Stats
Actions
Tags
From visual-app-skills
Build, install, and run a native Android app (Kotlin or Java, Jetpack Compose or Views, Gradle) on a connected device or emulator, capture real screenshots via adb, read logcat, and verify the visible UI and runtime behavior match what a recent code change intended. Use whenever the user asks to "test the app", "run it on the emulator", "see the visual changes", "verify a UI fix", "check if my change works/renders", or otherwise wants empirical on-device confirmation that a native Android change rendered correctly — even when they don't say "screenshot" or "logs". Handles the Gradle install task (and build variants/flavors), launching the activity, waiting for the first frame, navigating with adb input, capturing the screen, reading logcat scoped to the app, and reporting a concrete verdict with evidence. Optionally diffs against a Figma reference when one is provided.
How this skill is triggered — by the user, by Claude, or both
Slash command
/visual-app-skills:native-android-test-visuallyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Interactive, on-device verification of a native Android app (Kotlin/Java,
Interactive, on-device verification of a native Android app (Kotlin/Java,
Jetpack Compose or classic Views) — the "did my last change actually render
correctly" check. Installs the app via Gradle, launches the activity, captures
real screenshots via adb, reads logcat, and gives a concrete verdict.
references/capture-loop.md — the universal procedure: preflight,
launch in the background, wait for the first real frame, screenshot, capture
logs, analyze the PNG against the change, report a verdict.installDebug task and how
to pick a build variant/flavor, launching the activity with am start /
monkey, finding the applicationId, the "activity displayed" signal, and
logcat scoped to the app's pid — read references/native-android.md.references/driving-the-ui.md.references/troubleshooting.md.references/figma-comparison.md
(requires the Figma MCP server; skip entirely if you don't use Figma).references/other-frameworks.md or use the matching skill.scripts/check-devices.sh, launch.sh, snap.sh, capture-logs.sh,
stop.sh wrap the common adb/Gradle commands with device disambiguation.
capture-loop.md shows how they fit together. Note that a native Gradle install
does not launch the app — see the framework reference for the am start step.
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub lukas-hinterleitner/visual-app-skills --plugin visual-app-skills