New advertisers: 50% off your first month with code FIRSTMONTHSee slots

Inline execution of a pre-registered analysis plan with review checkpoints, for sessions without subagents.

GitHub stars
202
last updated
Jun 1, 2026
View on GitHub

What it does

  • Covers loading and critically reviewing a frozen pre-registration, then running each analysis step exactly as registered
  • Includes per-step validation on simulated data, output shape and range checks, and checkpoints that separate confirmatory from exploratory results
  • Enforces a hard stop on surprising results, plan deviations, and repeated validation failures, routing them to root-cause investigation
  • Designed for analysts on platforms without subagents; subagent-driven execution is preferred where available

Install

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

Installs into .agents/skills for every agent it finds here, and .claude/skills for Claude Code.

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.

The Process

Step 1: Load and Review

Details

Repository
github.com/k-dense-ai/science-superpowers
Category
Automation & Workflows
First seen
Jun 11, 2026

More from k-dense-ai/science-superpowers

All 15

Similar to Executing Analysis

More Automation & Workflows