free-vision-skill
Run the following command in DeepSeek Harness:
dsh plugin install niyongsheng/free-vision-skill
Paste the following prompt into your AI chat to install this plugin:
You can install this plugin in DeepSeek Harness by running the command `dsh plugin install niyongsheng/free-vision-skill`, with the full source code at https://github.com/niyongsheng/free-vision-skill.
About this plugin
In the digital era, image processing needs are growing, but many cloud-based solutions raise privacy concerns by relying on external servers. The free-vision-skill plugin leverages the macOS Vision framework to enable fully local image understanding, ensuring images never leave your Mac and protecting your privacy. It offers two core tools: view_image for describing image content like scenes, people, QR codes, and composition; and ocr_image for text extraction with support for table structure and coordinates, accepting inputs via HTTP(S) URL, base64, or local path. This plugin is ideal for privacy-conscious macOS users, including developers, researchers, and everyday users, especially suitable for offline image processing or protecting sensitive data. It requires macOS 11+ and Xcode Command Line Tools, with initial compilation taking about 5-10 seconds, cached for subsequent runs.
Use Cases
- Extract text from images in offline environments.
- Process images with tables to obtain structured data.
- Describe image content without compromising privacy.
Best For
- Individual users who prioritize data privacy.
- Developers needing local image processing.
- Researchers analyzing image data.
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.