DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins
Q

@silentforfar/dsh-qq-screenshot

Qq Screenshot

Capture a screen region with QQ's own screenshot tool and share it with the agent.

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:Silentforfar/dsh-qq-screenshot#afe3eb421f717c55f53aa610fb9a6b2ddc49dacf
READMECompatibilityVersions

Compatibility and provenance

Qq Screenshot is published as @silentforfar/dsh-qq-screenshot and currently resolves to version 0.1.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated
10/21/2026

Versions

0.1.0stable
10/21/2026

Related plugins

Loading related plugins…

Latest
0.1.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
web
License
MIT
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
10/21/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in vision-media.

Experimental Voice Input Bundle@deepseek-ai/dsh-experimental-voice-input-bundleExperimental voice input with local SenseVoice; downloads its runtime on first useModlens@liustack/modlensPlug-in vision for text-only LLMs, powered by the free Antigravity CLIImage Gendsh-image-genBring ChatGPT-like image generation to DeepSeek Harness — Gemini, OpenAI, Seedream, DashScope, local ComfyUI & more.Ab Ocrdsh-ab-ocr--- description: "The out-of-tree ocr tool: recognizes a scanned PDF or image page by page, merges the pages in order only after the last one, and saves one Markdown document with the heading levels the model decided." kind: "package-reference" ---

README

QQ 截图(DSH 插件)

English

QQ Screenshot — Captures a screen region with QQ's own screenshot tool and hands the PNG to the model — from the input box button, the /screenshot command, or the qq_screenshot tool.

A DSH bundle (DeepSeek Harness plugin).

Install from the DSH plugin market

  1. Open Plugins in the DSH Web sidebar, select More next to Experimental plugins, and switch on Custom plugin markets.

  2. Open the Discover tab and add this index source:

    https://silentforfar.github.io/dsh-market-index/index.json

  3. Find QQ Screenshot (@silentforfar/dsh-qq-screenshot) in the list and press install.

Install straight from this repository

Pass this spec to plugin_manager's install_bundle (or the equivalent bundle install in your profile):

git+https://github.com/Silentforfar/dsh-qq-screenshot.git#<commit-sha>

Use a full 40-character commit SHA from this repository's history so the install stays pinned and reproducible.

Requirements. Windows, DSH 0.2.1-rc.2 or newer, and a running, signed-in QQ NT. Its screenshot hotkey is Ctrl+Alt+A by default; override it in %USERPROFILE%\.dsh\qq-screenshot.json.

License. MIT. The rest of this README documents the plugin in Chinese.


用 QQ 自带的截图工具截屏,把图片交给 DSH 里的模型。

  • 模型工具 qq_screenshot:模型可以主动调用;调用后 QQ 截图界面弹出,框选区域并按 Enter,图片保存到工作区并随结果返回(模型支持图片输入时)。
  • 输入框按钮:消息输入框左下角(权限下拉框右侧)的取景框图标,点一下就会唤起 QQ 截图;完成后会把图片路径写进输入框。
  • 命令 /screenshot:与按钮同一套逻辑,可以在输入框直接输入。

截图保存在当前会话工作区的 screenshots/ 目录,文件名形如 qq-20261018-170519.png。

依赖

  • Windows
  • QQ NT 正在运行且已登录(截图快捷键默认 Ctrl+Alt+A)
  • 完成后按 Enter,QQ 会把截图复制到剪贴板,插件从剪贴板取图

工作原理

  1. 宿主插件用 capture.ps1 通过 SendInput 触发 QQ 的截图快捷键;
  2. 轮询检测 QQ 的截图窗口(窗口类 QQScreenCapture Window Class);
  3. 等用户框选完成、QQ 把位图写入剪贴板后,把剪贴板图片保存为 PNG;
  4. 工具路径再通过 attachments 服务把 PNG 作为图片附件返回给模型。

如果 QQ 的截图快捷键不是 Ctrl+Alt+A,新建 %USERPROFILE%\.dsh\qq-screenshot.json(每次截图都会重新读取,改完立即生效):

{
  "hotkey": "Ctrl+Alt+A",
  "timeoutSec": 100
}

常见问题

  • 提示“QQ 的截图窗口没有打开”:确认 QQ 在运行并已登录;确认快捷键与配置一致。
  • 提示“截图已在 QQ 中被取消”:在 QQ 截图界面里按 Enter(复制到剪贴板)而不是点关闭;也可以先点“完成”按钮。
  • 模型看不到图:当前模型不支持图片输入时,工具只返回文件路径,可以用 read_image 查看该文件,或换一个支持图片输入的模型。