deepseekplugins

DeepSeek Harness plugin

dsh-desktop-hynahla

DSH host plugin: OS-level desktop control tools (screen OCR with coordinates, mouse click/drag, Unicode typing, key combos) so the model can operate the whole browser including the address bar, and

Development & Runtime
Jump to install

Source facts

Repository
Hyna-hla/dsh-desktop
Latest update
Aug 15, 2026
Category
Development & Runtime
GitHub stars
0
Format
plugin
Catalog evidence
Upstream dsh.bundle evidence
Evidence path
package.json#dsh.bundle
Checked against
0.1.0-rc.8
Upstream check date
2026-08-20

This evidence comes from the upstream catalog. This site has not installed, run, or security-reviewed the plugin.

Install

Start with a prompt that asks an agent to review the GitHub repository and source. Switch to the command if you want to install it yourself.

Copy this prompt into DSH, Codex, or another agent and ask it to review the GitHub repository and source first.

Do not install or run any commands yet. Read this plugin's GitHub repository, README, and relevant source code. Then answer the questions below clearly and directly so I can decide whether it fits my needs:

1. What is this plugin, and what problem does it solve?
2. Who is it for, and what are its typical use cases?
3. How is it used after installation? Include one minimal example.
4. What known limitations or privacy, security, compatibility, or maintenance risks does it have?
5. Give a clear recommendation: recommend, conditionally recommend, or do not recommend, with reasons.

Distinguish statements documented by the repository, inferences from source code, and unknowns. If evidence is insufficient, say so explicitly. Do not guess or simply repeat the README.

GitHub: https://github.com/Hyna-hla/dsh-desktop
Plugin: dsh-desktop-hynahla
Author: Hyna-hla

Check the source files

Read the README and other files from this plugin directory before installing.

File explorer3 files
README.mdSource · read only

dsh-desktop

宿主插件：操作系统级桌面控制工具，让模型操作整个浏览器（含地址栏/搜索栏）和任意窗口。

工具

工具作用
desktop_ocr截屏 + Windows OCR，返回每个词的坐标框（定位用）
desktop_screen虚拟屏幕尺寸与原点
desktop_click(x, y, button?, double?)移动鼠标并点击（左/右/中，可双击）
desktop_drag(x1,y1,x2,y2)按住拖动
desktop_type(text)Unicode 文本输入（支持中文）
desktop_press(combo)组合键：ctrl+l 地址栏、enter、alt+tab、f5、ctrl+t…
desktop_cursor当前光标位置
desktop_screenshot(path?)截屏存 PNG

典型流程（打开网址）：desktop_press "ctrl+l" → desktop_type "https://..." → desktop_press "enter"；任意界面点击：desktop_ocr 找坐标 → desktop_click。

原理与边界

  • 工具在宿主进程里 spawn powershell.exe 跑 lib/desktop.ps1（Win32 SetCursorPos / mouse_event / SendInput + Windows 自带 OCR），完全不受 DSH 沙盒限制；
  • 与 Edge 扩展互补：扩展管网页内容，桌面层管浏览器框架和所有程序；
  • 高权限操作：模型只有在收到你的指令时才调用这些工具；屏幕上的一切它都能看（OCR）、能动。

构建安装

pnpm install
pnpm build
.\scripts\install-to-profile.ps1 -Name dsh-desktop -SourceDir .
# 重启 DeepSeek Harness
Back to searchOpen GitHub repository

More related plugins

View category