agentleFS
gronxbgronxb/codex-relay/.agents/skills/agent-device/SKILL.md

agent-device

Skill733 starsChanged 2 months agoApache-2.0View on GitHub

Automates interactions for Apple-platform apps (iOS, tvOS, macOS) and Android devices. Use when navigating apps, taking snapshots/screenshots, tapping, typing, scrolling, extracting UI info, or collecting logs, network inspection, and perf snapshots across mobile, TV, and desktop targets.

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

30 rules. 0 are common, 11 are distinctive, and 19 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 11

    Distinctive

    This author's own choices. Worth a look.

  • 19

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start conservative. Prefer read-only inspection before mutating the UI.

    line 12
  2. Distinctive:

    Start deterministic. If the app name, package, device, or session is uncertain, load bootstrap and discover them before interacting.

    line 13
  3. Very specific:

    Use plain snapshot when the task is to verify what text or structure is currently visible on screen.

    line 14
  4. Very specific:

    Use snapshot -i only when you need interactive refs such as @e3 for a requested action or targeted query.

    line 15
  5. Very specific:

    Prefer diff snapshot after a nearby mutation when you only need to know what changed.

    line 16
  6. Distinctive:

    Avoid speculative mutations.

    line 17
  7. Distinctive:

    Do not browse the web or use external sources unless the user explicitly asks.

    line 20
  8. Very specific:

    Treat refs in default snapshot output as actionable-now, not durable identities.

    line 22
  9. Very specific:

    Prefer @ref or selector targeting over raw coordinates.

    line 23
  10. Distinctive:

    Ensure the correct target is pinned and an app session is open before interacting.

    line 24
  11. Very specific:

    Keep the loop short: open -> inspect/act -> verify if needed -> close.

    line 25
  12. Distinctive:

    Use bootstrap first to confirm or establish the correct target, app install, and open app session.

    line 30
  13. Very specific:

    Start with plain snapshot if the goal is to read or verify what is visible.

    line 32
  14. Very specific:

    Use get, is, or find before mutating the UI when a read-only command can answer the question.

    line 34
  15. Distinctive:

    Use bootstrap to confirm or establish deterministic setup, especially in sandbox or cloud environments.

    line 45
  16. Distinctive:

    Use exploration once the app session is open and stable.

    line 46
  17. Very specific:

    Use plain snapshot when you need to verify whether text is visible.

    line 51
  18. Very specific:

    Use snapshot -i mainly for interactive exploration and choosing refs.

    line 52
  19. Very specific:

    Use diff snapshot for compact post-action verification.

    line 53
  20. Very specific:

    Use get, is, or find when they can answer the question without changing UI state.

    line 54
  21. Very specific:

    Use fill to replace text.

    line 55
  22. Very specific:

    Use type to append text.

    line 56
  23. Very specific:

    Do not write type @eN "text".

    line 57
  24. Very specific:

    If the on-screen keyboard blocks the next step, prefer keyboard dismiss over navigation.

    line 58
  25. Very specific:

    When a task asks to "go back", use plain back for predictable app-owned navigation and reserve back --system for platform back gestures or …

    line 59
  26. Very specific:

    Use type --delay-ms or fill --delay-ms for debounced search fields that drop characters when typed too quickly.

    line 60
  27. Very specific:

    If there is no simulator, no app install, or no open app session yet, switch to bootstrap-install.md instead of improvising setup steps.

    line 61
  28. Distinctive:

    Use the smallest unblock action first when transient UI blocks inspection, but do not navigate, search, or enter new text just to make the …

    line 62
  29. Distinctive:

    Do not use external lookups to compensate for missing on-screen data unless the user asked for them.

    line 65
  30. Distinctive:

    If the needed information is not exposed on screen, say that plainly instead of compensating with extra navigation, text entry, or web …

    line 66

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

agent-device

Use this skill as a router with mandatory defaults. Read this file first. For normal device tasks, always load references/bootstrap-install.md and references/exploration.md before acting. Use bootstrap to confirm or establish deterministic setup. Use exploration for UI inspection, interaction, and verification once the app session is open.

Default operating rules

  • Start conservative. Prefer read-only inspection before mutating the UI.
  • Start deterministic. If the app name, package, device, or session is uncertain, load bootstrap and discover them before interacting.
  • Use plain snapshot when the task is to verify what text or structure is currently visible on screen.
  • Use snapshot -i only when you need interactive refs such as @e3 for a requested action or targeted query. On iOS and Android, default snapshot output uses the same visible-first model: off-screen interactive content is exposed as discovery hints, not tappable refs.
  • Prefer diff snapshot after a nearby mutation when you only need to know what changed.
  • Avoid speculative mutations. You may take the smallest reversible UI action needed to unblock inspection or complete the requested task, such as dismissing a popup, closing an alert, or clearing an unintended surface.
  • In React Native dev or debug builds, check early for visible warning or error overlays, tooltips, and toasts that can steal focus or intercept taps. If they are not part of the requested behavior, dismiss them and continue. If you saw them, report them in the final summary.
  • In Metro-backed React Native dev loops, use agent-device metro reload for a JS app reload before falling back to open <app> --relaunch. It mirrors pressing r in the Metro terminal and preserves the native app process.
  • Do not browse the web or use external sources unless the user explicitly asks.
  • Re-snapshot after meaningful UI changes instead of reusing stale refs.
  • Treat refs in default snapshot output as actionable-now, not durable identities. If a target appears only in an off-screen summary, use scroll <direction> and re-snapshot until the target is visible.
  • Prefer @ref or selector targeting over raw coordinates.
  • Ensure the correct target is pinned and an app session is open before interacting.
  • Keep the loop short: open -> inspect/act -> verify if needed -> close.

Default flow

  1. Load references/bootstrap-install.md and references/exploration.md before acting on a normal device task.
  2. Use bootstrap first to confirm or establish the correct target, app install, and open app session.
  3. Once the app session is open and stable, use exploration for inspection, interaction, and verification.
  4. Start with plain snapshot if the goal is to read or verify what is visible.
  5. Escalate to snapshot -i only if you need refs for interactive exploration or a requested action.
  6. Use get, is, or find before mutating the UI when a read-only command can answer the question.
  7. End by capturing proof if needed, then close.

QA modes

  • Open-ended bug hunt with reporting: use ../dogfood/SKILL.md.
  • Pass/fail QA from acceptance criteria: stay in this skill, start with references/bootstrap-install.md, then use the QA loop in references/exploration.md.

Required references

  • For every normal device task, after reading this file, load references/bootstrap-install.md first, then references/exploration.md, before acting.
  • Use bootstrap to confirm or establish deterministic setup, especially in sandbox or cloud environments.
  • Use exploration once the app session is open and stable.
  • Load additional references only when their scope is needed.

Decision rules

  • Use plain snapshot when you need to verify whether text is visible.
  • Use snapshot -i mainly for interactive exploration and choosing refs.
  • Use diff snapshot for compact post-action verification; use snapshot --diff when that alias is easier to discover from snapshot help.
  • Use get, is, or find when they can answer the question without changing UI state.
  • Use fill to replace text.
  • Use type to append text.
  • Do not write type @eN "text". Use fill @eN "text" to target a field directly, or press @eN then type "text" when the field already has focus and you want append semantics.
  • If the on-screen keyboard blocks the next step, prefer keyboard dismiss over navigation. On iOS, keep an app session open first; keyboard status|get remains Android-only.
  • When a task asks to "go back", use plain back for predictable app-owned navigation and reserve back --system for platform back gestures or button semantics.
  • Use type --delay-ms or fill --delay-ms for debounced search fields that drop characters when typed too quickly.
  • If there is no simulator, no app install, or no open app session yet, switch to bootstrap-install.md instead of improvising setup steps.
  • Use the smallest unblock action first when transient UI blocks inspection, but do not navigate, search, or enter new text just to make the UI reveal data unless the user asked for that interaction.
  • In React Native dev or debug apps, treat visible warning or error overlays as transient blockers unless the user is explicitly asking you to diagnose them. Dismiss them when safe, then continue the requested flow.
  • For React Native code changes where the app is already connected to Metro, prefer agent-device metro reload, then wait and re-snapshot. Use open <app> --relaunch only when Metro reload does not reconnect or native startup state must reset.
  • Do not use external lookups to compensate for missing on-screen data unless the user asked for them.
  • If the needed information is not exposed on screen, say that plainly instead of compensating with extra navigation, text entry, or web search.
  • Prefer @ref or selector targeting over raw coordinates.

Additional references

  • Need logs, network, alerts, permissions, or failure triage: references/debugging.md
  • Need screenshots, diff, recording, replay maintenance, or perf data: references/verification.md
  • Need desktop surfaces, menu bar behavior, or macOS-specific interaction rules: references/macos-desktop.md
  • Need remote HTTP transport, connect --remote-config, or tenant leases on a remote macOS host: references/remote-tenancy.md This includes remote React Native runs where agent-device now prepares Metro locally and manages the local Metro companion tunnel automatically.
  • Need the React Native component tree, props, state, hooks, or render profiling: use agent-device react-devtools ... and the react-devtools skill.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.