CordisPluginGuide & Directory
Contact

niyongsheng / free-vision-skill

Listed

Local‑only vision skill for macOS 本地化识图技能

mainToolSkill View source

Installation

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

This installation command is an unverified starting point generated from the GitHub repository address.

README

Maintainer-authored documentation snapshot.

View on GitHub ↗
Commit c47846fSynced Aug 18, 2026

free-vision-skill

License Platform Framework Privacy

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

Notes

  • Requires macOS 11+ & Xcode Command Line Tools
  • First run compiles ~5–10s, cached afterwards

License

MIT © 2026 Nico

Project files and signals

Shown items are public repository signals detected in the directory snapshot.

TestsDetected
ExamplesDetected

Repository information

Language
TypeScript
License
MIT
Latest release
v0.3.1
Last updated
Aug 15, 2026, 11:03 AM

Install deliberately

Review source code, permissions, lifecycle hooks, dependencies and network access. Test untrusted plugins in an isolated environment.

Related plugins

More plugins

View all plugins

picturereader

Model · Tool · Skill

21

DSH plugin: pixel-to-text image reading for text-only models. image_scan/image_ocr/image_sample tools + image-reading skill (34-image trained methodology). Pure local, optional PaddleOCR.

npx -y @deepseek-ai/dsh plugin --profile web add github:jing-hy/picturereader
GitHub installView details

dsh-image-bridge

Tool · Skill

5

DSH 插件：让纯文本模型也能看图。Web 端直接粘贴图片即可发送，无需指定图片路径；模型自主调用视觉技能查看，多模态模型原生直通，零skill绑定。

npx -y @deepseek-ai/dsh plugin --profile web add github:kbpoyo/dsh-image-bridge
GitHub installView details

DeepSeek_Prism

Model · Tool · Skill

3

为纯文本模型按需识图：DSH 零补丁 Cordis 插件（prism_see 工具 + 图片 VEP 降级 + 技能运行时注册）+ Codex Skill；多 Provider 视觉 API，VEP/1 低 Token 视觉证据包

npx -y @deepseek-ai/dsh plugin --profile web add github:YOGEMOW/DeepSeek_Prism
GitHub installView details

dsh-vision-skill

Tool · Skill

2

Vision skill plugin for DeepSeek Harness (image analysis and OCR)

npx -y @deepseek-ai/dsh plugin --profile web add github:DDDFXYqiming/dsh-vision-skill
GitHub installView details

dsh-plugins

Model · Tool · Skill

1

DeepSeek Harness (DSH) plugins. qwen-image gives a text-only coding model eyes: an image goes to a Qwen-VL route through ctx.llm and comes back as text, so DeepSeek keeps coding while Qwen looks. Pure ESM, no build permission at install. | DSH 插件集：qwen-image 让纯文本模型借千问 VL 读图，返回文本；纯 ESM，安装无需构建授权。

npx -y @deepseek-ai/dsh plugin --profile web add github:zjcdkj/dsh-plugins
GitHub installView details

modlens

Model · Tool · Skill

3073

The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。

npx -y @deepseek-ai/dsh plugin --profile web add github:liustack/modlens
GitHub installView details