Skip to content

Improve infographic prompt guidance#1

Draft
NimaChu wants to merge 1 commit into
mainfrom
agent/improve-infographic-prompting
Draft

Improve infographic prompt guidance#1
NimaChu wants to merge 1 commit into
mainfrom
agent/improve-infographic-prompting

Conversation

@NimaChu

@NimaChu NimaChu commented Jul 11, 2026

Copy link
Copy Markdown
Owner

What changed

  • Require the complete source block to be included in infographic image-generation prompts.
  • Let the image model choose the information architecture instead of imposing a card, grid, table, or node layout.
  • Require inspection of every label, number, unit, and line break, with targeted regeneration when needed.
  • Keep local text overlay as a fallback only.

Why

The previous workflow generated decorative backgrounds and added text locally. A direct source-content prompt produced a more coherent infographic composition and better visual integration.

Validation

  • python3 /Users/chunima/.codex/skills/.system/skill-creator/scripts/quick_validate.py /Users/chunima/.codex/skills/mp-article
  • git diff --check

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant