Desktop Find Element

SkillWeb & browsing

Lets your agent locate desktop UI elements like buttons and icons and get their on-screen positions.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Desktop Find Element skill

About this skill

Find desktop UI elements using UIAutomation (fast, accurate) or vision recognition (fallback). When you need to locate buttons/menus/icons, get element positions before clicking, or verify UI state. For browser webpage elements, use browser_* tools instead.

What this skill tells your AI

The instructions your AI receives, as published by openakita/openakita in skills/system/desktop-find-element/SKILL.md and read by ahel’s review.

查找桌面 UI 元素。优先使用 UIAutomation(快速准确),失败时用视觉识别(通用)。

Parameters

参数类型必填说明
targetstring是元素描述,如 '保存按钮'、'name:文件'、'id:btn_ok'
window_titlestring否限定在某个窗口内查找
methodstring否查找方法:auto(默认)、uia、vision

Supported Target Formats

  • 自然语言:"保存按钮"、"红色图标"
  • 按名称:"name:保存"
  • 按 ID:"id:btn_save"
  • 按类型:"type:Button"

Find Methods

  • auto: 自动选择(推荐)
  • uia: 只用 UIAutomation
  • vision: 只用视觉识别

Returns

  • 元素位置(x, y)
  • 元素大小
  • 元素属性

Warning

如果操作的是浏览器内的网页元素,请使用 browser_* 工具。

Related Skills

  • desktop-click: 点击找到的元素
  • desktop-inspect: 查看元素树结构

Signals

GitHub stars
2k
Forks
280
Last commit
Sep 2026
Advanced
Item type
skill
Key
desktop-find-element
Source
github.com/openakita/openakita