$ show asuojun/claude-vision-skill
This repository provides a lightweight CLI tool (`vision.js`) that enables text-only AI models (like Claude Code without native vision) to 'see' images by converting them to text via an external vision API. The core script reads images from local files, URLs, or the system clipboard (via platform-specific helpers for macOS and Windows), encodes them as base64, and sends them to any OpenAI-compatible vision API (defaulting to Alibaba Cloud's DashScope). It features automatic clipboard fallback, configurable API credentials via environment variables, and clear error handling. The repo also includes documentation files (`AGENTS.md`, `CLAUDE.md`, `SKILL.md`) that instruct AI agents on when and how to invoke the script, plus integration instructions for the cyberboss chatbot framework. It is a practical, well-structured utility that solves a common limitation of text-only AI models.
The LLM identified 3 files worth highlighting for reuse:
The core script that orchestrates image reading, encoding, and API calling. It demonstrates clean argument parsing, automatic clipboard fallback when no valid image source is provided, and platform-specific clipboard reading via external scripts. The code is self-contained (only depends on Node.js built-ins and optional dotenv), uses environment variables for configuration, and handles errors gracefully. It can be extracted and reused in any project needing to send images to an OpenAI-compatible vision API with minimal modification.
A minimal Swift script that reads the current image from the macOS system clipboard and saves it as a PNG file. It uses AppKit's NSPasteboard and NSBitmapImageRep to handle both PNG and TIFF clipboard data. This is a self-contained, reusable utility for any macOS project that needs to extract an image from the clipboard programmatically.
A PowerShell script that reads the current image from the Windows clipboard using System.Windows.Forms and System.Drawing, then saves it as a PNG file. It is self-contained and can be reused in any Windows project requiring clipboard image extraction, demonstrating knowledge of Windows GUI automation via PowerShell.