agentleFS
mdiri-aimdiri-ai/SoduWork/skills/computer-use/SKILL.md

computer-use

Skill930 starsChanged 6 days agoMITView on GitHub

Use when a Windows desktop application has no reliable CLI or web entry point, or when a real mouse, keyboard, window, or screen must be verified end to end.

69 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use competitor-news-monitor, claude-buddy and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • aivrarSkill

    competitor-news-monitor

    Watch named companies for material news; cited digests.

    Also in 6 projects that use this

  • autonomous-aiSkill

    claude-buddy

    Coordinate with the Claude Buddy companion (Claude Desktop + Claude Code on the user's Mac) — voice-approve tool permission prompts and stay aware of Claude activity.

    Also in 3 projects that use this

  • autonomous-aiSkill

    face-enroll

    Manage the device's face recognition roster — enroll new faces (3 paths: user-supplied photo, agent-captured snapshot on user request, or HAL's familiar-stranger prompt) and maintain the enrolled set (status / remove / reset). All enrolled persons are friends; strangers stay unnamed until promoted via one of the enroll flows.

    Also in 3 projects that use this

  • +9 more from autonomous-ai

The file

Files
SKILL.md

Computer Use

通过 PowerShell + .NET 操作本机 Windows 桌面。脚本使用真实鼠标消息、高分屏坐标和可取消的桌面控制租约;输入失败会返回非零退出码,不能把失败当成成功。

安全护栏

  1. 先看再动:点击、输入或快捷键前先 shot,确认前台窗口、目标和物理坐标;动作后再截图留证。
  2. 只在当前请求明确授权时填写凭据;不把凭据写入文件、日志或截图。不要操作系统设置、安全软件、防火墙、注册表、管理员弹窗、支付、删除、卸载或不可逆确认框。
  3. 先 windows 检查前台窗口;无关窗口先 focus。用户按 Esc 或提示层取消后立即停止,不绕过租约、不自动重试这一轮。
  4. 坐标必须来自最新截图;脚本拒绝桌面范围外的鼠标坐标、越界截图、超过 64 MP 的截图、过长文本和未声明的批量动作。

快速参考

$s = '<技能目录>/scripts/screen.ps1'
powershell -File $s shot before.png
powershell -File $s windows
powershell -File $s focus '窗口标题片段'
powershell -File $s click 640 480
powershell -File $s type '要输入的文字'
powershell -File $s key '^s'
'[{"cmd":"click","x":640,"y":480},{"cmd":"wait","ms":300},{"cmd":"key","keys":"^s"}]' |
  powershell -File $s batch stdin

批量动作最多 50 步,仅允许 wait(0–5000 ms)、move、click、dblclick、rclick、type(最多 4000 字符)和 key(最多 64 字符)。批量执行只初始化一次桌面租约,适合连续操作,仍会在每步前检查取消状态。

SoduWork 控制层

保留运行时注入的 SODUWORK_DESKTOP_CONTROL_ENDPOINT 和轮次标识。首次输入会等待真实的提示层就绪;截图和窗口查询不启动提示层。独立 Runner 没有本机提示层,不能假设存在彩虹边框或鼠标光环。

交付与验证

关键操作要保留操作前后截图,并说明观察到的窗口、坐标和结果。发生超时、取消、前台窗口变化或脚本非零退出时,停止并报告原因;不要用另一套输入工具绕过本技能。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.