
When you have a frozen, pre-registered analysis plan with independent steps, this skill runs them one by one using fresh subagents per step, each with isolated context to prevent improvisation. After each step completes, it dispatches two reviewers in sequence: first a protocol compliance check to ensure nothing beyond the pre-registration was run, then a statistical rigor review for correctness and reproducibility. The continuous execution loop only pauses for blockers or genuine ambiguities. This is rigorous to the point of being almost bureaucratic, but that's the design. If your analysis isn't pre-registered yet or your harness doesn't support subagents, you'll need different skills first.
$ npx -y skills add k-dense-ai/science-superpowers --skill subagent-driven-analysis --agent claude-codeInstalls into .claude/skills of the current project.
Execute a pre-registered analysis plan by dispatching a fresh subagent per analysis step, with two-stage review after each: protocol-compliance review first (did it run exactly what was pre-registered, nothing more), then statistical-rigor review (assumptions, leakage, correctness, reproducibility).
Why subagents: You delegate steps to specialized agents with isolated context. By precisely crafting their instructions, you keep them focused and prevent them from improvising analyses you didn't pre-register. They never inherit your session's history — you construct exactly what they need. This also preserves your own context for coordination.
Core principle: Fresh subagent per step + two-stage review (protocol then rigor) = trustworthy, reproducible results.
Continuous execution: Do not pause to check in between steps. Execute the whole plan. The only reasons to stop: a BLOCKED status you cannot resolve, an anomaly that needs science-superpowers:investigating-anomalous-results, a genuine ambiguity, or all steps complete.
Sponsors