niyongsheng/free-vision-skill

macOS 本地化识图技能

Project Overview项目介绍

This is a DSH-native skill plugin that provides fully local image understanding capabilities using Apple’s native Vision framework. It can be installed directly via the DSH CLI with the command dsh plugin add @niyongsheng/free-vision-skill, after which you need to add a configuration entry to your cordis.patch.yml file. It offers two core tools, view_image for describing image content like scenes, people, and QR codes, and ocr_image for extracting text with optional table structure and coordinate output. It accepts inputs via HTTP URLs, base64 encoded image data, and local file paths. All processing stays on your local Mac so images never leave your device.

This plugin is designed for DSH users who need to process image content without sending data to third-party servers. It also can be used as an independent skill for Claude Code, with standalone Swift scripts you can run directly from the command line for OCR, layout analysis, or image description. In the DSH web UI, it adds a convenient paste-to-path feature that inserts the local absolute path of a pasted image directly into the input box automatically. It checks file magic bytes to verify the image format, and supports all common types including PNG, JPEG, GIF, WebP, HEIC, and HEIF.

This plugin is released under the open source MIT license, so it is free to use, modify, and distribute for any purpose. It has a few hard requirements that you must meet before installing and running it. It only works on macOS version 11 or newer, and you must have Xcode Command Line Tools installed on your device to allow it to compile the required Swift code. The configuration step after installation requires adding a simple entry to your existing cordis.patch.yml file that specifies the plugin ID, name, and timeout setting. The first time you run the plugin after installation, it will take between 5 and 10 seconds to complete compilation.

这是一个专为DeepSeek Harness(DSH)开发的原生视觉技能插件,也可作为独立技能配合Claude Code使用。它基于macOS原生Vision框架实现完全本地的图像理解能力,支持OCR文本提取、带坐标的表格结构识别、图像内容描述,所有处理都在本地Mac完成,图像数据不会外传,支持HTTP链接、base64编码、本地路径三种输入格式。

该插件适合需要对图像内容进行文本提取或者场景分析的DSH和Claude Code用户使用。在DSH的Web界面中,用户可以直接粘贴图片,插件会自动将粘贴的图片转换为本地绝对路径插入输入框,仅本地回传,会检查图片魔数,支持PNG、JPEG、GIF、WebP、HEIC等所有常见图片格式。

该插件采用MIT许可协议免费开源,目前仅支持运行在macOS 11及以上版本的系统,需要提前安装Xcode命令行开发工具。首次使用时插件会自动完成编译,耗时大约5到10秒,编译后缓存结果,后续使用无需重复编译,用户可通过DSH命令行一键添加安装。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 4 stars - very few users, little community feedback星标只有 4,几乎没人在用,遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装(适合开发者)

CLI Install命令行安装

dsh plugin add @niyongsheng/free-vision-skill

把 niyongsheng/free-vision-skill 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

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

← 上一个 Prev dsh-plugin-deepseek-balance 下一个 Next dsh-agentmemory →