dsh-plugin-vision-toolkit
DeepSeek Harness 的视觉工具包——glance、ground、detect、crop CLI 工具，帮助仅支持文本的智能体理解图像
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add dsh-plugin-vision-toolkit@0.1.1Plugin Vision Toolkit 以 dsh-plugin-vision-toolkit 发布，当前版本为 0.1.1。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
正在加载相关插件…
Vision toolkit for DeepSeek Harness -- give text-only agents the ability to see images.
Provides CLI tools that call a vision API (DeepSeek VL, GPT-4V, or any OpenAI-compatible endpoint) to describe, locate, detect, and crop elements from images. Registered as a dsh skill so agents know when and how to use them.
glance -- describe, ask about, or OCR an imageground -- locate a specific element (returns bounding box)detect -- find all instances of an element kindcrop -- cut a region from an imagedsh plugin --profile your-profile add dsh-plugin-vision-toolkit
Set environment variables:
export VISION_API_KEY=sk-xxx # Vision API key (falls back to DEEPSEEK_API_KEY)
export VISION_BASE_URL=https://... # API endpoint (falls back to DEEPSEEK_BASE_URL)
export VISION_MODEL=deepseek-vl2 # Vision model name
# Describe an image
glance screenshot.png
# Ask a question
glance screenshot.png -q "What error is shown?"
# OCR
glance screenshot.png --ocr
# Find a button
ground screenshot.png "the login button"
# Output: 450,820,620,870
# Find all buttons
detect screenshot.png "buttons"
# Crop a region
crop screenshot.png 450,820,620,870 button.png
The plugin registers a skill in the system prompt that teaches the agent about the vision tools. When the agent encounters an image (user pastes one, references a screenshot, etc.), it calls the appropriate CLI tool which:
The agent never sees raw pixels -- it gets text descriptions it can reason about.
MIT -- YYTbit