baoyu-infographic

Generate raster infographics by combining 21 layout structures with 22 visual styles.

Updated May 18, 2026
One-click install
npx skills add https://github.com/fts-pro/FTS-MMIS-AFRIKA --skill baoyu-infographic-fts-pro
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: baoyu-infographic
Source: https://github.com/fts-pro/FTS-MMIS-AFRIKA/tree/main/.agent/skills/baoyu-infographic
Command: npx skills add https://github.com/fts-pro/FTS-MMIS-AFRIKA --skill baoyu-infographic-fts-pro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Turning articles, guides, or data into publication-ready infographics normally requires design skills and manual layout work. This Skill analyzes source content, recommends layout and style combinations, builds a reproducible prompt file, and generates the final image through an available image-generation backend. ## Core Features & Use Cases - Layout × Style Matrix: Choose from 21 layouts (bento-grid, funnel, dashboard, dense-modules, etc.) and 22 visual styles (craft-handmade, chalkboard, cyberpunk-neon, retro-pop-grid, etc.), with recommended pairings per content type. - Structured Workflow: A seven-step pipeline covering content analysis, structured content extraction with verbatim data preservation, combination recommendation, user confirmation, prompt generation, and image rendering. - Preference Persistence: EXTEND.md stores preferred layout, style, aspect ratio, language, and image backend across project, XDG, or user-home scopes. - Use Case: Paste a product buying guide and ask for a high-density infographic; the Skill recommends dense-modules with morandi-journal style in portrait aspect, confirms with you, then generates a publication-ready PNG. ## Quick Start Ask the agent to create an infographic from your article or notes, for example: create an infographic from this markdown file summarizing the key steps.

Frequently Asked Questions about baoyu-infographic

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

FAQPage Schema
How do I generate an infographic from an article or markdown file?▼

Provide the source content or file path and invoke the skill. It analyzes the content, recommends 3-5 layout and style combinations, asks you to confirm the combination, aspect ratio, and language, then writes a prompt file and generates the final PNG image.

What layouts and styles are available for infographics?▼

The skill offers 21 layouts including bento-grid, linear-progression, funnel, dashboard, and dense-modules, plus 22 styles including craft-handmade, chalkboard, corporate-memphis, and retro-pop-grid. Any layout can be freely combined with any style.

Which image generation backends does the skill support?▼

It resolves backends in priority order: a user-specified override, a saved preferred_image_backend preference, then auto-selection favoring runtime-native tools like Codex imagegen or Hermes image_generate, falling back to installed skills like baoyu-imagine. It never substitutes SVG or HTML rendering for raster output.

Can I set default preferences so I don't get asked every time?▼

Yes. An EXTEND.md file stored at project, XDG config, or user-home level can pin preferred_layout, preferred_style, preferred_aspect, language, and preferred_image_backend. These shape recommendations and defaults but never bypass the confirmation step unless you explicitly request it.

Why does the skill ask for confirmation before generating the image?▼

Confirmation is a hard gate by design: layout, style, aspect ratio, language, and backend choices must be approved before generation to avoid wasted image-generation calls. You can skip it only by explicitly saying so, for example with --no-confirm or equivalent wording.

What happens if the generated infographic has misspelled or garbled text?▼

The skill never patches bitmaps with code overlays. Instead it regenerates from a corrected prompt, writing a new prompt file and output path so the flawed candidate is preserved for comparison, or switches to a layout with less on-image text.