Stats
Actions
Tags
From visual-app-skills
Run a Flutter app on a connected Android device or emulator, capture real screenshots via adb, read the Dart + logcat logs, 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 Android", "see the visual changes", "verify a UI fix", "check if my change works/renders", or otherwise wants empirical on-device confirmation that a Flutter change rendered correctly — even when they don't say "screenshot" or "logs". Handles launching with the right entry point and flags, waiting for the first real frame, navigating with adb input, capturing the screen, reading flutter + logcat output, and reporting a concrete verdict with evidence. Optionally diffs against a Figma reference when one is provided. Android only (iOS needs a Mac).
How this skill is triggered — by the user, by Claude, or both
Slash command
/visual-app-skills:flutter-test-android-visuallyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Interactive, on-device verification of a Flutter Android app — the "did my last
Interactive, on-device verification of a Flutter Android app — the "did my last
change actually render correctly" check you'd otherwise do by squinting at an
emulator. Builds and runs the app on a device or emulator, captures real
screenshots via adb, reads the logs, and gives you enough evidence to answer
did the change render correctly.
Works for any Flutter app, including multi-entry apps where the default
entry point throws by design and a --target flag is mandatory. Android only —
iOS needs a Mac and xcrun simctl, which is out of scope here.
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.flutter run command and flags,
the first-frame log signal, where Flutter logs, hot reload, and cold-build
timing — read references/flutter.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/run commands with device disambiguation.
capture-loop.md shows how they fit together.
npx claudepluginhub lukas-hinterleitner/visual-app-skills --plugin visual-app-skillsProvides 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.