niyongsheng/free-vision-skill

free-vision-skill

Name: free-vision-skill
Author: niyongsheng

UIVision3 GitHub stars· updated 2026-08-19

free-vision-skill is a community DeepSeek Harness plugin. Read the repository README before installing.

Install

npx -y @deepseek-ai/dsh plugin --profile web add @niyongsheng/free-vision-skill

Restart `dsh web` after install. Bundle APIs can change during the developer preview.

README badge

[![DSH Hub](https://dshhub.dev/badge/free-vision-skill.svg)](https://dshhub.dev/plugins/free-vision-skill)

Paste this into your README. The star count updates with every catalog sync.

GitHub Install guide

From the README

Excerpt from niyongsheng/free-vision-skill, cleaned of badges and images.

free-vision-skill

Fully-local image understanding (OCR / table extraction / description) via macOS Vision. Images never leave your Mac.

Install (DSH-Plugin)

dsh plugin add @niyongsheng/free-vision-skill

Then add to cordis.patch.yml:

- insert:
    - id: free-vision-skill
      name: '@niyongsheng/free-vision-skill'
      config:
        timeout: 120000

Tools

view_image — describe image content (scene, people, QR, composition)
ocr_image — extract text; layout=true for table structure + coordinates

Input: http(s) URL / base64 / local path.

Paste-to-path (Web UI)

Paste (⌘V) an image in the DSH web input box → its local absolute path is inserted. Loopback-only upload, magic-byte checked: PNG / JPEG / GIF / WebP / HEIC / HEIF.

Usage (Claude Code Skill)

swift scripts/ocr.swift image.png          # OCR
swift scripts/ocr.swift --layout image.png # table + coordinates
swift scripts/ocr.swift --describe image.png # describe image