Back to Details

cover-image

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

ABOUTME: Generate editorial cover images from article context using Gemini image generation

ABOUTME：基于文章内容，使用Gemini图像生成功能制作社论风格封面图

ABOUTME: Distills articles into hand-drawn sketch visual metaphors with ink stroke style

ABOUTME：将文章提炼为手绘素描风格的视觉隐喻，采用墨水笔触样式

Cover Image Skill

封面图生成技能

Generate editorial cover images using Gemini's image generation. Distill article content into a visual metaphor rendered as a hand-drawn sketch.
借助Gemini的图像生成功能制作社论风格封面图。将文章内容提炼为视觉隐喻，以手绘素描的形式呈现。

Workflow

工作流程

1. Understand the Article

1. 理解文章内容

Read the article/context provided by the user. Identify the core concept, tension, or insight that could become a visual metaphor.
阅读用户提供的文章/上下文内容，识别可转化为视觉隐喻的核心概念、矛盾点或关键见解。

2. Craft the Prompt

2. 撰写提示词

Build a prompt using this structure:
Black and white hand-drawn sketch, loose ink strokes, technical architectural drawing style.
[visual metaphor distilled from article context]. High contrast, minimalist, white background,
editorial tech illustration. --ar 16:9
Visual metaphor guidelines:
  • Translate abstract concepts into concrete imagery (e.g., "microservices" -> "separate buildings connected by bridges")
  • Prefer architectural/technical metaphors over literal depictions
  • Keep the scene simple: one strong central image, not a collage
  • Avoid text, labels, or UI elements in the image
按照以下结构构建提示词：
Black and white hand-drawn sketch, loose ink strokes, technical architectural drawing style.
[从文章内容中提炼的视觉隐喻]. High contrast, minimalist, white background,
editorial tech illustration. --ar 16:9
视觉隐喻创作指南：
  • 将抽象概念转化为具象画面（例如：“微服务” -> “由桥梁连接的独立建筑”）
  • 优先选择建筑/技术类隐喻，而非字面化呈现
  • 画面需简洁：聚焦一个核心主体，避免拼接 collage
  • 图像中避免出现文字、标签或UI元素

3. Show Prompt for Approval

3. 提交提示词待确认

Present the crafted prompt to the user. Wait for confirmation before generating.
将撰写好的提示词提交给用户，等待确认后再进行生成操作。

4. Generate

4. 生成图像

bash
uv run ~/.claude/skills/_generate_image.py "<approved prompt>" --ar 16:9 -o cover.png
bash
uv run ~/.claude/skills/_generate_image.py "<approved prompt>" --ar 16:9 -o cover.png

5. Report

5. 反馈结果

Report the saved file path and suggest reviewing the image.
告知用户生成文件的保存路径，并建议用户查看生成的图像。

Example

示例

Article about: "Why we migrated from monolith to microservices"
Prompt:
Black and white hand-drawn sketch, loose ink strokes, technical architectural drawing style.
A massive ancient stone building cracking apart, its fragments floating and reorganizing into
a constellation of small interconnected structures, linked by thin precise lines.
High contrast, minimalist, white background, editorial tech illustration. --ar 16:9
文章主题：“我们为何从单体架构迁移到微服务”
提示词：
Black and white hand-drawn sketch, loose ink strokes, technical architectural drawing style.
A massive ancient stone building cracking apart, its fragments floating and reorganizing into
a constellation of small interconnected structures, linked by thin precise lines.
High contrast, minimalist, white background, editorial tech illustration. --ar 16:9

Notes

注意事项

  • Requires 
    GEMINI_API_KEY
    or 
    GOOGLE_API_KEY
    in environment
  • Default output: 
    cover.png
    in current directory
  • Default aspect ratio: 16:9 (landscape, editorial)
  • Uses shared script: 
    ~/.claude/skills/_generate_image.py
  • 环境变量中需配置
    GEMINI_API_KEY
    或
    GOOGLE_API_KEY
  • 默认输出文件：当前目录下的
    cover.png
  • 默认宽高比：16:9（横版，社论风格）
  • 使用共享脚本：
    ~/.claude/skills/_generate_image.py