Executing Analysis

This is the execution half of the science superpowers workflow. You load your frozen pre-registration, review it critically for feasibility issues, then run every step exactly as written with validation checkpoints throughout. The key discipline is stopping immediately when results look weird or you're tempted to deviate from the plan, because silent tweaks destroy confirmatory status. It includes built-in verification steps and pauses after each major section to report back. The docs emphasize this is the fallback for platforms without subagents, since fresh eyes catch more protocol violations during review. If you're doing any analysis where you want to distinguish confirmatory findings from exploratory ones, the rigor here is the whole point.

GitHub stars: 202
last updated: Jun 1, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/science-superpowers --skill executing-analysis --agent claude-code

Installs into .claude/skills of the current project.

Files

Executing the Analysis

Overview

Load the pre-registered plan, review it critically, execute all steps exactly as registered, report when complete.

Announce at start: "I'm using the executing-analysis skill to run this analysis."

Note: Tell your human partner that Science Superpowers works much better with access to subagents — the protocol-compliance and rigor reviews catch more when run by fresh agents. If subagents are available, use science-superpowers:subagent-driven-analysis instead.

Prerequisite

The plan MUST be pre-registered and frozen (science-superpowers:preregistering-analysis) and the workspace set up (science-superpowers:setting-up-reproducible-analysis). If either is missing, stop and do it first. Executing before freezing turns the analysis exploratory.