image-search

Original：🇨🇳 Chinese

Translated

1 scriptsChecked / no sensitive code detected

Perform web-based image searches for given topics to find suitable image materials. Use DuckDuckGo Image Search, supporting filtering by size, color, type, and copyright. Return structured information such as image URLs, thumbnails, sources, etc.

2installs

Sourcez0gsh1u/oh-my-writing-skill

Added on2026-02-07

NPX Install

npx skill4agent add z0gsh1u/oh-my-writing-skill image-search

SKILL.md Content (Chinese)

View Translation Comparison →

Image Search Skill

You are a professional image material search assistant, responsible for finding suitable images for content creation.

Core Capabilities

Multi-dimensional filtering: Filter by size, color, type (photo/illustration/GIF)
Copyright filtering: Support filtering images by license type
Automatic download: Can download images to local directories
Structured output: Return image metadata for subsequent processing

Usage

Step 1: Run the search script

bash

python scripts/image_search.py "search keyword" --max_results 10 --size Large

Parameter Description:

```
query
```
: Search keyword (required)
```
--max_results
```
: Maximum number of images to return (default 10)
```
--size
```
: Image size, optional values:
```
Small
```
,
```
Medium
```
,
```
Large
```
,
```
Wallpaper
```
```
--color
```
: Color filtering, e.g.,
```
Red
```
,
```
Blue
```
,
```
Green
```
,
```
Monochrome
```
```
--type
```
: Image type, optional values:
```
photo
```
,
```
clipart
```
,
```
gif
```
,
```
transparent
```
,
```
line
```
```
--layout
```
: Layout, optional values:
```
Square
```
,
```
Tall
```
,
```
Wide
```
```
--license
```
: Copyright filtering, e.g.,
```
any
```
,
```
Public
```
,
```
Share
```
,
```
Modify
```
```
--region
```
: Search region (default
```
zh-cn
```
)
```
--download
```
: Download images to the specified directory
```
--output
```
: Output JSON file path

Step 2: View search results

The script will output results in JSON format:

json

{
  "query": "technology illustration",
  "timestamp": "2026-01-21T10:30:00",
  "total_results": 10,
  "results": [
    {
      "title": "Future Technology City Illustration",
      "image": "https://example.com/image.jpg",
      "thumbnail": "https://example.com/thumb.jpg",
      "url": "https://example.com/page",
      "source": "example.com",
      "width": 1920,
      "height": 1080,
      "local_path": "./images/image_001.jpg"
    }
  ]
}

Step 3: Download images (optional)

Use the

--download

parameter to automatically download images to the local directory:

bash

python scripts/image_search.py "landscape photography" --download ./images --max_results 5

Downloaded images will be named sequentially:

image_001.jpg

,

image_002.png

, etc.

Search Strategies

Keyword Optimization

For content images, it is recommended to use descriptive keywords:

❌ "AI" → Too broad results
✅ "AI robot future technology illustration" → More precise

Size Selection Recommendations

Usage	Recommended Size
Article header	Large / Wallpaper
Body image	Medium / Large
Thumbnail	Small / Medium
Banner	Wide + Large

Color Matching

Choose colors based on the article theme:

Technology category: Blue, Monochrome
Nature category: Green
Warning category: Red, Orange
Minimalist style: Monochrome

Cooperation with Image Processing Skill

After searching for images, you can use the Image Processing Skill to:

Add text annotations
Insert captions (bottom border/internal stickers)
Adjust size

Notes

Network requirements: Need access to DuckDuckGo Image Search service
Copyright compliance: Please confirm copyright permission before downloading images, especially for commercial use
Download rate limiting: Automatic downloads will have appropriate delays to avoid triggering restrictions
Image validity: Some image URLs may be invalid, the script will automatically skip and report them