agent-device
Automate native mobile apps with agent-device: simulator setup, selectors, screenshots and scenario execution.
- License 许可
- MIT
- 所属仓库
- 1aGh/maude
- 最近更新
- 2026-11-13
- Stars
- ★ 3
- Forks
- 0
01 前言 Front Matter
- name
- agent-device
- hidden
- true
- description
- Automate native mobile apps with agent-device: simulator setup, selectors, screenshots and scenario execution.
- allowed-tools
- Bash(agent-device:*), Bash(npx agent-device:*), Bash(xcrun simctl:*)
02 资源文件 12
- 参考文档_guide-00-overview.md698 B
- 参考文档_guide-01-first-time-setup-new-machine.md2.7 KB
- 参考文档_guide-02-day-to-day-rules.md9.7 KB
- 参考文档_guide-03-the-core-loop.md769 B
- 参考文档_guide-04-auth-state-already-persistent.md1.2 KB
- 参考文档_guide-05-recipes.md4.5 KB
- 参考文档_guide-06-token-efficiency-cheat-sheet.md1.2 KB
- 参考文档_guide-07-snapshot-reading-guide.md877 B
- 参考文档_guide-08-selectors.md580 B
- 参考文档_guide-09-troubleshooting.md1.1 KB
- 参考文档_guide-10-when-not-to-use-agent-device.md454 B
- 参考文档_guide-11-reference.md453 B
03 SKILL.md 正文
agent-device
Follow host conventions for Claude Code or Codex.
Use the project device/bundle configuration, stable selectors and compact snapshots. Keep per-device sessions and artifacts isolated. Use screenshot evidence and the documented platform workaround when needed; classify unavailable infrastructure separately from product failures. Read setup only on an unconfigured machine and platform-specific recipes only for that target.
Read only the relevant procedure
The references below retain the complete procedure. Read the entry for the stage before performing it; conditional examples, setup and troubleshooting load only when needed. A staged workflow follows its applicable stages in order, including verification and close-out. References to another section mean the matching row here, not permission to skip that requirement. Do not read all references at once.
| When | Read |
|---|---|
| Initial orientation, prerequisites and scope | Overview |
| Only for a new or unconfigured machine | First-time setup (new machine) |
| When performing this stage: Day-to-day rules | Day-to-day rules |
| When performing this stage: The core loop | The core loop |
| Before login, session reuse or authentication changes | Auth state — already persistent |
| When the task needs a worked implementation example | Recipes |
| When performing this stage: Token efficiency cheat-sheet | Token efficiency cheat-sheet |
| When performing this stage: Snapshot reading guide | Snapshot reading guide |
| When performing this stage: Selectors | Selectors |
| When diagnosing the corresponding failure | Troubleshooting |
| When performing this stage: When NOT to use agent-device | When NOT to use agent-device |
| When performing this stage: Reference | Reference |
04 同仓库更多 Skills
workflow-state
Read and update workflow state when planning, executing, completing, pausing or resuming project work.
ui-rules
UI hard-stop rules and audit method: WCAG 2.1 AA accessibility, responsive layout and motion.
testing-rules
Apply test quality rules during implementation and review: meaningful assertions, isolation and coverage.
security-rules
Apply application and AI security checks to code reviews, implementation and threat-driven validation.
scenario
Author or run cross-platform UI scenarios with selectors, screenshots, platform coverage and result reports.
question-protocol
Batch necessary questions from workflow participants, collect user answers and route them to the requester.