Skip to content
cccskills
FreePublished on GitHub

paper-comic

Generate educational comics from academic papers, using visual storytelling to explain core ideas and innovations. Supports 4 art styles: classic (clean lines), tech (futuristic), warm (friendly), chalk (blackboard). Uses genimg-gemini-web to generate images.

The English summary is being prepared. Showing the original description.

See how to install

Files included (6)

  • SKILL.md5.6 KB
  • references/base-prompt.md2.6 KB
  • references/styles/chalk.md642 B
  • references/styles/classic.md750 B
  • references/styles/tech.md632 B
  • references/styles/warm.md648 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Paper 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

StyleFeaturesSuitable Papers
classicClean-line style, simple and professional, easy to readGeneral purpose, most papers (default)
techFuturistic look, circuit and neon elementsAI/Computer/Engineering papers
warmGentle tone, nostalgic feeling, approachablePsychology/Cognitive Science/Education
chalkBlackboard effect, academic atmosphereMath/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

  1. Read paper content (PDF or Markdown)
  2. Extract key information:
    • Paper title and authors
    • Research background and motivation
    • Core innovations (1–3)
    • Key methods/algorithms
    • Main experimental results
  3. 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):

StagePagesContent
Introduction1–2 pagesProblem background — why the research is needed
Exploration2–3 pagesLimitations of existing methods, leading to innovation
Core3–5 pagesExplain the innovation in detail, visualized with metaphors
Summary1–2 pagesExperimental 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 template
  • references/styles/classic.md - Clean-line style
  • references/styles/tech.md - Tech style
  • references/styles/warm.md - Warm style
  • references/styles/chalk.md - Chalkboard style

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Generate format-controlled research reports with evidence tracking, citations, and iterative review. This skill should be used when users request a research report, literature review, market or industry analysis, competitive landscape, policy or technical brief, or require a strict report template and section formatting that a single deepresearch pass cannot reliably enforce.

The English summary is being prepared. Showing the original description.

proyecto26/sherlock-ai-plugin39Updated Sep 1, 2026

Image generation skill using Gemini Web. Generates images from text prompts via Google Gemini. Also supports text generation. Use as the image generation backend for other skills like cover-image, xhs-images, article-illustrator.

The English summary is being prepared. Showing the original description.

proyecto26/sherlock-ai-plugin39Updated Sep 1, 2026

Transform academic papers into in-depth technical articles with multiple writing style options. Use the MinerU Cloud API for high-precision PDF parsing, automatically extracting images, tables, and formulas. Optional formula explanations and GitHub code analysis, generating Markdown and HTML formats.

The English summary is being prepared. Showing the original description.

proyecto26/sherlock-ai-plugin39Updated Sep 1, 2026

Analyzes research papers (PDF/arXiv URL) and converts them into executable code. Automatically activated upon requests for paper replication, algorithm implementation, or research reproduction. Responds to requests like "Implement this paper", "paper2code", "Convert paper to code".

The English summary is being prepared. Showing the original description.

proyecto26/sherlock-ai-plugin39Updated Sep 1, 2026

Transform research papers into professional visual schemas. Analyzes paper logic, selects optimal layout patterns, and generates detailed prompts for AI image generation.

The English summary is being prepared. Showing the original description.

proyecto26/sherlock-ai-plugin39Updated Sep 1, 2026

See all skills by proyecto26

Report a problem with this skill