14 tagged desktop automation, measured the same way as everything else here.
Browse within: accessibility 8computer-use 8browser-automation 7cross-platform 5linux 5macos 5
Command
A command that produces a report measuring Computer Use capabilities, such as task completion and tool activity. Computer Use means controlling applications through an interactive computer interface.
Command
A command that diagnoses the Computer Use plugin, its environment, and its mapped capabilities. Computer Use lets an agent interact with a computer through supported actions.
Command
A command that starts a planned, isolated Windows computer-use task. It follows prepared steps, checks the computer setup, uses screenshots when needed, and reports what was actually verified.
Command Claude Code
Run the complete ClawBridge release process. This is the ONLY way to deploy — follow every step.
Command Claude Code
Run this before /deploy to catch security issues. Three-step process: scan, triage, report.
Command Claude Code
Automate a desktop workflow described by the user.
Command Claude Code
Inspect and debug the UI structure of an app.
Command Claude Code
Take a screenshot of the current screen and describe what you see.
Command Claude Code
End-to-end feature/bug-sweep workflow for ui-debugger-mcp — understand, reproduce against a real target, explore in parallel, split into path-disjoint slices, build with a hive of agents in this ONE checkout (never worktrees), gate green, PR, merge, release to npm. Tracks in GitHub issues. Reads intent from the prompt.
Command Claude Code
Write a concise, self-contained execution plan to docs/plans/ / / / - / for another AI to implement.
Command
Record a demo video of an app — the agent clicks through it by itself, the screen is recorded, and the output is a finished video with zoom to clicks and voiceover.
Command
Check the machine and install everything the screencast-desktop plugin needs (Python packages, ffmpeg, screen capture, voice).