Analyzes and extracts information from images and videos.

Install

mkdir -p .claude/skills/image-analysis && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17143" && unzip -o skill.zip -d .claude/skills/image-analysis && rm skill.zip

Installs to .claude/skills/image-analysis

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

图片分析与识别,可分析本地图片、网络图片、视频、文件。适用于 OCR、物体识别、场景理解等。当用户发送图片或要求分析图片时必须使用此技能。
69 chars · catalog descriptionno explicit “when” trigger
Beginner

Key capabilities

  • Analyze local images using vision models
  • Analyze network images using vision models
  • Perform OCR to extract text from images
  • Identify objects and understand scenes in images
  • Compare multiple images for differences
  • Analyze video content for summarization

How it works

The skill uses either the Zhipu GLM-4V or Qwen Qwen-VL vision model to analyze images or videos based on a given prompt.

Inputs & outputs

You give it
Image path (local or URL) or video path, and a prompt for analysis
You get back
Description of image content, extracted text, object locations, or video summary

When to use image-analysis

  • Extract text from screenshot
  • Analyze image content
  • Describe visual elements

About this skill

图片分析与识别

支持智谱 GLM-4V 和千问 Qwen-VL 两种视觉模型。

当用户发送图片或要求分析图片时,必须使用此技能,不要使用 PIL、pytesseract 等其他方法。

配置

编辑 skills/image-analysis/scripts/config.json

{
  "default_model": "zhipu",
  "zhipu": {
    "api_key": "your-zhipu-api-key",
    "model": "glm-4.6v-flash"
  },
  "qwen": {
    "api_key": "your-qwen-api-key",
    "model": "qwen3-vl-plus"
  }
}

API Key 获取:

命令行调用

# 分析本地图片(最常用)
python3 skills/image-analysis/scripts/vision.py analyze --image 图片路径 --prompt "描述图片内容"

# 分析网络图片
python3 skills/image-analysis/scripts/vision.py analyze --image https://example.com/image.jpg --prompt "描述图片"

# 多图对比
python3 skills/image-analysis/scripts/vision.py analyze --image img1.jpg --image img2.jpg --prompt "对比差异"

# 指定模型
python3 skills/image-analysis/scripts/vision.py analyze --image image.jpg --prompt "描述图片" --model qwen

# 开启思考模式(仅智谱,提升准确度)
python3 skills/image-analysis/scripts/vision.py analyze --image image.jpg --prompt "详细分析" --thinking

# 视频分析
python3 skills/image-analysis/scripts/vision.py analyze --video video.mp4 --prompt "总结视频内容"

# JSON 输出
python3 skills/image-analysis/scripts/vision.py analyze --image image.jpg --prompt "描述图片" --json

AI 调用场景

用户发送图片后,系统下载到本地(如 data/temp/images/xxx.jpg):

# 图片描述
python3 skills/image-analysis/scripts/vision.py analyze --image data/temp/images/xxx.jpg --prompt "描述这张图片的内容"

# OCR 识别
python3 skills/image-analysis/scripts/vision.py analyze --image data/temp/images/xxx.jpg --prompt "提取图片中的所有文字信息"

# 物体定位(开启思考模式)
python3 skills/image-analysis/scripts/vision.py analyze --image data/temp/images/xxx.jpg --prompt "找出物体位置,返回坐标" --thinking

模型选择

场景推荐
简单描述任意
复杂推理、物体定位智谱 + --thinking
高精度识别、文档解析千问
成本敏感智谱(免费)

注意事项

  • 本地图片自动转 Base64,支持 jpg/png/gif/webp/bmp
  • 智谱图片限制 5MB,像素不超过 6000x6000
  • 千问不支持同时处理图片、视频和文件
  • 思考模式会增加响应时间但提升准确度

When not to use it

  • When using PIL or pytesseract for image analysis
  • When the task involves only text processing without images
  • When Qwen model is used for simultaneous image, video, and file processing

Prerequisites

Zhipu API keyQwen API key

Limitations

  • Zhipu images are limited to 5MB and 6000x6000 pixels
  • Qwen does not support simultaneous processing of images, videos, and files
  • Thinking mode increases response time but improves accuracy

How it compares

This workflow use advanced vision models for complete image and video analysis, unlike basic image processing libraries.

Compared to similar skills

image-analysis side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
image-analysis (this skill)05moReviewBeginner
docetl22moReviewIntermediate
slm-lab-benchmark15moReviewAdvanced
tss-pipeline04moNo flagsAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

docetl

ucbepic

Build and run LLM-powered data processing pipelines with DocETL. Use when users say "docetl", want to analyze unstructured data, process documents, extract information, or run ETL tasks on text. Helps with data collection, pipeline creation, execution, and optimization.

29

slm-lab-benchmark

kengz

Run SLM-Lab deep RL benchmarks, monitor dstack jobs, extract results, and update BENCHMARKS.md. Use when asked to run benchmarks, check run status, extract scores, update benchmark tables, or generate plots.

12

tss-pipeline

LocNguyen-247

Use when implementing or debugging the TSS remote-sensing workflow in this workspace: Landsat/Sentinel preprocessing, ACOLITE atmospheric correction, cloud/water masking, adjacency correction, station matchup, and model training.

00

quant-analyst

zenobi-us

Expert quantitative analyst specializing in financial modeling, algorithmic trading, and risk analytics. Masters statistical methods, derivatives pricing, and high-frequency trading with focus on mathematical rigor, performance optimization, and profitable strategy development.

103355

data-engineering

pluginagentmarketplace

ETL pipelines, Apache Spark, data warehousing, and big data processing. Use for building data pipelines, processing large datasets, or data infrastructure.

13192

crawl4ai

basher83

This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines. Includes optimized extraction patterns with schema generation for efficient, LLM-free extraction.

21137

Search skills

Search the agent skills registry