paper-comic
Scannednpx machina-cli add skill proyecto26/sherlock-ai-plugin/paper-comic --openclawPaper Comic - Academic Paper to Comic Generator
Transform academic papers into coherent educational comics, making complex concepts easier to understand through visual storytelling.
Usage
/paper-comic /path/to/paper.pdf
/paper-comic /path/to/paper.pdf --style tech
/paper-comic # Then paste the paper content
Art Style Options
| Style | Features | Suitable Papers |
|---|---|---|
| classic | Clean-line style, simple and professional, easy to read | General purpose, most papers (default) |
| tech | Futuristic look, circuit and neon elements | AI/Computer/Engineering papers |
| warm | Gentle tone, nostalgic feeling, approachable | Psychology/Cognitive Science/Education |
| chalk | Blackboard effect, academic atmosphere | Math/Physics/Theoretical papers |
Output Structure
[output-dir]/
├── outline.md # Storyboard and scene outline
├── characters/
│ ├── characters.md # Character definitions
│ └── characters.png # Character reference image
├── prompts/
│ ├── 00-cover.md # Cover prompt
│ └── XX-page.md # Page prompts
├── 00-cover.png # Cover page
└── XX-page.png # Comic pages
Output Directory:
- If source files exist:
[source-dir]/comic/ - If no source files:
comic-outputs/YYYY-MM-DD/[topic-slug]/
Workflow
Step 1: Analyze the Paper
- Read paper content (PDF or Markdown)
- Extract key information:
- Paper title and authors
- Research background and motivation
- Core innovations (1–3)
- Key methods/algorithms
- Main experimental results
- Automatically recommend an art style based on the paper field (or use user-specified style)
Step 2: Design Narrative Structure
Four-part structure (suitable for 8–12 pages of comic):
| Stage | Pages | Content |
|---|---|---|
| Introduction | 1–2 pages | Problem background — why the research is needed |
| Exploration | 2–3 pages | Limitations of existing methods, leading to innovation |
| Core | 3–5 pages | Explain the innovation in detail, visualized with metaphors |
| Summary | 1–2 pages | Experimental results, significance, and future outlook |
Step 3: Define Characters
Create characters/characters.md:
Required characters:
- Mentor: The explainer, wise and approachable
- Student: Represents the reader, asks questions and learns
- Concept embodiment (optional): A personified version of an abstract concept
Character consistency rules:
- Mentor and student must appear in ≥60% of pages
- Each page should clearly list appearing characters
- Character design must remain consistent throughout all pages
Step 4: Create Storyboard
Create outline.md, containing:
- Metadata (title, art style, page count)
- Cover design
- Panel layout and content of each page
Storyboard rules:
- Each page has 3–5 panels
- Note which characters, scenes, and dialogue appear in each panel
- All dialogue must be written in Chinese
- Formulas should be represented visually, not as text formulas
Step 5: Generate Images
Use genimg-gemini-web to generate images (requires Google account authentication):
# Get skill installation path (assuming installed via npx skills add)
SKILL_DIR="$HOME/.claude/skills/genimg-gemini-web"
# Or if located elsewhere:
# SKILL_DIR="$HOME/.codex/skills/genimg-gemini-web"
# Generate character reference image
npx -y bun "$SKILL_DIR/scripts/main.ts" \
--promptfiles references/base-prompt.md characters/characters.md \
--image characters/characters.png \
--sessionId comic-[topic]-[timestamp]
# Generate pages (use the same sessionId for consistency)
npx -y bun "$SKILL_DIR/scripts/main.ts" \
--promptfiles references/base-prompt.md prompts/XX-page.md \
--image XX-page.png \
--sessionId comic-[topic]-[timestamp]
Important: Use the same --sessionId across all runs to ensure consistent character appearance.
First run: Chrome will open for Google account authentication; cookies will then be cached.
Step 6: Generate Final Document
Generate [topic]-paper-comic.md:
# [Paper Title] - Comic Interpretation
## Overview
- **Paper**: [Title]
- **Art Style**: [Selected Style]
- **Pages**: [N]
- **Generated on**: [YYYY-MM-DD]
## Comic Pages
### Cover
### Page 1
**Content**: [Brief summary of this page’s content]
...
## Core Knowledge Points
1. [Concept 1]
2. [Concept 2]
3. [Concept 3]
Key Principles
Text Requirements
- All dialogue and narration must be in Chinese
- Professional terms: Chinese + English, e.g., “梯度下降 (Gradient Descent)”
- Text must be clear and readable
Formula Handling
- Do not write formulas as text
- Use visual or metaphorical representations instead
- Example: Gradient descent → draw a small ball rolling down a hill
Visual Consistency
- Characters’ appearance must remain consistent
- Scene style should be uniform
- Narrative logic should flow clearly and progressively
Reference Files
references/base-prompt.md- Base prompt templatereferences/styles/classic.md- Clean-line stylereferences/styles/tech.md- Tech stylereferences/styles/warm.md- Warm stylereferences/styles/chalk.md- Chalkboard style
Source
git clone https://github.com/proyecto26/sherlock-ai-plugin/blob/main/skills/paper-comic/SKILL.mdView on GitHub Overview
Paper Comic converts scholarly papers into a visual narrative that clarifies core ideas. It supports four art styles—classic, tech, warm, and chalk—and uses genimg-gemini-web to generate illustrations, producing a complete comic package with outlines, characters, prompts, and page assets.
How This Skill Works
Start by analyzing the paper to extract title, motivation, core innovations, methods, and results. Then design a four-part narrative (Introduction, Exploration, Core, Summary) for 8–12 pages and select an art style based on the paper’s field. Finally, generate images with genimg-gemini-web and organize outputs into the standard comic directory.
When to Use It
- You need to explain AI/CS papers to students with visuals.
- You want to visualize math, physics, or engineering concepts for a lecture.
- You’re turning a research paper into course-ready material with a consistent narrative.
- You need a classroom-friendly summary of experiments, results, and implications.
- You’re creating bilingual (Chinese dialogue) educational content for language-supported classrooms.
Quick Start
- Step 1: Provide the paper as a PDF or paste content to the skill (e.g., /paper-comic /path/to/paper.pdf or paste the paper text).
- Step 2: Pick an art style (classic, tech, warm, chalk) or let the system auto-select based on the field.
- Step 3: Review the generated outputs (outline.md, characters.md, prompts, and page images) and iterate on the storyboard and prompts as needed.
Best Practices
- Identify 1–3 core innovations from the paper before drafting the storyboard.
- Define Mentor, Student, and optional Concept embodiment characters and keep them visible on ≥60% of pages.
- Write all dialogue in Chinese within the storyboard and panels.
- Choose an art style aligned with the paper’s field (classic for general topics, tech for AI/engineering, warm for education/psychology, chalk for math/physics).
- Plan 8–12 pages with 3–5 panels per page and clearly map which characters and scenes appear on each panel.
Example Use Cases
- Explain a deep learning optimization paper using a tech-style comic to illustrate gradients and convergence.
- Visualize a cognitive science study on learning mechanisms with warm styling to feel approachable.
- Summarize a theoretical physics or math paper using chalk style to convey abstract concepts as diagrams.
- Convert a computer vision method paper into an 8–12 page comic for lecture slides.
- Turn an education technology paper into classroom-ready material with mentor/student dialogue in Chinese.