Surveying Prior Work

This is the "read the existing codebase before you write new code" step for research. Use it after you've framed a question but before you design the analysis. It walks you through grounding four things: what methods are standard for this question, what confounds are already known, what effect sizes others have found (so you can power your study), and whether your work is actually novel or just a rediscovery. The workflow dispatches parallel subagents for broad surveys to keep context clean, then synthesizes findings into a short note with sources cited. Honest take: skipping this is how you reinvent methods badly or report known artifacts as discoveries. The red flags section is blunt about common mistakes, which is refreshing.

GitHub stars: 202
last updated: Jun 1, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/science-superpowers --skill surveying-prior-work --agent claude-code

Installs into .claude/skills of the current project.

Files

Surveying Prior Work

Overview

Before designing an analysis, ground the question and your chosen methods in what is already known. Most questions have established methods, known confounds, and prior effect sizes. Reinventing a method badly — or rediscovering a known artifact and reporting it as a finding — wastes effort and erodes credibility.

Core principle: Find out what is already known before you generate new claims.

This is the science analog of reading the existing codebase before writing new code. It is a flexible skill — adapt depth to the stakes of the investigation.

When to Use

After framing-research-questions, before designing-the-analysis
When selecting a statistical method or model and unsure what is standard
When a result looks novel — check whether it is a known effect or artifact first
When you need a plausible prior effect size to power the study
When you suspect confounds but don't know which are established in the field