ai-html-generate

Recreate PDF pages as semantic HTML5 from PNG, JSON, and ASCII inputs.

Updated Nov 13, 2025
One-click install
npx skills add https://github.com/AbeJitsu/Game-Settings-Panel --skill ai-html-generate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ai-html-generate
Source: https://github.com/AbeJitsu/Game-Settings-Panel/tree/main/.claude/skills/calypso/ai-html-generate
Command: npx skills add https://github.com/AbeJitsu/Game-Settings-Panel --skill ai-html-generate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually converting complex PDF pages into structured, semantic HTML is a labor-intensive and error-prone process. This Skill automates the recreation of PDF content into high-quality HTML, preserving layout and content integrity, saving significant development time.

Core Features & Use Cases

  • Three-Input Context: Leverages a PNG image (visual layout), rich text extraction (accurate content), and ASCII preview (structural blueprint) for comprehensive AI understanding.
  • Semantic HTML5 Output: Generates HTML with proper heading tags, paragraphs, lists, and semantic CSS classes for accessibility and maintainability.
  • Content Integrity Gate: Includes a mandatory verification step to ensure 99-100% text coverage, preventing AI hallucinations and content loss.
  • Use Case: Convert a textbook PDF page into a fully semantic HTML document, preserving layout, text, and hierarchy, ready for web display or further content processing.

Quick Start

Generate semantic HTML for page 16 of the attached PDF, using the provided image, text data, and ASCII preview.

Frequently Asked Questions about ai-html-generate

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

FAQPage Schema
How do I convert a PDF page into semantic HTML?

Convert PDFs to semantic HTML by providing three inputs: a PNG visual reference of the page, rich text extraction data, and an ASCII structural preview. The Skill analyzes layout, hierarchy, and content relationships to generate valid HTML5 with proper heading tags, paragraphs, lists, and semantic CSS classes.

Can I preserve document layout and text accuracy when converting PDF to HTML?

Yes. The Skill preserves layout and text integrity through a content verification gate that ensures 99-100% text coverage, preventing AI hallucinations and content loss while maintaining the original document's structure and hierarchy.

What's the best way to automate PDF document conversion to web-ready HTML?

Automate PDF to HTML conversion by leveraging multi-modal inputs—visual, textual, and structural data—for comprehensive AI understanding. This approach generates semantic, accessible HTML ready for web display or downstream content processing without manual reconstruction.

Does this work for complex PDF pages with varied layouts?

Yes. The three-input context method—PNG image, rich text extraction, and ASCII preview—handles complex pages by inferring layout, hierarchy, and relationships. The mandatory verification step ensures accurate reconstruction of intricate document structures.

What are the limitations when converting PDFs to semantic HTML?

Output is deterministic and subject to downstream validation gates. Success depends on quality of input data (visual reference, text extraction accuracy, and structural preview). Complex non-standard layouts may require refinement after generation.