Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计提醒

paper-comic纸漫画

Agent Skill

paper-comic 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

399

周安装

16

GitHub Stars

22

下载量

129
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:paper-comic(纸漫画)
来源仓库:https://github.com/proyecto26/sherlock-ai-plugin
仓库路径:skills/paper-comic
安装命令:
npx skills add https://github.com/proyecto26/sherlock-ai-plugin --skill paper-comic
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/proyecto26/sherlock-ai-plugin --skill paper-comic

简介

paper-comic 可将学术论文转化为 1–2 页中文漫画,通过导师与学生角色讲解概念。

  • 适用于 Codex、Claude、Cursor 等平台中需要可视化呈现科研内容、提升传播效果时使用。
  • 通过 npx skills add 安装后按步骤定义角色、创建故事板并生成图像,保持风格一致。
  • 使用前需准备 Google 账号以调用 genimg-gemini-web 技能,并注意图像版权归属问题。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

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

  1. 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

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.23%
按下载量换算43

Claude

30%
按下载量换算39

Cursor

19.28%
按下载量换算25

Gemini CLI

10.22%
按下载量换算13

安全审计

Gen Agent Trust Hub

可疑

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills