baoyu-comic

Generate multi-page educational comics with storyboards, character sheets, and PDF output.

2|Updated May 30, 2026
One-click install
npx skills add https://github.com/virahitvin8/crafty-gis --skill baoyu-comic-virahitvin8
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: baoyu-comic
Source: https://github.com/virahitvin8/crafty-gis/tree/main/GIT_STAR/assignment-generator/antigravity-skills-main/antigravity-skills-main/skills/baoyu-comic
Command: npx skills add https://github.com/virahitvin8/crafty-gis --skill baoyu-comic-virahitvin8

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pdf-lib, and includes scripts (resource) and references (resource) components.

What problem does it solve? Turning articles, tutorials, or biographies into engaging educational comics requires coordinating storyboarding, character design, image generation, and page assembly — a slow, inconsistent manual process. ## Core Features & Use Cases - End-to-End Comic Pipeline: Analyzes source content, builds a storyboard with panel breakdowns, defines characters, writes per-page image prompts, generates pages in batches, and merges everything into a PDF. - Style System: Six art styles, seven tones, seven layouts, and five presets (ohmsha, wuxia, shoujo, concept-story, four-panel) with an auto-selection matrix based on content signals. - Consistency Controls: Character reference sheets passed as image refs, saved prompt files for reproducibility, and partial workflows (--storyboard-only, --prompts-only, --images-only, --regenerate N). - Use Case: Paste a technical tutorial and ask for an ohmsha-style educational manga; the skill produces a storyboard, character sheet, generated pages, and a final merged PDF. ## Quick Start Create a knowledge comic from the attached article using the ohmsha preset and merge the pages into a PDF.

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?

Provide the source content and invoke the skill; it analyzes the material, confirms an art style and tone with you, generates a storyboard and character sheet, writes per-page prompts, generates images in batches, and merges the pages into a PDF.

What art styles and presets does the comic generator support?

It offers six art styles (ligne-claire, manga, realistic, ink-brush, chalk, minimalist), seven tones, seven layouts, and five presets: ohmsha, wuxia, shoujo, concept-story, and four-panel. An auto-selection matrix recommends combinations from content signals.

Can I regenerate only specific comic pages?

Yes. Use --regenerate with page numbers (e.g., 3 or 2,5,8) to re-render selected pages from their saved prompt files, then the PDF is rebuilt. Partial workflows like --storyboard-only, --prompts-only, and --images-only are also supported.

Which image generation backends are supported?

The skill resolves backends in priority order: a runtime-native image tool such as Codex imagegen, codex-imagegen via the codex CLI, other runtime-native tools, or an installed backend like baoyu-image-gen. You can pin a backend with preferred_image_backend in EXTEND.md.

Why does the skill require bun or npx?

The PDF merge script (scripts/merge-to-pdf.ts) is TypeScript executed via bun, with npx -y bun as a fallback. It embeds generated PNG or JPEG pages into a PDF using pdf-lib.

How are characters kept consistent across comic pages?

A character reference sheet is generated first and passed as a reference image on every page when the backend supports it. Otherwise, detailed character descriptions from characters.md are embedded directly into each page's prompt file.