Skip to content
Skills Library
Data & analytics · Analysis

vision-analyze

/vision-analyze

Image analysis using multimodal vision models. Use when user needs to: (1) Describe what's in an image, (2) Extract text from images (OCR), (3) Analyze visual content, (4) Compare images, (5) Answer questions about images. Supports JPG, PNG, GIF, WebP formats.

Licence
MIT
Last repository change
20.10.2026

Assessment and security

95/ 100Class: good
Format20 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
3
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 20.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Image analysis using multimodal vision models. Use when user needs to: (1) Describe what's in an image, (2) Extract text from images (OCR), (3) Analyze visual content, (4) Compare images, (5) Answer questions about images. Supports JPG, PNG, GIF, WebP formats.

Original author description

Image analysis using multimodal vision models. Use when user needs to: (1) Describe what's in an image, (2) Extract text from images (OCR), (3) Analyze visual content, (4) Compare images, (5) Answer questions about images. Supports JPG, PNG, GIF, WebP formats.

How it works

  1. Quick Start
  2. Usage Patterns
  3. Tips
  4. When to Use
Original SKILL.md headings · 88 lines, 273 words
SKILL.md preview
---
name: vision-analyze
description: Image analysis using multimodal vision models. Use when user needs to: (1) Describe what's in an image, (2) Extract text from images (OCR), (3) Analyze visual content, (4) Compare images, (5) Answer questions about images. Supports JPG, PNG, GIF, WebP formats.
metadata:
  {
    "openclaw":
      {
        "emoji": "👁️",
        "requires": {},
      },
  }
---

# Vision Analyze

Analyze images using the built-in vision capabilities of multimodal AI models.

## Quick Start

### Analyze an Image

Describe what's in an image:

```python
# The agent will automatically use vision when you provide an image path
image("/path/to/image.jpg", prompt="Describe what's in this image")
```

### Extract Text (OCR)

Extract text from images:

```python
image("/path/to/document.png", prompt="Extract all text from this image")
```

### Analyze Multiple Images

Compare or analyze multiple images:

```python
images(["/path/to/image1.jpg", "/path/to/image2.jpg"], 
       prompt="Compare these two images and describe the differences")
```

## Usage Patterns

### Visual Q&A

Ask specific questions about image content:

```python
image("menu.jpg", prompt="What are the prices of the main courses?")
image("chart.png", prompt="What trend does this graph show?")
image("screenshot.png", prompt="What error message is displayed?")
```

### Content Moderation

Check image content:

```python
image("upload.jpg", prompt="Is this image appropriate for a professional setting?")
```

### Data Extraction

Extract structured data from visual content:

```python
image("receipt.jpg", prompt="Extract the date, total amount, and items purchased")
image("business_card.png", prompt="Extract name, phone, email, and company")
image("form.jpg", prompt="Extract all filled fields as key-value pairs")
```

### Visual Comparison

Compare images:

```python
images(["before.jpg", "after.jpg"], 
       prompt="What changes were made between these two images?")
```

## Tips

- **Be specific**: The more specific your prompt, the better the results
- **Multiple images**: You can analyze up to 20 images at once
- **Supported formats**: JPG, PNG, GIF, WebP
- **Size limits**: Large images are automatically resized

## When to Use

- Reading text from screenshots, documents, or photos
- Describing visual content for accessibility
- Analyzing charts, graphs, or diagrams
- Comparing visual changes
- Extracting data from forms or receipts
- Understanding UI elements or error messages
Files in this package (3)
  • SKILL.md 2 KB
  • _meta.json 1 KB
  • .clawdhub/origin.json 1 KB

Versions

The database has no other skills named vision-analyze.

Database snapshot: 13.11.2026 · package version 2b41deeac683 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 95fal-vision
    Analyze images using AI — segment objects, detect objects, extract text (OCR), describe images, ask questions about images. Use when the user requests "Segment image", "Detect objects", "OCR", "Extract text from image", "Describe image", "What's in this image", "Image analysis".
  • 100vision-analysis
    Analyze, describe, and extract information from images using the MiniMax vision MCP tool. Use when: user shares an image file path or URL (any message containing .jpg, .jpeg, .png, .gif, .webp, .bmp, or .svg file extension) or uses any of these words/phrases near an image:…
  • 90openakita/skills@image-understander
    Analyze images using GPT-4 Vision for detailed description, OCR text extraction, object recognition, and visual Q&A. Use when the user needs to understand image content, extract text from screenshots, identify objects in photos, or ask questions about images via OpenAI GPT-4 Vision API.
  • 98modlens
    Plug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .heic, .heif) appears anywhere in the conversation (typed by the user, injected as a `[Image: source: <path>]` line, or inside a tag) and you cannot…
  • 100convert-image-to-jpg
    Convert local image files from common raster formats into JPG while setting a target DPI (default 96). Use when Codex needs to convert a file or folder of images such as HEIC, HEIF, PNG, TIFF, WebP, BMP, GIF, AVIF, or JPEG into `.jpg` for upload, OCR, archiving, or tools that require JPEG output.
  • 100convert-to-webp
    Convert images (PNG, JPG, etc.) to WebP format. Use when saving screenshots or images for web projects, Hugo sites, or any context where WebP is preferred.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.