF page image and its corresponding cleaned per-page Markdown. Strict input validation enforces page-level read and write boundaries to ensure accurate asset catalog generation.

Related Skills

Explore More Data & Analytics Skills→
KaihuaTangKaihuaTang
77

extract-pdf

Extract structured markdown text and per-page PNG images from PDF files.

Community
Advanced
striderZAstriderZA
72

asset-spec

Generate per-asset visual specs and AI image prompts from GDDs.

Community
Advanced
igorrazvodovskyigorrazvodovsky
1

pdf-processing

Extract text and tables from PDFs using pdfplumber.

Community
Intermediate
linxulelinxule
14

interview-ingest

Transcribe audio interviews and convert PDFs into analyzable markdown.

Community
Intermediate