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.

Install to Claude Code

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