Use the built-in `Computer` sub-agent with `agent-desktop` for macOS desktop automation. Apply when a task needs application launching, accessibility snapshots, stable element refs, window focusing, semantic clicks/typing, or visual confirmation outside the browser sandbox.
75
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Use this skill when the task involves the host macOS desktop rather than repository files, shell output, or browser-only verification.
This project uses agent-desktop on the host. Prefer the built-in Computer sub-agent for these tasks instead of trying to drive the desktop with plain shell commands.
agent-desktop must be installed and its native binary available.grok needs Accessibility permission.computer_snapshot are only valid until the next snapshot.task with agent: "computer" unless the current agent already has the computer_* tools and the task is tiny.computer_launch, computer_list_windows, or computer_focus_window to get the target app/window ready.computer_snapshot.computer_snapshot: primary observation tool; prefer interactive_only.computer_click: use ref values from the latest snapshot whenever possible.computer_type: requires a target ref and is preferred over coordinate typing.computer_press: use for shortcuts and special keys such as Enter, Tab, cmd+space, or cmd+k.computer_scroll: pass an element ref, not raw coordinates.computer_get: read text, value, bounds, role, or states from a ref.computer_screenshot: use for visual confirmation or when the accessibility tree is not enough.computer_screenshot for confirmation and explain the limitation.Stop and report clearly if:
agent-desktop is unavailable or its native binary is missing.fb97af8
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.