hasna/read-image
skills/read-image/SKILL.md
Analyze an image from a local path or URL with Claude vision. Supports prompt-controlled description, OCR, object counting, and brand/visual extraction.
data-ai
Updated May 12, 2026
$ install --global
skillsauthnpx skillsauth add hasna/skills read-imageInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 12, 2026, 2:51 AM189.8s4 files scanned
SKILL.md
- name:
- read-image
- description:
- Analyze an image from a local path or URL with Claude vision. Supports prompt-controlled description, OCR, object counting, and brand/visual extraction.
Read Image
Analyze an image with Claude vision and return structured JSON containing the prompt, model, and extracted analysis.
Features
- Supports local files and remote URLs
- Accepts PNG, JPG, JPEG, GIF, and WEBP
- Prompt-controlled output for OCR, object counting, branding, layout analysis, and more
- Emits plain text or JSON
Requirements
ANTHROPIC_API_KEYmust be available in the environment
Usage
# Describe a local image
read-image --input ./product-shot.jpg
# OCR a receipt from a URL
read-image \
--input https://example.com/receipt.png \
--prompt "Extract every line item, subtotal, tax, and total."
# Return plain text only
read-image --input ./wireframe.webp --text
Options
| Option | Description | Default |
|--------|-------------|---------|
| -i, --input <path-or-url> | Local image path or image URL | required |
| -p, --prompt <text> | What Claude should extract or describe | detailed description + OCR |
| -m, --model <name> | Anthropic model to call | ANTHROPIC_MODEL or built-in default |
| --max-tokens <n> | Maximum response tokens | 1200 |
| -o, --output <path> | Save result to a file | stdout |
| --text | Emit only Claude's text response | false |
| --help | Show usage | |
| --version | Show version | |
Related Skills
hasna/voiceover-jingle-pack
tools
VerifiedTrustedCommunity
Generate hosted voiceover variants and short jingles
5SKILL.mdUpdated May 29, 2026
hasna/video-highlight-pack
tools
VerifiedTrustedCommunity
Generate premium video highlight packages with clip plans, captions, thumbnails, chapter markers, social copy, edit decisions, and manifest metadata.
5SKILL.mdUpdated May 29, 2026
hasna/write
testing
VerifiedTrustedCommunity
Generate high-quality articles using parallel AI agents. Supports research, writing, and optional cover image generation. Write single articles or batch process multiple topics with configurable parallelism.
5SKILL.mdUpdated May 12, 2026
hasna/video
testing
VerifiedTrustedCommunity
Generate videos using OpenAI Sora, Minimax Hailuo, Gemini Veo, or Seedance through the hosted Skills runtime with provider-cost pricing.
5SKILL.mdUpdated May 12, 2026