code-screenshot-reader

Extract code from screenshots with OCR and return language and region metadata.

5|Updated Apr 15, 2026
One-click install
npx skills add https://github.com/47network/Sven --skill code-screenshot-reader
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-screenshot-reader
Source: https://github.com/47network/Sven/tree/main/skills/ocr/code-screenshot-reader
Command: npx skills add https://github.com/47network/Sven --skill code-screenshot-reader

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Screenshots and images often contain programming code that is difficult to copy accurately due to formatting and fonts. This Skill uses code-aware OCR to reliably extract code blocks while preserving indentation and syntax cues.

Core Features & Use Cases

  • Code-aware OCR preserves indentation and detects code blocks in images for clean copy-paste results.
  • Language detection infers the programming language from code patterns when not explicitly provided.
  • Single or multi-region extraction handles multiple code regions within a single image and returns structured results for each.

Quick Start

Provide a screenshot content string and set action to extract_code to obtain code blocks with detected language.

Frequently Asked Questions about code-screenshot-reader

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract code from a screenshot?

You extract code from a screenshot by applying code-aware OCR that processes the image and returns plain code. This method preserves indentation and detects code blocks for clean copy-paste results.

What is code-aware OCR and how does it work for programming images?

Code-aware OCR is an extraction technique that identifies programming patterns in images and returns plain code with detected language. It processes single or multiple code regions to provide structured results for each block.

Can I detect the programming language from a code screenshot automatically?

Yes, you can detect the programming language from a code screenshot automatically. The language detection feature infers the programming language from code patterns when an explicit language hint is not provided.

Does OCR work with multi-region code extraction in a single image?

Yes, OCR supports multi-region code extraction in a single image. It handles multiple code regions within a single image and returns structured results for each, including region-level metadata and a total region count.

How do I start extracting code blocks from images using automation?

To start extracting code blocks from images using automation, provide a screenshot content string and set the action to extract_code. This returns the code blocks along with the detected language and confidence score.