Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Vision — Multi-Provider Image Analysis

Calls external vision models (Doubao, Qwen, OpenAI, Anthropic, or any OpenAI-compatible endpoint) to turn screenshots, mockups and diagrams into text descriptions.

UtilitiesIntermediate★ 171⑂ 5AI score 9/10Last updated: Aug 3, 2026

What it does

  • Runs vision.py with an image path plus a prompt and returns a text description of the image.
  • Ships with four built-in providers — Doubao (Volcengine Ark), Qwen (DashScope), OpenAI GPT-4o, Anthropic Claude — resolved in order: --provider flag > VISION_PROVIDER env > first API key found.
  • Any custom provider works with no code changes: set {NAME}_API_KEY, {NAME}_BASE_URL, {NAME}_MODEL (and optionally {NAME}_PROTOCOL=anthropic), covering vLLM, Ollama, LiteLLM, OpenRouter, Azure OpenAI and self-hosted proxies.
  • Tunables include VISION_TEMPERATURE, VISION_MAX_TOKENS, and per-provider model overrides.
  • Supports png/jpg/webp/gif, and tells the agent to run --check-routing first so it skips the tool when the session already has native image understanding.

Who it's for

  • Developers working in CLI sessions where the model can't view images directly.
  • Frontend and design engineers automating visual regression or mockup-to-implementation comparison.
  • Teams that must route through self-hosted or regional vision models such as Doubao or Qwen.

Examples

  1. python vision.py "screenshot.png" "Describe the page layout and any visible UI issues."
  2. python vision.py --provider qwen "mockup.png" "List all components, colors, and spacing patterns."
  3. python vision.py -p openai "after.png" "Compare with the design spec, flag differences."

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/xiincs/claude-code-vision-skill/HEAD/vision/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the vision folder from the GitHub repo xiincs/claude-code-vision-skill into my ~/.claude/skills/vision/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/xiincs/claude-code-vision-skill.git /tmp/vision-skill && mkdir -p ~/.claude/skills && cp -r /tmp/vision-skill/vision ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Clone the repo: git clone https://github.com/xiincs/claude-code-vision-skill.git
  2. Copy the skill into place: mkdir -p ~/.claude/skills && cp -r claude-code-vision-skill/vision ~/.claude/skills/
  3. Make sure Python 3 is installed. If you plan to use the Anthropic provider, also run pip install anthropic.
  4. Export the API key for your chosen provider, e.g. export OPENAI_API_KEY="sk-..." (or DOUBAO_API_KEY, DASHSCOPE_API_KEY, ANTHROPIC_API_KEY).
  5. Optionally pin a default with export VISION_PROVIDER=openai; add it to your shell profile (~/.zshrc or ~/.bashrc) to persist.
  6. Restart Claude Code and ask something like "analyze this screenshot" with an image path.
  7. If nothing happens, run python vision.py --check-routing inside the skill folder to verify routing status and env vars.
View source on GitHub ↗License: MIT