SkillFoxx

Claude Vision Skill

A skill that gives image recognition to models without native vision: it sends the image to a vision model and returns a text description

  • 2,291 ★ on the repository
  • Last commit
Skill

Extended access

Why this level

  • Runs the vision.js script, reads files and the clipboard, and sends images to an external vision service
  • Requires an API key stored in a file next to the script
All reasons and checks

asuojun/claude-vision-skillAuthor:asuojun

Install

Manual install

git clone https://github.com/asuojun/claude-vision-skill.git

After cloning, ask the agent to read the README and set the skill up; it will ask for the service and key.

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Runs the vision.js script, reads files and the clipboard, and sends images to an external vision service
  • Requires an API key stored in a file next to the script

This is third-party code. Review the repository files before installing.

What it does

The skill adds image recognition to models that have no native vision, such as DeepSeek. When the user gives a file path, a URL or pastes an image, the agent runs the bundled vision.js script instead of trying to view the image directly. The script reads the image, encodes it as base64 and sends it to a vision model through an OpenAI-compatible format, then returns the answer as text. By default it recommends Qwen on the Aliyun DashScope platform, but any vision model with an OpenAI-compatible API fits, including gpt-4o-mini. It can read an image from the clipboard, using a bundled Swift helper on macOS and a PowerShell script on Windows, and falls back to the clipboard automatically when a file is not found.

Who it is for. For people working with a model that has no vision but who still want the agent to read screenshots and images.

Good fit when

  • The main model cannot read images but you need to parse a screenshot or picture
  • You want to paste an image into chat and get a description without manual commands
  • You need a cheap or free vision model through an OpenAI-compatible API

Not a fit when

  • Your model already reads images directly
  • You cannot send images to an external vision service for privacy reasons

Example request

Look at this screenshot and describe it in text

Limitations

The skill does not recognize images itself; it only forwards them to an external vision model, so you need an API key and pay the service's rates, and images leave for the provider. It needs Node, plus a Swift helper on macOS and a PowerShell script on Windows for the clipboard. By default descriptions come in Chinese unless you ask otherwise. The recommended Qwen on Aliyun is reachable from Russia without a VPN, while the OpenAI option does not work without one. SKILL.md hardcodes the author's absolute path, which you must replace with your own on install. No license is stated in the repository.

How to disable. Remove the skill folder from the skills directory, delete vision.js from the project and drop the skill's mentions from CLAUDE.md.

FAQ

Which vision model should I use?

The author recommends Qwen on Aliyun DashScope for its free tier for new users. Any other model with an OpenAI-compatible API also fits, including gpt-4o-mini; you then change the base URL and model name.

Do my images leave my machine?

Yes, the script sends the image to an external vision model. The API key is read from a .env next to vision.js and must not end up in the repository.

How is Claude Vision Skill different from models with built-in vision?

The skill adds image recognition to models without their own vision, such as DeepSeek. The agent sends the image to a vision model and gets a text description instead of viewing it directly.

How do I install Claude Vision Skill and where do images go?

Clone the repository with git clone https://github.com/asuojun/claude-vision-skill.git and connect the skill to Claude Code or Codex. Images are sent to the chosen vision model, so they leave for that service.

Discussion

No questions or reviews yet.

Skills

A skill that gives text-only models sight: an image by path or from a paste becomes structured JSON with transcribed text, layout and semantics

SkillExtended access4.9K

A set of CLI tools and a skill that give a text-only agent sight: image analysis, long-screenshot OCR and UI restoration

SkillExtended access1.3K

An MCP server that gives text models sight: it takes a clipboard image, sends it to Qwen-VL and returns a text description.

MCP serverExtended access63

Ten QianWen skills for agents: text, images, video, speech, model choice, keys, usage and payment through one entry point

SkillBroad access124

A skill that distills a person's digital twin from chat logs and documents into a ready Agent Skill package

SkillBroad access1.1K

A personal Claude Code marketplace with 100+ skills: charts, codebase mapping, video, GitHub work and subagent dispatch.

PluginExtended access375

README in short

The Chinese README explains that the skill gives vision to models that lack it by sending the image to a vision model and returning text. The core is the vision.js script in an OpenAI-compatible format that is not tied to one provider. It describes three scenarios for Claude Code: a plain project, cyberboss integration and a short explanation of how it works. It recommends Qwen on Aliyun for its free tier, but OpenAI or any compatible service works after changing the base URL and model. Installation is automatic via the agent following the README, or manual by copying vision.js and CLAUDE.md into the project.

README badge

Original SKILL.md

---
name: claude-vision-skill
description: Use when the user shares, pastes, or references an image (local path or URL) and you need to describe, analyze, or recognize its content, especially when the current model cannot read images directly. Run the bundled vision.js helper to convert the image into text.
---

# Vision Helper

The current model may not support native image input. When the user provides an image path or URL, do not rely on viewing the image directly. Instead run:

node /path/to/claude-vision-skill/vision.js "<absolute image path>" "<prompt>"

For an image URL use --url, for a pasted image use --clipboard. The --clipboard mode reads the current image from the system clipboard (macOS uses a bundled Swift helper, Windows a bundled PowerShell script). If a local path does not exist, vision.js falls back to the clipboard automatically; pass --no-fallback to disable this.

Rules: always use the absolute path to vision.js; use an absolute image path for local files or --url for remote images; configuration lives in .env next to vision.js (DASHSCOPE_API_KEY, VISION_MODEL, DASHSCOPE_BASE_URL); never print or commit the API key.

Report a problem