Dispatching Parallel Investigations

When you have multiple independent investigations that don't share state, this runs them in parallel rather than sequentially. Think literature surveys across different subtopics, replicating the same analysis on separate datasets, or pre-specified robustness checks. The key constraint is intellectual honesty: it's built for cases where you'll report all results, not for fishing through 20 specifications to cherry-pick the one that works. Each agent gets a focused scope and exact instructions, runs its investigation independently, then you synthesize and verify everything. The documentation is unusually direct about the p-hacking risk, which is refreshing. Works well when parallelism actually saves time and you were going to run all the analyses anyway.

GitHub stars: 202
last updated: Jun 1, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/science-superpowers --skill dispatching-parallel-investigations --agent claude-code

Installs into .claude/skills of the current project.

Files

Dispatching Parallel Investigations

Overview

You delegate investigations to specialized agents with isolated context. By precisely crafting their instructions, you keep each focused and preserve your own context for synthesis. They never inherit your session history — you construct exactly what each needs.

When you have multiple independent investigations (different datasets, different sub-topics in a literature survey, different pre-specified robustness checks), running them sequentially wastes time. Each is independent and can run in parallel.

Core principle: One agent per independent investigation. Let them run concurrently, then synthesize.

The Pre-Registration Guard (read first)

Parallelism multiplies researcher degrees of freedom. If you dispatch 20 specifications and report the one that "works," you have p-hacked at scale — parallelism made it faster, not more honest.

SKILL.md on GitHub