agent-desktop
Use the built-in `Computer` sub-agent with `agent-desktop` for macOS desktop automation.
Skill by Solizardking
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/solizardking-agent-desktop
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-desktop
What's inside
- Skill name
agent-desktop- Description
- 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.
- License
- MIT
- Instructions
- 55 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- metadata.json
- verification.json
SKILL.md (first lines)
# 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-desktop` must be installed and its native binary available. - On macOS, the terminal app running `grok` needs Accessibility permission. - Refs from `computer_snapshot` are only valid until the next snapshot. ## Preferred flow 1. Delegate to `task` with `agent: "computer"` unless the current agent already has the `computer_*` tools and the task is tiny. 2. Use `computer_launch`, `computer_list_windows`, or `computer_focus_window` to get the target app/window ready. 3. Start with `computer_snapshot`. 4. Pick one ref-based action. 5. After any UI transition, snapshot again before reusing refs. ## Tool guidance - `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. ## 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_screenshot` for confirmation and explain the limitation. ## Blockers Stop and report clearly if: - Accessibility permission is missing. - `agent-desktop` is 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.
From Solizardking/skillhub-main, MIT.
More from Solizardking/skillhub-main
- 0.516score
agentic-wallet
Solizardking
Crypto wallet operations via the awal CLI — sign in, check balances, send USDC/ETH/POL/SOL, trade tokens, fund the wallet, and use the x402 payment protocol…
SkillBFreshness: BClaude Code +9 - 0.500score
huashu-design
Solizardking
花叔Design——用HTML做高保真原型、幻灯片、动画、可视化与专家评审。任何新设计100%先出三个方向初稿给用户选(指定风格/品牌也不豁免),选定后才执行。触发词:做原型、PPT、幻灯片、动画、设计风格、评审、做个HTML页面、UI mockup、导出MP4/GIF、做个好看的。生产级Web…
SkillBFreshness: BClaude Code +9 - 0.466score
migrate-radix-to-base
Solizardking
Migrates React projects and components from Radix UI to Base UI.
SkillCFreshness: CClaude Code +9 - 0.463score
agent-browser
Solizardking
Use the host-side `agent-browser` CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs.
SkillCFreshness: CClaude Code +9 - 0.437score
agent-orchestration-handoff
Solizardking
Compact the current conversation into a single, detailed handoff message — everything that happened, why it happened, and what's left — output in a code block…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 10, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Solizardking/skillhub-main
- Website
- skills.x402.wtf
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from Solizardking
- 0.516score
agentic-wallet
Solizardking
Crypto wallet operations via the awal CLI — sign in, check balances, send USDC/ETH/POL/SOL, trade tokens, fund the wallet, and use the x402 payment protocol…
SkillBFreshness: BClaude Code +9 - 0.500score
huashu-design
Solizardking
花叔Design——用HTML做高保真原型、幻灯片、动画、可视化与专家评审。任何新设计100%先出三个方向初稿给用户选(指定风格/品牌也不豁免),选定后才执行。触发词:做原型、PPT、幻灯片、动画、设计风格、评审、做个HTML页面、UI mockup、导出MP4/GIF、做个好看的。生产级Web…
SkillBFreshness: BClaude Code +9 - 0.485score
brand-guidelines
Solizardking
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel.
SkillBFreshness: BClaude Code +9 - 0.485score
canvas-design
Solizardking
Create beautiful visual art in .png and .pdf documents using design philosophy.
SkillBFreshness: BClaude Code +9 - 0.485score
doc-coauthoring
Solizardking
Guide users through a structured workflow for co-authoring documentation.
SkillBFreshness: BClaude Code +9 - 0.481score
algorithmic-art
Solizardking
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration.
SkillBFreshness: BClaude Code +9
Cite this page
agent-desktop skill. Agent Mart. https://agentmart.dev/skills/solizardking-agent-desktop (last updated 2026-10-24)