跳到正文
cccskills
免费在 GitHub 公开

gui-automation

Use when you need to visually interact with a GUI — test buttons, fill forms, verify visual layouts, fuzz web pages, automate user flows, take screenshots, or perform end-to-end QA on any application. Works on cloud VMs, Docker containers, local machines, and sandboxes. Install: pip install cua.

中文简介正在准备中。当前显示原文说明。

集成工具Docker
查看安装方法

包含的文件(2)

  • SKILL.md5.6 KB
  • references/command-reference.md5.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

GUI Automation

CUA gives you eyes and hands on a real computer: see the screen, move the mouse, click, type, drag, and manage windows — like a human at the keyboard.

Use this skill for visual interaction that can't be done via shell or API.

Setup

cua --version          # check install; if missing: pip install cua

# Connect to target (pick one)
cua do switch cloud my-vm
cua do switch docker my-container
cua do-host-consent && cua do switch host   # local machine (one-time consent)

ANTHROPIC_API_KEY is optional. With it, cua do snapshot returns an AI-annotated screen with element coordinates. Without it, use screenshot and read the image yourself.

Workflow

Look → Act → Verify — repeat until done, then share:

cua do screenshot          # look
cua do click 450 280       # act
cua do screenshot          # verify
cua trajectory share       # share replay link with user

Re-screenshot after every UI change — coordinates go stale when the screen changes.

Scenarios

Click a button

cua do screenshot
cua do click 450 280
cua do screenshot

Fill a form

cua do screenshot
cua do click 400 200 && cua do type "Jane Doe"
cua do key tab            && cua do type "jane@example.com"
cua do key tab            && cua do type "SecureP@ss123"
cua do click 400 500
cua do screenshot

File upload dialog

cua do click 350 400       # "Choose File"
cua do type "/home/user/report.pdf"
cua do key enter
cua do screenshot

Zoom in for precision clicks (host or small targets)

When clicking small or dense UI elements — especially on the host machine — zoom into the target window first. Coordinates become window-relative and screenshots show only that window, giving you higher effective resolution.

cua do zoom "Google Chrome"   # crop to Chrome window; coords are now window-relative
cua do screenshot              # zoomed view — easier to locate small elements
cua do click 112 44            # precise click on a small tab or button
cua do screenshot              # verify
cua do unzoom                  # restore full-screen coords when done
cua do screenshot              # back to full desktop view

Use zoom any time click accuracy is uncertain. unzoom before switching windows or when you need to see the full desktop again.

Drag and drop

cua do window ls               # list open windows
cua do drag 150 300 650 400    # source → destination
cua do screenshot

Fuzz a form

cua do screenshot
cua do click 400 200
cua do type "<script>alert(1)</script>"
cua do key tab && cua do type "'; DROP TABLE users; --"
cua do key tab && cua do type "AAAAAAAAAAAAAAAAAAAAAAA"
cua do click 400 500
cua do screenshot              # check for errors, crashes, unexpected behavior

Trajectory

Every action is auto-recorded to ~/.cua/trajectories/{machine}/{session}/.

cua trajectory share           # upload and get shareable HTTPS link (always do this at end)
cua trajectory ls              # list sessions
cua trajectory export          # generate HTML report
cua do --no-record click 100 200   # disable recording for a single action

Tell the user: "Here is the trajectory of my session: {url}"

Quick Reference

ActionCommand
Connect to targetcua do switch <provider> [name]
Screenshotcua do screenshot
AI-annotated screencua do snapshot ["instructions"]
Clickcua do click <x> <y> [left|right|middle]
Double-clickcua do dclick <x> <y>
Type textcua do type "text"
Press keycua do key <key>
Hotkeycua do hotkey <combo> (e.g. ctrl+c)
Scrollcua do scroll <direction> [amount]
Dragcua do drag <x1> <y1> <x2> <y2>
Move cursorcua do move <x> <y>
Shell commandcua do shell "command"
Open URL/filecua do open <url|path>
List windowscua do window ls [app]
Focus windowcua do window focus <id>
Zoom to windowcua do zoom "App Name"
Unzoomcua do unzoom
Share trajectorycua trajectory share

Providers

ProviderExample
cloudcua do switch cloud my-vm
cloudv2cua do switch cloudv2 my-vm
dockercua do switch docker my-container
lumecua do switch lume my-vm
lumiercua do switch lumier my-vm
winsandboxcua do switch winsandbox
hostcua do switch host

See references/command-reference.md for full argument syntax.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real application on the host.

中文简介正在准备中。当前显示原文说明。

openinterpreter/interpreter-cua22026年10月16日 更新

查看 openinterpreter 的全部技能

报告此技能的问题