The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads implementation plans from the docs/plans/ directory and executes tasks based on their content.
Ingestion points: The agent reads plan files using cat docs/plans/YYYY-MM-DD-<feature>-plan.md in SKILL.md.
Boundary markers: The skill includes a 'Review critically' step (Step 1.4) and instructs the agent to raise concerns before starting.
Capability inventory: The agent has the ability to create/modify files, execute flutter pub get, flutter analyze, flutter test, flutter build, and perform git commit operations.
Sanitization: No automated sanitization is present; the skill relies on the agent's critical review of the plan content.

flutter-executing