All skills
jimliu avatar

/baoyu-comic

@b0ac523 official
by Jim Liu 宝玉jimliu/baoyu-skills26k stars
2,896

Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and batch-capable image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".

Use this Skill: https://skilld.dev/gh/jimliu/baoyu-skills/baoyu-comic

This session only. Nothing lands on disk.

referencespresetsohmsha.md

≈1.1k tokens on demand. Your agent reads this file only when SKILL.md points to it.

ohmsha

Ohmsha预设 - Educational manga with visual metaphors

Base Configuration

Dimension Value
Art Style manga
Tone neutral
Layout webtoon (default)

Equivalent to: --art manga --tone neutral

Unique Rules

This preset includes special rules beyond the art+tone combination. When --style ohmsha is used, ALL rules below must be applied.

Visual Metaphor Requirements (CRITICAL)

Every technical concept MUST be visualized as a metaphor:

Concept Type Visualization Approach
Algorithm Gadget/machine that demonstrates the process
Data structure Physical space characters can enter/explore
Mathematical formula Transformation visible in environment
Abstract process Tangible flow of particles/objects

Wrong approach: Character points at blackboard explaining Right approach: Character uses "Concept Visualizer" gadget, steps into metaphorical space

Visual Metaphor Examples

Concept Wrong (Talking Head) Right (Visual Metaphor)
Attention mechanism Character points at formula on blackboard "Attention Flashlight" gadget illuminates key words in dark room
Gradient descent "The algorithm minimizes loss" Character rides ball rolling down mountain valley
Neural network Diagram with arrows Living network of glowing creatures passing messages
Overfitting "The model memorized the data" Character wearing clothes that fit only one specific pose

Character Roles (Required)

DEFAULT: Use Doraemon characters unless user explicitly specifies --characters or has character presets in EXTEND.md.

Role Default Character Visual Traits
Student (Role A) 大雄 (Nobita) Boy, 10yo, round glasses, black hair, yellow shirt, navy shorts Confused, asks basic but crucial questions, represents reader
Mentor (Role B) 哆啦A梦 (Doraemon) Blue robot cat, white belly, 4D pocket, red nose, golden bell Knowledgeable, patient, uses gadgets as technical metaphors
Challenge (Role C) 胖虎 (Gian) Stocky boy, small eyes, orange shirt Represents misunderstanding, or "noise" in the data
Support (Role D) 静香 (Shizuka) Cute girl, black short hair, pink dress Asks clarifying questions, provides alternative perspectives

IMPORTANT: These Doraemon characters ARE the default for ohmsha preset. Generate character definitions using these exact characters unless user requests otherwise.

To use custom characters: --characters "Student:小明,Mentor:教授" or define in EXTEND.md.

Page Title Convention

Every page MUST have a narrative title (not section header):

Wrong: "Chapter 1: Introduction to Transformers" Right: "The Day Nobita Couldn't Understand Anyone"

Gadget Reveal Pattern

When introducing a concept:

  1. Student expresses confusion with visual indicator (?, spiral eyes)
  2. Mentor dramatically produces gadget with sparkle effects
  3. Gadget name announced in bold with explanation
  4. Demonstration begins - student enters metaphorical space

Ending Requirements

Final page MUST include:

  1. Student demonstrating understanding (applying the concept)
  2. Callback to opening problem (now resolved)
  3. Mentor's satisfied expression
  4. Optional: hint at next topic

NO Talking Heads Rule

Critical: Characters must DO things, not just explain.

Every panel should show:

  • Action being performed
  • Metaphor being demonstrated
  • Character interaction with concept-space
  • NOT: two characters facing each other talking

Special Visual Elements

Element Usage
Gadget reveals Dramatic unveiling with sparkle effects
Concept spaces Rounded borders, glowing edges for "imagination mode"
Information displays Holographic UI style for technical details
Aha moments Radial lines, light burst effects
Confusion Spiral eyes, question marks floating above head

Quality Markers

  • ✓ Every concept is a visual metaphor
  • ✓ Characters are DOING things, not just talking
  • ✓ Clear student/mentor dynamic
  • ✓ Gadgets and props drive the explanation
  • ✓ Expressive manga-style emotions
  • ✓ Information density through visual design, not text walls
  • ✓ Narrative page titles

Reference

For complete guidelines, see references/ohmsha-guide.md

Source: SKILL.md on GitHub

1 warning17d5 checks · Risk MEDIUM
  • Gen Agent Trust Hub17d

    This skill is a complex comic creation tool that uses dynamic script execution for PDF merging and environment-aware image generation. It includes logic to discover and run local wrapper scripts by searching directory paths at runtime. While these behaviors are documented as part of its cross-platform support (Codex, Cursor, etc.), the use of dynamic execution from computed paths and the processing of untrusted user content for prompt generation represent notable security surfaces.

  • Socket17d

    No alerts

  • Snyk17d

    Risk: LOW · No issues

  • Runlayer6mo

    2/34 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at b0ac523. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 4 months ago
version
1.117.4
Other metadata
metadata
{
  "openclaw": {
    "homepage": "https://github.com/JimLiu/baoyu-skills#baoyu-comic",
    "requires": {
      "anyBins": [
        "bun",
        "npx"
      ]
    }
  }
}
  • TypeScript
  • comic
  • education
  • knowledge
  • image-generation
  • batch-capable
  • panel-layout
  • art-styles
  • storytelling
  • bun

README badge

README badge for jimliu/baoyu-skills/baoyu-comic

Creates original educational comics with flexible art style and tone combinations, supporting batch image generation and detailed panel layouts. Use when asked to generate knowledge comics, biography comics, tutorial comics, or similar educational visual narratives in styles like ligne-claire, manga, or ink-brush.

Generated from the current SKILL.md.

What art styles and tones does this skill support?
Six art styles (ligne-claire, manga, realistic, ink-brush, chalk, minimalist) and seven tones (neutral, warm, dramatic, romantic, energetic, vintage, action) can be combined. Five named presets (ohmsha, wuxia, shoujo, concept-story, four-panel) bundle specific art+tone combinations with special visual rules.
Can I use my own reference images to guide the comic style?
Yes. Pass reference images via `--ref <files...>` and specify usage mode (direct, style, or palette). Direct mode passes the image to the backend; style and palette modes extract traits and embed them in prompts.
What image backends does this skill work with?
It auto-detects and prioritizes Codex `imagegen`, Cursor `GenerateImage`, or other runtime-native tools. If none are available, it falls back to `baoyu-image-gen` or asks you to choose from installed backends.
Can I regenerate just a few pages instead of the whole comic?
Yes. Use `--regenerate N` to regenerate specific pages (e.g., `--regenerate 3` or `--regenerate 2,5,8`), or `--images-only` to generate images from existing prompts without rebuilding the storyboard.
Does this skill require bun or npm?
It requires either `bun` or `npx` installed. The skill will use `bun` if available; otherwise it falls back to `npx -y bun`.

Generated from the current SKILL.md. These answers refresh after source changes.