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
- callstack/agent-devicetheir own version, first seen Nov 5, 2026
- callstackincubator/react-native-bottom-tabstheir own version, first seen Oct 9, 2026
- callstack/react-native-bottom-tabstheir own version, first seen Oct 9, 2026
- gronxb/hot-updatertheir own version, first seen Oct 8, 2026
- callstackincubator/agent-devicetheir own version, first seen Oct 8, 2026
- CherryHQ/cherry-studio-apptheir own version, first seen Oct 8, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- Shopify/flash-list★ 7.2ksame name
- callstackincubator/agent-device★ 5.3ksame name
- callstack/agent-device★ 5.3ksame name
- Expensify/App★ 5.1ksame name
- CherryHQ/cherry-studio-app★ 4.1ksame name
- gronxb/hot-updater★ 1.8ksame name
- callstack/react-native-bottom-tabs★ 1.5ksame name
- callstackincubator/react-native-bottom-tabs★ 1.5ksame name
- Aceproulx/claude-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/vercel-react-best-practices/AGENTS.mdAGENTS.md
- .agents/skills/vercel-react-native-skills/AGENTS.mdAGENTS.md
- agent-cdpSkill
- deploy-iosSkill
- dogfoodSkill
- hot-updater-qa-shipSkill
- hot-updaterSkill
- react-devtoolsSkill
- react-native-best-practicesSkill
- vercel-react-best-practicesSkill
- vercel-react-native-skillsSkill
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
- Distinctive: line 12
Start conservative. Prefer read-only inspection before mutating the UI.
- Distinctive: line 13
Start deterministic. If the app name, package, device, or session is uncertain, load bootstrap and discover them before interacting.
- Very specific: line 14
Use plain snapshot when the task is to verify what text or structure is currently visible on screen.
- Very specific: line 15
Use snapshot -i only when you need interactive refs such as @e3 for a requested action or targeted query.
- Very specific: line 16
Prefer diff snapshot after a nearby mutation when you only need to know what changed.
- Distinctive: line 17
Avoid speculative mutations.
- Distinctive: line 20
Do not browse the web or use external sources unless the user explicitly asks.
- Very specific: line 22
Treat refs in default snapshot output as actionable-now, not durable identities.
- Very specific: line 23
Prefer @ref or selector targeting over raw coordinates.
- Distinctive: line 24
Ensure the correct target is pinned and an app session is open before interacting.
- Very specific: line 25
Keep the loop short: open -> inspect/act -> verify if needed -> close.
- Distinctive: line 30
Use bootstrap first to confirm or establish the correct target, app install, and open app session.
- Very specific: line 32
Start with plain snapshot if the goal is to read or verify what is visible.
- Very specific: line 34
Use get, is, or find before mutating the UI when a read-only command can answer the question.
- Distinctive: line 45
Use bootstrap to confirm or establish deterministic setup, especially in sandbox or cloud environments.
- Distinctive: line 46
Use exploration once the app session is open and stable.
- Very specific: line 51
Use plain snapshot when you need to verify whether text is visible.
- Very specific: line 52
Use snapshot -i mainly for interactive exploration and choosing refs.
- Very specific: line 53
Use diff snapshot for compact post-action verification.
- Very specific: line 54
Use get, is, or find when they can answer the question without changing UI state.
- Very specific: line 55
Use fill to replace text.
- Very specific: line 56
Use type to append text.
- Very specific: line 57
Do not write type @eN "text".
- Very specific: line 58
If the on-screen keyboard blocks the next step, prefer keyboard dismiss over navigation.
- Very specific: line 59
When a task asks to "go back", use plain back for predictable app-owned navigation and reserve back --system for platform back gestures or …
- Very specific: line 60
Use type --delay-ms or fill --delay-ms for debounced search fields that drop characters when typed too quickly.
- Very specific: line 61
If there is no simulator, no app install, or no open app session yet, switch to bootstrap-install.md instead of improvising setup steps.
- Distinctive: line 62
Use the smallest unblock action first when transient UI blocks inspection, but do not navigate, search, or enter new text just to make the …
- Distinctive: line 65
Do not use external lookups to compensate for missing on-screen data unless the user asked for them.
- Distinctive: line 66
If the needed information is not exposed on screen, say that plainly instead of compensating with extra navigation, text entry, or web …
“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.
Files
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
snapshotwhen the task is to verify what text or structure is currently visible on screen. - Use
snapshot -ionly when you need interactive refs such as@e3for 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 snapshotafter 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 reloadfor a JS app reload before falling back toopen <app> --relaunch. It mirrors pressingrin 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
@refor 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
- Load references/bootstrap-install.md and references/exploration.md before acting on a normal device task.
- Use bootstrap first to confirm or establish the correct target, app install, and open app session.
- Once the app session is open and stable, use exploration for inspection, interaction, and verification.
- Start with plain
snapshotif the goal is to read or verify what is visible. - Escalate to
snapshot -ionly if you need refs for interactive exploration or a requested action. - Use
get,is, orfindbefore mutating the UI when a read-only command can answer the question. - 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
snapshotwhen you need to verify whether text is visible. - Use
snapshot -imainly for interactive exploration and choosing refs. - Use
diff snapshotfor compact post-action verification; usesnapshot --diffwhen that alias is easier to discover from snapshot help. - Use
get,is, orfindwhen they can answer the question without changing UI state. - Use
fillto replace text. - Use
typeto append text. - Do not write
type @eN "text". Usefill @eN "text"to target a field directly, orpress @eNthentype "text"when the field already has focus and you want append semantics. - If the on-screen keyboard blocks the next step, prefer
keyboard dismissover navigation. On iOS, keep an app session open first;keyboard status|getremains Android-only. - When a task asks to "go back", use plain
backfor predictable app-owned navigation and reserveback --systemfor platform back gestures or button semantics. - Use
type --delay-msorfill --delay-msfor 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.mdinstead 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. Useopen <app> --relaunchonly 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
@refor 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 whereagent-devicenow 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.
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
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.

