Reporting And Archiving Findings

When your analysis is done, this walks you through closing the loop: verify it reproduces from scratch, then choose whether to merge locally, write it up for sharing, keep the branch, or discard. It detects whether you're in a worktree or detached HEAD and adjusts the menu accordingly. The discipline here is requiring reproducibility before you report anything, and forcing you to separate confirmatory results from exploratory ones in whatever you write. It also handles the cleanup choreography so you don't orphan worktrees or delete branches that haven't been merged yet. Opinionated about scientific rigor but the mechanics work for any analysis you want to archive properly.

GitHub stars: 202
last updated: Jun 1, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/science-superpowers --skill reporting-and-archiving-findings --agent claude-code

Installs into .claude/skills of the current project.

Files

Reporting and Archiving Findings

Overview

Complete an investigation by confirming reproducibility, presenting clear options, handling the chosen one, and archiving everything needed to reproduce the result.

Core principle: Confirm reproducibility -> separate confirmatory from exploratory -> present options -> execute choice -> archive code + data + environment + pre-registration.

Announce at start: "I'm using the reporting-and-archiving-findings skill to complete this work."

Step 1: Verify Reproducibility

Before reporting anything, confirm the whole analysis reproduces from immutable raw data with the fixed seed in the pinned environment.

# From a clean state: re-run the pipeline end to end
# Confirm headline numbers match what you intend to report

Use science-superpowers:verifying-results-before-claiming. If it doesn't reproduce, stop — fix reproducibility (possibly via science-superpowers:investigating-anomalous-results) before reporting. Don't report a number you can't regenerate.

For any confirmatory claim, also run the pre-registration audit and keep its output for the report:

SKILL.md on GitHub