baoyu-comic

Generate multi-page knowledge comics from source content using prompt-based image generation.

Updated Sep 10, 2026
One-click install
npx skills add https://github.com/loteiron/ZeusAgent --skill baoyu-comic-loteiron
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: baoyu-comic
Source: https://github.com/loteiron/ZeusAgent/tree/main/optional-skills/creative/baoyu-comic
Command: npx skills add https://github.com/loteiron/ZeusAgent --skill baoyu-comic-loteiron

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Turning educational content, biographies, or tutorials into engaging visual comics requires coordinating storyboarding, character design, style selection, and image generation, which is difficult to do consistently by hand. ## Core Features & Use Cases - Structured Comic Pipeline: Analyzes source content, builds a storyboard and character definitions, writes per-page image prompts, then generates and downloads each page as a PNG. - Style System: Combines 6 art styles, 7 tones, 7 layouts, and 5 presets (ohmsha, wuxia, shoujo, concept-story, four-panel) with a content-signal auto-selection matrix. - Character Consistency: Embeds text character descriptions inline in every page prompt, with an optional character reference sheet for human review. - Use Case: Paste a tutorial on neural networks and ask for an ohmsha-style educational comic; the skill produces analysis.md, storyboard.md, character definitions, prompt files, and downloaded page images under comic/{topic-slug}/. ## Quick Start Create a knowledge comic from this article about gradient descent using the ohmsha preset, 10 pages, in English.

Frequently Asked Questions about baoyu-comic

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

FAQPage Schema
How do I create an educational comic from text content?▼

Provide your source content as pasted text, a file path, a URL, or a topic, and the skill analyzes it, confirms style options with you, builds a storyboard and characters, writes per-page prompts, and generates each page image. Output lands in a comic/{topic-slug}/ directory.

What art styles and tones are available for comic generation?▼

Six art styles (ligne-claire, manga, realistic, ink-brush, chalk, minimalist) combine with seven tones (neutral, warm, dramatic, romantic, energetic, vintage, action). Five presets like ohmsha and four-panel add special rules beyond the base combination.

Can I use reference images to keep comic characters consistent?▼

The image_generate tool is prompt-only and does not accept reference images. Character consistency is enforced by embedding text descriptions from characters/characters.md inline in every page prompt; reference images are only used to extract style or palette traits as text.

How do I regenerate a single comic page without redoing everything?▼

Ask to regenerate specific pages, such as page 3 or pages 2, 5, 8. The skill reads the existing prompt files, calls image_generate again, and overwrites only those PNGs, backing up prior versions with a timestamp suffix.

Does the comic workflow produce a merged PDF?▼

No. This port removed the upstream PDF merge step because it depended on pdf-lib, which is not available. Pages are delivered as individual PNG files in the output directory.

Why did my generated comic pages save to the wrong directory?▼

The image download step must use absolute paths with curl -o, because the terminal's persistent working directory can drift between batches. Relative output paths can silently write files to an unintended location.