// Full Android audit orchestration. Builds audit-context.json, dispatches specialist agents against that shared evidence, then applies canonical gate and cap logic. Triggers on: "audit", "full android check", "analyze my android project", "project health check".
Android project audit and preflight skill. Builds a shared audit_context.json from static project evidence, then uses specialist agents to interpret that evidence with explicit confidence and deterministic gate caps. Supports Kotlin/Compose and XML/Java repos, including library-only projects. Triggers on: "android audit", "android assessment", "android review", "android project health".
Accessibility preflight for Android projects. Uses static source evidence to flag likely issues in semantics, labels, and touch-target setup while clearly separating low-confidence heuristics from verified findings.
Build system and dependency hygiene review for Android projects. Focuses on module-aware Gradle evidence, KAPT/KSP migration risk, release shrink config, repository hygiene, and dependency verification. Triggers on: "build system", "gradle", "dependencies", "version catalog", "KAPT", "KSP".
Android 15/16 compatibility preflight. Evaluates target SDK posture, edge-to-edge signals, predictive back migration risk, large-screen behavior, and 16 KB page-size readiness with explicit version awareness. Triggers on: "compatibility", "android 16", "edge-to-edge", "predictive back", "large screen".
Design system implementation audit for Android projects. Evaluates Material 3 adoption, theme structure, dynamic color, adaptive layout hooks, and token usage from source evidence. Triggers on: "design review", "material design", "dynamic color", "UI review".
Android performance preflight. Focuses on static build and source signals such as benchmark modules, baseline-profile setup, shrink config, and Compose recomposition hints. It does not claim runtime startup or ANR scores without external artifacts.
| name | android-audit |
| description | Full Android audit orchestration. Builds audit-context.json, dispatches specialist agents against that shared evidence, then applies canonical gate and cap logic. Triggers on: "audit", "full android check", "analyze my android project", "project health check". |
| user-invokable | true |
| argument-hint | [path] |
scripts/build_audit_context.py and write generated/audit-context.jsonscripts/score.py to apply deterministic gates and capsANDROID-AUDIT-REPORT.mdANDROID-ACTION-PLAN.mdexternal evidence required.