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。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:free-vision-skill(niyongsheng/free-vision-skill)
仓库:https://github.com/niyongsheng/free-vision-skill
本站详情页:https://www.yhbd.top/plugins/niyongsheng-free-vision-skill/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 4 · 最近提交 2026-08-19 · 主语言 TypeScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- 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
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=truefor 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
Alisa0808/vox-director
Anionex/agent-vision-toolkit
Anionex/dsh-vision-toolkit
shanliuling/dsh-image-gen
zhaoolee/notes
Fishsb/dsh-prompt-enhancer
chiphoton/DeepSeek-Harness-Video-Director