Skip to main content
plugin

vision-specialist · rohitg00 — Claude Code plugin: image analysis and OCR

A Claude Code plugin that analyzes images, extracts text from screenshots, and interprets visual content. Triggered by /vision-specialist:analyze or when working with images.

Apache-2.0 ★ 2,858 updated 2026-05-12

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add rohitg00/awesome-claude-code-toolkit
/plugin install vision-specialist@claude-code-toolkit
Open on GitHub

What vision-specialist does

The plugin adds computer vision capabilities: it recognizes image content, reads text from interface screenshots and documents, and describes visual elements. Works with PNG, JPEG, WebP, and other raster formats.

Requires Claude Code with filesystem access to the project directory. The plugin reads images from the working directory and returns structured descriptions: recognized text, UI elements, color schemes.

Install from the marketplace with two commands: first /plugin marketplace add rohitg00/awesome-claude-code-toolkit, then /plugin install vision-specialist@claude-code-toolkit.

What it helps with

  • extract text from application screenshots or documents
  • describe image content for documentation
  • analyze UI elements in mockups
  • recognize the structure of visual content
  • get a text representation of a graphic file

Example prompts for the agent

  • Analyze dashboard.png and extract all text
  • Describe what's shown in mockup.jpg
  • Run /vision-specialist:analyze on screenshot-error.png

How to install vision-specialist

Plugin marketplace

/plugin marketplace add rohitg00/awesome-claude-code-toolkit
/plugin install vision-specialist@claude-code-toolkit

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about vision-specialist

How to install vision-specialist in Claude Code?

Run /plugin marketplace add rohitg00/awesome-claude-code-toolkit, then /plugin install vision-specialist@claude-code-toolkit.

What does vision-specialist do?

It analyzes images, extracts text from screenshots, and describes visual content in files.

Which formats does vision-specialist support?

It supports raster formats: PNG, JPEG, WebP, and other common image file types.

Source text

vision-specialist · Apache-2.0
Image and visual analysis with screenshot interpretation and text extraction

© rohitg00 · Apache-2.0 · rohitg00/awesome-claude-code-toolkit

Similar plugins

All plugins for Agent setup: memory, context, orchestration →

vision-specialist by other authors comes first.

vision-specialist alanKerrigan vision-specialist is a Claude Code plugin for computer vision tasks, including OCR, barcode detection, and document and image analysis. It activates for image or document processing tasks. ★ 1,013repo stars vision-analysis MiniMax-AI vision-analysis is a Claude Code skill that examines images through MiniMax and extracts their contents. It activates for image paths or URLs and requests about screenshots, diagrams, mockups, charts, or photos. CX Codex +1 2,700installs three.ws Vision nirholas three.ws Vision examines images, extracts screenshot text, and generates captions through visual models. Runs over stdio without billing or API credentials. CX Codex +1 ★ 284repo stars image-to-text pascalorg image-to-text — a skill for Claude Code, Codex, Cursor, Copilot, Gemini CLI and OpenCode that extracts text from images via Tesseract. Runs when you need to pull labels from a screenshot or design mockup. CX Codex +1 725installs godot-agent-vision thedivergentai godot-agent-vision — a skill that gives agents eyes in Godot projects: cross-platform screenshot capture, WebP encoding, and visual review scored by a taste receptor system. Use when agents need to see UI, assets, or the editor. CX Codex +1 287installs modlens liustack The modlens Claude Code skill sends images to a CLI for analysis and returns extracted text, layout regions, and visual clues. It runs when an image is mentioned but the model cannot view its contents. CX Codex +1 1,300installs gemini-image johnlindquist gemini-image — a skill that runs images through Gemini: pulls text out of screenshots, reads code off a picture, explains diagrams and error messages. CX Codex +1 1,200installs

From the same set178

The whole set →
golang-idioms golang-idioms is a Claude Code skill that provides idiomatic Go guidance for error handling, concurrency, and testing. CX Codex +1 ★ 2,858repo stars workflow-optimizer The workflow-optimizer plugin analyzes development workflows and suggests ways to improve them. Use it when you want recommendations on how work in a project is organized. ★ 2,858repo stars web-dev web-dev — a plugin for Claude Code that automates full-stack web app creation: generates project structure, components, and pages in a single step. ★ 2,858repo stars visual-regression Runs visual regression testing via screenshot comparison in Claude Code. Pinpoints unwanted layout shifts right after styling changes. ★ 2,858repo stars update-branch update-branch — a Claude Code plugin that rebases feature branches onto the main branch and resolves merge conflicts. Runs when syncing long-lived branches before a merge. ★ 2,858repo stars unit-test-generator unit-test-generator generates unit tests for any function or module in Claude Code. Useful when you need to cover code with tests without writing boilerplate scenarios by hand. ★ 2,858repo stars ultrathink The ultrathink plugin enables deep analysis with extended reasoning, aimed at complex problems that need more than a brief response. ★ 2,858repo stars ui-designer ui-designer — a Claude Code plugin that generates UI components from design specs with pixel precision. Runs when you need to turn a mockup into code without manual layout work. ★ 2,858repo stars

Project sponsors

Companies that keep this analytics open