scientific-method

Spawned after an investigation reaches resolved-verified status — analyzes the iteration log to produce a mermaid investigation timeline, result analysis (what worked, what did not, pattern observations), and a retrospective with lessons learned and rubric update recommendations. Use when an investigation is complete and the user wants structured analysis and visualization.

Use when debugging software, investigating incidents, diagnosing flaky tests, or analyzing performance regressions — enforces structured observation recording with evidence IDs, causality validation, and verification gates to prevent correlation-causation pollution. Use when an agent might otherwise summarize or speculate instead of reporting observed evidence.

Design and run controlled experiments using the experiment-registry MCP server — domain-agnostic, pluggable, mechanically enforced. Use when you need evidence that a change actually improves behaviour.

Use when facing unknowns, debugging without a clear cause, or making architecture decisions — enforces hypothesis-driven scientific reasoning through observation, hypothesis formulation, prediction, experiment design, and evidence-based conclusion. Use when previous attempts have failed or the problem space involves uncertainty.

1 hook across 1 event