Agent Skills › Wide-Moat/open-computer-use › describe-image

describe-image

GitHub

利用 Vision AI 分析图表、截图等图像并生成文本描述，支持单图及批量文件夹处理，适用于无法直接读取图像时的辅助场景。

skills/public/describe-image/SKILL.md Wide-Moat/open-computer-use

Trigger Scenarios

需要识别或描述图片内容处理包含多个图像的文件夹

Install

npx skills add Wide-Moat/open-computer-use --skill describe-image -g -y

More Options

Non-standard path

npx skills add https://github.com/Wide-Moat/open-computer-use/tree/main/skills/public/describe-image -g -y

Use without installing

npx skills use Wide-Moat/open-computer-use@describe-image

指定 Agent (Claude Code)

npx skills add Wide-Moat/open-computer-use --skill describe-image -a claude-code -g -y

安装 repo 全部 skill

npx skills add Wide-Moat/open-computer-use --all -g -y

预览 repo 内 skill

npx skills add Wide-Moat/open-computer-use --list

SKILL.md

Frontmatter

{
    "name": "describe-image",
    "description": "Describe images (charts, diagrams, tables, screenshots) using Vision AI. Use as fallback when you cannot read an image file directly. Supports batch processing of folders."
}

Describe Image

Analyze images using Vision AI and generate detailed text descriptions in Russian.

Quick Start

# Single image
python /mnt/skills/public/describe-image/scripts/describe.py \
    -i /path/to/image.png

# Folder with images
python /mnt/skills/public/describe-image/scripts/describe.py \
    -i /path/to/folder

Parameters

Parameter	Default	Description
`-i, --input`	required	Image file or folder path
`-c, --context`	""	(optional) Context for better accuracy (e.g., "Sales dashboard Q4")
`--page`	1	(optional) Page number for folder processing
`--page-size`	50	(optional) Images per page (max 100)
`--quiet`	false	(optional) Suppress per-image logging in single-file mode

Supported Image Types

Charts and graphs (bar, line, pie, radar, scatter)
Tables and spreadsheets
UI screenshots
Flowcharts and process diagrams
Architecture diagrams
Document photos and scans

Examples

Single image:

python /mnt/skills/public/describe-image/scripts/describe.py \
    -i /home/assistant/document/images/img_001.jpg

With context for better accuracy:

python /mnt/skills/public/describe-image/scripts/describe.py \
    -i dashboard.png \
    -c "Quarterly sales report showing EMEA region performance"

Folder with images (batch processing):

# Process first 50 images
python /mnt/skills/public/describe-image/scripts/describe.py \
    -i /home/assistant/assessment/images/

# Process images 51-100 (page 2)
python /mnt/skills/public/describe-image/scripts/describe.py \
    -i /home/assistant/assessment/images/ --page 2

# Process with custom page size
python /mnt/skills/public/describe-image/scripts/describe.py \
    -i /home/assistant/assessment/images/ --page-size 100

Output

Single image: Returns structured description to stdout.

Folder: Creates manifest-N.md file in the folder. Use view to read it.

Console output:

Processed 50/150 images
Created: /home/assistant/assessment/images/manifest-1.md
Remaining pages: 2 (use --page 2, --page 3)

Use: view /home/assistant/assessment/images/manifest-1.md

After running the command, use the view tool to read the manifest file.

Manifest format (LLM-friendly XML):

<images folder="/home/assistant/assessment/images" page="1" total_pages="3">

<image path="img_001.jpg">
Horizontal bar chart showing deviations from the average score...
</image>

<image path="img_002.jpg">
Diagram with five rating categories: "Below expectations", "Needs development"...
</image>

</images>