image-analyzer
Image Analyzer uses AI to process images and pull out actionable insights. Extract visible text via OCR, identify objects, describe visual content, and capture structured data from receipts, screenshots, and other image sources.
Image Analyzer extracts text and structured data from images using AI vision capabilities.
AI-generated summary based on this skill's SKILL.md
Install
gooseworks-ai/goose-skills/image-analyzer · repository language: Python
git clone https://github.com/gooseworks-ai/goose-skills
cp -r goose-skills/skills/research-tools/capabilities/image-analyzer ~/.claude/skills/image-analyzerFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What can image-analyzer extract from images using AI?
Image Analyzer extracts text via OCR, identifies objects, describes visual content, and captures structured data from receipts, screenshots, and photos. The skill uses AI to pull actionable insights from images, converting visual information into machine-readable formats for automation and analysis.
How does image-analyzer extract text from images with OCR?
Image Analyzer uses OCR technology to scan images and recognize visible text, converting it into editable, searchable data. This enables automated text extraction from documents, receipts, screenshots, and photos without manual data entry.
Can image-analyzer detect objects in photos?
Yes, Image Analyzer analyzes image content to detect and identify objects within photos. The skill recognizes visual elements and can describe what it finds, supporting object detection workflows for automated image processing and analysis.
What does image-analyzer do with website screenshots?
Image Analyzer captures and processes website screenshots to extract both text and structured data. It analyzes screenshot content, pulls out readable information, and converts visual elements into actionable data for automation and reporting.
How can image-analyzer automate receipt and document scanning?
Image Analyzer processes receipt and document images to automatically extract structured data like amounts, dates, and line items. This eliminates manual scanning and data entry, converting receipt images into machine-readable information for accounting and expense tracking.
Is image-analyzer open source and what license does it use?
Image Analyzer is released under the MIT license, making it open source and freely available for commercial and personal use. The MIT license permits modification and distribution with minimal restrictions.
SKILL.md
rendered from the published skill — quoted content, verbatim
Image Analyzer - AI Image Analysis
Setup
Read your credentials from ~/.gooseworks/credentials.json:
export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")
If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login
All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"
Analyze images to extract text, describe content, and detect objects using AI.
Workflow
Step 1: Get Image from URL
Fetch image content:
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
-H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"api":"linkup","path":"/fetch","body":{"url":"https://example.com/image.jpg"}}'
Step 2: Extract Text (OCR)
Use AI to extract text from images:
```bash curl
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 2 files
skills/research-tools/capabilities/image-analyzer/SKILL.md
skills/research-tools/capabilities/image-analyzer/skill.meta.json