Agent-skills agent-device
Automates interactions for Apple-platform apps (iOS, tvOS, macOS) and Android devices. Use when navigating apps, taking snapshots/screenshots, tapping, typing, scrolling, or extracting UI info across mobile, TV, and desktop targets.
install
source · Clone the upstream repo
git clone https://github.com/callstackincubator/agent-skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/callstackincubator/agent-skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/plugins/vendored/.agents/skills/agent-device" ~/.claude/skills/callstackincubator-agent-skills-agent-device && rm -rf "$T"
manifest:
plugins/vendored/.agents/skills/agent-device/SKILL.mdsource content
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.
- Use plain
when the task is to verify what text or structure is currently visible on screen.snapshot - Use
only when you need interactive refs such assnapshot -i
for a requested action or targeted query.@e3 - 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.
- 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.
- Prefer
or selector targeting over raw coordinates.@ref - Ensure the correct target is pinned and an app session is open before interacting.
- Keep the loop short:
-> inspect/act -> verify if needed ->open
.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
if the goal is to read or verify what is visible.snapshot - Escalate to
only if you need refs for interactive exploration or a requested action.snapshot -i - Use
,get
, oris
before mutating the UI when a read-only command can answer the question.find - 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
when you need to verify whether text is visible.snapshot - Use
mainly for interactive exploration and choosing refs.snapshot -i - Use
,get
, oris
when they can answer the question without changing UI state.find - Use
to replace text.fill - Use
to append text.type - When a task asks to "go back", use plain
for predictable app-owned navigation and reserveback
for platform back gestures or button semantics.back --system - Use
ortype --delay-ms
for debounced search fields that drop characters when typed too quickly.fill --delay-ms - If there is no simulator, no app install, or no open app session yet, switch to
instead of improvising setup steps.bootstrap-install.md - 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.
- 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
or selector targeting over raw coordinates.@ref
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,
launches, or tenant leases on a remote macOS host: references/remote-tenancy.md--remote-config