baoyu-comic

Generate multi-page educational knowledge comics from source content using AI image generation.

Updated May 13, 2026
One-click install
npx skills add https://github.com/superfhp/lumi-agent-body --skill baoyu-comic-superfhp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: baoyu-comic
Source: https://github.com/superfhp/lumi-agent-body/tree/main/skills/creative/baoyu-comic
Command: npx skills add https://github.com/superfhp/lumi-agent-body --skill baoyu-comic-superfhp

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Turning articles, biographies, tutorials, or technical explanations into engaging visual comics normally requires illustration skills and hours of layout work. This Skill automates the full pipeline from raw content to finished comic pages. ## Core Features & Use Cases - End-to-End Comic Pipeline: Analyzes source content, builds a storyboard with panel breakdowns, defines consistent characters, writes per-page image prompts, and generates PNG pages via the image_generate tool. - Style System: Combines 6 art styles (ligne-claire, manga, realistic, ink-brush, chalk, minimalist), 7 tones, 7 layouts, and 5 presets (ohmsha, wuxia, shoujo, concept-story, four-panel) with a content-signal auto-selection matrix. - Consistency & Reproducibility: Embeds character descriptions inline in every page prompt, saves all prompts as files, and supports partial workflows (storyboard-only, prompts-only, images-only, regenerate specific pages). - Use Case: Paste a tutorial on neural networks and ask for an ohmsha-style educational manga; the Skill produces a storyboard, character sheet, and a full set of downloadable comic pages. ## Quick Start Create a knowledge comic from this article about Alan Turing's life using the ligne-claire art style and a warm tone.

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 an article or tutorial?▼

Provide the source content as pasted text, a file path, or a URL, and the Skill analyzes it, proposes an art style and tone, then generates a storyboard, character definitions, prompts, and final PNG pages. You confirm the style and review options before image generation begins.

What art styles and tones are available for knowledge comics?▼

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, and a content-signal matrix recommends combinations automatically.

Can I regenerate only specific pages of a comic?▼

Yes, partial workflows support storyboard-only, prompts-only, images-only, and regenerating specific page numbers. Existing prompt and image files are backed up with a timestamp suffix before being overwritten.

How does the comic keep characters consistent across pages?▼

Character descriptions from characters/characters.md are embedded inline in every page prompt, since the image generation tool accepts text prompts only and no reference images. An optional character sheet PNG is generated as a human review artifact.

Does the comic generator produce a merged PDF file?▼

No, PDF assembly was removed in this port because it required an external pdf-lib dependency. Output is delivered as individual PNG page files plus markdown artifacts like the storyboard and analysis.

What happens if I don't respond to the style confirmation questions?▼

Each unanswered question falls back to a per-question default chosen by best judgement, and the defaults taken are surfaced visibly so you can correct them. The workflow never silently applies defaults across all questions at once.