Delegate image understanding tasks to configurable OpenAI-compatible vision models when native vision is unavailable.

Vision

Bring image recognition, OCR, and visual reasoning to Claude Code environments lacking native vision capabilities via a lightweight Python script.

Image AnalysisAsset ProcessingAgent Workflow

3 Stars0 ForksUpdated Aug 8, 2026View source

Overview Capabilities Quick start

Skill impact

A focused workflow with measurable value.

Stars

Forks

Updated

Aug 8, 2026

About Vision

See and understand images when you (the current model) have no native vision. Use this WHENEVER you need to look at, read, describe, OCR, or reason about the contents of an image, screenshot, photo, diagram, chart, UI mockup, or scanned page — including when the user references a local image file or an image URL and you cannot view it yourself.

What Vision Can Help You Do

Delegates image processing tasks such as screenshot analysis, OCR text extraction, UI mockup review, and diagram interpretation to an external vision model from within a text-only environment.

Transcribe text from images using optical character recognition while preserving layout

Analyze and diagnose error messages from application screenshots

Extract structured data and tables from charts and diagrams

Interpret user-uploaded photos, UI mockups, and remote image URLs

Common use cases

Extracting text and formatting from receipts and scanned pages

Debugging software error logs captured via screenshots

Converting visual charts and diagrams into markdown tables

Comparing UI implementation against design mockups

Explaining software architecture diagrams and remote image assets

Quick start

Install command

npx skills add kotot/vision@vision