agent-desktop
- Repo stars 3,082
- Author updated Live
- Author repo grok-cli
- Domain
- AI
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @superagent-ai · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- macOS
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Shell exec
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: agent-desktop
description: Use the built-in `Computer` sub-agent with `agent-desktop` for macOS desktop automation. Apply w…
category: ai
runtime: no special runtime
---
# agent-desktop output preview
## PART A: Task fit
- Use case: 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..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “When to use it / Requirements / Preferred flow” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “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.”.
- **02** When the source has headings, the agent prioritizes “When to use it / Requirements / Preferred flow” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, run shell commands, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, run shell commands, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, run shell commands, write/modify files.
Validate with a small run
Start with a small task and check whether the result follows “When to use it / Requirements / Preferred flow”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: agent-desktop
description: Use the built-in `Computer` sub-agent with `agent-desktop` for macOS desktop automation. Apply w…
category: ai
source: superagent-ai/grok-cli
---
# agent-desktop
## When to use
- Use the built-in `Computer` sub-agent with `agent-desktop` for macOS desktop automation. Apply when a task needs appli…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “When to use it / Requirements / Preferred flow” and keep inference separate from source facts.
- read files, run shell commands, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "agent-desktop" {
input -> user goal + target files + boundaries + acceptance criteria
context -> When to use it / Requirements / Preferred flow
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, run shell commands, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}agent-desktop
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.
When to use it
- The user wants to inspect or interact with a native macOS application.
- The task needs app launch, window focus, accessibility snapshots, semantic element refs, clicks, typing, keypresses, or scrolling.
- A browser-only workflow is not enough, or the target is not a web page.
Requirements
agent-desktopmust be installed and its native binary available.- On macOS, the terminal app running
grokneeds Accessibility permission. - Refs from
computer_snapshotare only valid until the next snapshot.
Preferred flow
- Delegate to
taskwithagent: "computer"unless the current agent already has thecomputer_*tools and the task is tiny. - Use
computer_launch,computer_list_windows, orcomputer_focus_windowto get the target app/window ready. - Start with
computer_snapshot. - Pick one ref-based action.
- After any UI transition, snapshot again before reusing refs.
Tool guidance
computer_snapshot: primary observation tool; preferinteractive_only.computer_click: userefvalues 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 asEnter,Tab,cmd+space, orcmd+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.
Reliability rules
- Use a snapshot -> act -> snapshot loop.
- Prefer refs over coordinates.
- Refs go stale after the next snapshot; do not reuse them blindly.
- Keep actions reversible and low risk unless the user explicitly asked for something destructive.
- If the accessibility tree is poor or ambiguous, use
computer_screenshotfor confirmation and explain the limitation.
Blockers
Stop and report clearly if:
- Accessibility permission is missing.
agent-desktopis unavailable or its native binary is missing.- The target app/window cannot be found.
- Refs are stale or ambiguous after a UI transition.
- The requested action could be destructive and the user did not explicitly ask for it.
Decide Fit First
Computersub-agent withagent-desktopfor macOS desktop automation. Apply when a task needs application lau…Design Intent
How To Use It
Boundaries And Review