ascii-preview-generate

Generate ASCII previews of PDF page layouts from images and extraction metadata.

Updated Nov 13, 2025

Search Tags:#ai generation #document analysis #multi-modal #semantic context #pdf structure #layout preview #ascii art

Ready to run

npx skills add https://github.com/AbeJitsu/Game-Settings-Panel --skill ascii-preview-generate

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ascii-preview-generate
Source: https://github.com/AbeJitsu/Game-Settings-Panel/tree/main/.claude/skills/calypso/ascii-preview-generate
Command: npx skills add https://github.com/AbeJitsu/Game-Settings-Panel --skill ascii-preview-generate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI needs clear structural context to accurately convert visual PDF layouts into semantic HTML. This Skill uses AI to create a human-readable, ASCII text-based representation of a PDF page's layout, bridging the gap between visual and textual data for superior HTML generation.

Core Features & Use Cases

Multi-Modal Analysis: Analyzes both PDF page images and rich extracted text data to understand layout and structure comprehensively.
Structured ASCII Output: Generates a visual ASCII preview showing heading hierarchy, paragraphs, lists, and tables using box-drawing characters.
Enhanced AI Context: Provides a clear structural blueprint for downstream AI HTML generation, ensuring accurate and semantically correct output.
Use Case: Generate an ASCII layout preview for a complex PDF page, helping the AI understand the visual flow and element relationships before converting it to HTML.

Quick Start

Generate an ASCII layout preview for page 16 using the attached '02_page_16.png' and '01_rich_extraction.json'.

Frequently Asked Questions about ascii-preview-generate

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

FAQPage Schema

How do I convert a PDF page layout into a structured ASCII preview?▼

ASCII preview generation analyzes both the PDF page image and extracted text metadata to create a human-readable ASCII representation showing heading hierarchy, paragraphs, lists, and tables. This bridges visual and textual data, providing AI with clear structural context for accurate downstream HTML conversion.

What input data do I need to generate an ASCII layout preview from a PDF?▼

You need two inputs: a PDF page image file (02_page_XX.png) and rich extraction metadata in JSON format (01_rich_extraction.json) containing text structure and layout information. The Skill processes both to produce a detailed ASCII text representation.

Can ASCII preview generation help with converting PDFs to HTML?▼

Yes. ASCII preview generation creates a structural blueprint showing element relationships and visual flow that AI uses to generate semantically correct HTML. It bridges the gap between visual PDF layouts and semantic markup, improving conversion accuracy.

Why use multi-modal analysis for PDF layout understanding?▼

Multi-modal analysis—combining page images with extracted text data—captures both visual positioning and semantic structure that either source alone misses. This comprehensive understanding ensures the ASCII preview accurately represents heading hierarchy, content flow, and table relationships for downstream processing.

What output does the ASCII preview generation produce?▼

The Skill generates an ASCII text file (03_page_XX_ascii.txt) stored at output/chapter_XX/page_artifacts/page_YY/, embedding metadata including page number, chapter identifier, and timestamp alongside the visual layout representation using box-drawing characters.