The Agent Skills Directory

[SAFE]: The skill provides detailed instructions for Flutter UI performance engineering, adhering to industry best practices and official framework documentation.
[SAFE]: All external references point to official Flutter and Dart documentation domains (e.g., flutter.dev, dart.dev), which are trusted and well-known technical resources.
[SAFE]: The use of command-line tools such as flutter, dart, and rg is strictly aligned with the skill's stated purpose of performance analysis and optimization within a development environment.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted project data (source code and configuration files). However, the instructions are technically constrained and do not expose high-risk capabilities to potential injection vectors.
Ingestion points: Reads local project files (pubspec.yaml, pubspec.lock, Dart source files) and its own reference documentation.
Boundary markers: Not explicitly defined for external code, but the analysis scope is strictly limited to performance metrics.
Capability inventory: Uses standard development tools (flutter run, flutter build, rg) for profiling and analysis.
Sanitization: Not explicitly implemented, but the skill's focus on structured performance data minimizes exploitation risks.

flutter-ui-performance-engineering