Writing Science Skills

If you're building skills for Claude, this is your lab notebook discipline. It enforces the scientific method: observe baseline failures first, document exact rationalizations agents use to skip steps, then write guidance that closes those specific loopholes. The core insight is that writing skills without watching agents fail is like analyzing data you peeked at. You get plausible‑sounding guidance shaped by your assumptions rather than evidence. Includes pressure testing protocols for discipline skills, the "use when" description format that actually helps agents find relevant skills, and a rationalization table approach for bulletproofing. Opinionated about frontmatter structure, cross‑referencing syntax, and when flowcharts hurt more than they help.

GitHub stars: 202
last updated: Jun 1, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Writing Science Skills

Overview

Writing a skill is an experiment, not an essay. You form a hypothesis (this guidance will change agent behavior), run a baseline (watch agents fail without it), write the skill, and test that behavior changes.

Core principle: If you didn't watch an agent fail without the skill, you don't know whether the skill teaches the right thing — the same reason you pre-register before analyzing rather than rationalizing a result after.

REQUIRED BACKGROUND: Understand science-superpowers:preregistering-analysis first. The discipline of fixing a prediction before observing the outcome is exactly the discipline here: observe baseline behavior before writing the skill, so the skill is shaped by evidence, not by what you imagine agents do.