What problem does it solve? When multiple unrelated test failures or bugs appear across different files and subsystems, investigating them sequentially wastes time. This Skill provides a structured pattern for delegating each independent problem domain to a focused subagent so investigations run in parallel without shared state or context pollution. ## Core Features & Use Cases - Independence Decision Framework: A decision flowchart and criteria to determine whether failures are independent enough for parallel dispatch or require sequential investigation. - Agent Prompt Structure: Guidance for writing focused, self-contained agent prompts with specific scope, constraints, and expected output format. - Parallel Dispatch Pattern: Instructions for issuing multiple subagent dispatches in a single response so they execute concurrently, plus review and integration steps after agents return. - Use Case: After a major refactoring leaves 6 test failures across 3 files (abort logic, batch completion, race conditions), dispatch one agent per file, then verify the fixes don't conflict and run the full suite. ## Quick Start Ask the AI to dispatch one parallel subagent per failing test file, each with a focused prompt containing the failure details and a constraint to not touch other code.
