Use AI to recreate PDF page as semantic HTML. Consumes three inputs (PNG image, parsed text, ASCII preview) for complete contextual understanding and accurate generation.
SkillScore91Maintained
Automatic
◆AI Engineer pack
Last verified 8/22/2026
What it changes
Passed 20 of 22 test cases with the skill, and 6 of 22 without it.
Without skill26%
With skill91%
Checks it passed that the model alone missed
Italic text spans use em tags.
Bold text spans use strong tags.
Data tables use class exhibit-table.
and 20 more in the full report
15 fixed6 passed either way2 still failing0 broke
Pass-rate lift
+65 pp
Tokens
+221%
Agent turns
0%
Response time
-48%
Model gemini-3.6-flashMeasured 8/22/2026v121 of 23 cases passed with skill · 22 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 15
Prompt
I need to verify word fidelity for Chapter 3, Page 12 after generating the initial HTML output. What CLI command should be executed to run the text verification script?
What was checked, without and with the skill
Checked
Without skill
With skill
The CLI command executes python3 Calypso/tools/verify_text_content.py 3 12.
Missed
Passed
case-02 · gemini-3.6-flash · 8/22/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md526 linessingle file
AI HTML Generate Skill
Purpose
This skill leverages AI's probabilistic generation capabilities to recreate PDF pages as semantic HTML. The AI receives three complementary inputs that together provide complete context:
Visual reference (PNG image) - Page layout and visual hierarchy
Text data (rich_extraction.json) - Accurate text content and formatting metadata
Structural preview (ASCII text) - Logical layout and element relationships
This three-input approach ensures the AI understands not just what text to include, but how it should be structured semantically in HTML.
The output is probabilistic (AI-generated), but will be made deterministic by validation gates in subsequent skills.
What to Do
Prepare three input files
Load 02_page_XX.png (image file)
Load 01_rich_extraction.json (text spans with metadata)