dispatching-parallel-agents

What problem does it solve? When multiple unrelated test failures or bugs appear across different files and subsystems, investigating them sequentially wastes time and bloats your working context. This Skill provides a structured pattern for delegating each independent problem to a focused subagent that works in parallel with isolated context. ## Core Features & Use Cases - Independence Assessment: Decision criteria and a flowchart to determine whether failures are independent enough for parallel dispatch or require sequential investigation. - Agent Prompt Structure: A template for writing focused, self-contained agent prompts with specific scope, constraints, and expected output. - Parallel Dispatch Pattern: Guidance on issuing multiple subagent dispatches in a single response so they execute concurrently, plus review and integration steps. - 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 integrate the independent fixes and run the full suite. ## Quick Start Dispatch one subagent per failing test file to investigate and fix each independent failure in parallel, then review their summaries and run the full test suite.