dispatching-parallel-agents

What problem does it solve? Investigating multiple unrelated failures sequentially wastes time and pollutes your working context. This Skill coordinates one subagent per independent problem domain so concurrent investigations run in parallel while your own context stays free for integration work. ## Core Features & Use Cases - Independence Decision Logic: A decision flowchart and explicit criteria determine when failures are independent enough for parallel dispatch versus sequential handling. - Focused Agent Prompt Structure: Guidance for writing self-contained agent prompts with specific scope, constraints, and expected output summaries. - Parallel Dispatch Pattern: Instructions to issue multiple subagent dispatches in a single response so they execute concurrently, followed by review and integration steps. - Use Case: After a refactoring leaves 6 test failures across 3 files (abort logic, batch completion, race conditions), dispatch three agents simultaneously—one per test file—then verify the fixes do not conflict and run the full suite. ## Quick Start Dispatch one subagent per failing test file in parallel, giving each a focused prompt with the failing test names, constraints, and a request for a summary of root cause and fixes.