wave-parallelism

Execute independent tasks in parallel waves with dependency analysis and file ownership.

Updated Mar 25, 2026
One-click install
npx skills add https://github.com/tuanldas/superteam --skill wave-parallelism
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: wave-parallelism
Source: https://github.com/tuanldas/superteam/tree/main/skills/wave-parallelism
Command: npx skills add https://github.com/tuanldas/superteam --skill wave-parallelism

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Wave-parallelism provides a methodology for safely executing independent tasks in parallel using subagent waves. Tasks are grouped into waves based on dependency analysis — all tasks in a wave can run simultaneously, waves execute sequentially.

Two responsibilities:

  1. Safety — dependency analysis, file-ownership, git contention handling ensure parallel agents don't conflict.
  2. Orchestration — wave assignment, completion verification, inter-wave validation ensure correct execution order and results.

Core Features & Use Cases

  • Dependency analysis outlines needs, creates, files_modified for each task to build the dependency graph.
  • File ownership safety ensures one file is owned by a single agent per wave to prevent merge conflicts.
  • Wave scheduling & verification sequences waves and validates completion before proceeding.
  • Use Case: Run multiple feature studies in parallel to explore different paths, then orchestrate safe merges.

Quick Start

To begin, define tasks with clear dependencies and let the orchestrator dispatch waves in the current project context.

Frequently Asked Questions about wave-parallelism

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I safely parallelize tasks to avoid merge conflicts when modifying files?

Wave-based parallelism groups independent tasks into simultaneous execution waves while enforcing strict file ownership and dependency analysis to prevent git contention and merge conflicts.

What is wave-based execution for task coordination?

Wave-based execution is a task coordination method where independent tasks run simultaneously within a wave, while waves execute sequentially after verifying the previous wave's completion.

How do I set up dependency analysis for parallel task scheduling?

Define each task with its needs, creations, and files modified to build a dependency graph, which the orchestrator then uses to assign tasks to safe parallel waves.

Can I run parallel feature studies and merge the results safely?

Yes, you can run multiple feature studies in parallel to explore different paths, and the wave orchestrator ensures safe merges by validating completion and handling inter-wave dependencies.

When should I not use wave parallelism for task execution?

Wave parallelism is not suitable for tasks that share file ownership within the same wave or have unresolvable circular dependencies, as the orchestrator requires strict file ownership and sequential wave validation.