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.
npx -y skills add k-dense-ai/science-superpowers --skill writing-science-skills --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
supercent-io/skills-template
supercent-io/skills-template
huangjia2019/claude-code-engineering
remotion-dev/remotion
reactjs/react.dev