What problem does it solve?
This Skill addresses the challenge of efficiently managing and executing multiple, interdependent tasks across various projects simultaneously, ensuring optimal resource utilization and faster completion times.
Core Features & Use Cases
- Dependency Graph Execution: Manages tasks defined as nodes in a Directed Acyclic Graph (DAG), dispatching dependency-free nodes immediately.
- Worker Pools: Utilizes specialized worker pools (planning, coding, validation, research) for independent task execution.
- Concurrency Controls: Implements global limits, per-project quotas, and per-task-type quotas to prevent resource starvation and ensure fair scheduling.
- Prioritization & Preemption: Supports priority classes and preemption policies for critical tasks.
- Failure Handling: Includes bounded retries, partial-failure management, and a fast-fail toggle.
- Observability: Provides detailed dashboard counters and an event stream for real-time monitoring.
- Subagent-First Policy: Defaults to parallel
codex exec subagents for implementation work, with specific guidelines for manual edits and subagent wave execution.
Quick Start
Execute the defined workflow using the parallel-execution skill, prioritizing critical tasks and managing concurrency quotas.