What problem does it solve? Hard bugs and performance regressions resist casual code reading and single-hypothesis guessing. This Skill enforces a disciplined six-phase diagnosis loop that builds a tight, red-capable feedback signal before any hypothesis is tested, preventing wasted effort on unfalsifiable theories. ## Core Features & Use Cases - Feedback Loop Construction: Builds a deterministic, fast, agent-runnable pass/fail signal using failing tests, curl scripts, headless browser runs, trace replays, fuzz loops, or bisection harnesses. - Structured Hypothesis Testing: Generates 3-5 ranked, falsifiable hypotheses, then instruments with tagged debug logs or debugger breakpoints, changing one variable at a time. - Regression Lockdown: Writes the regression test before the fix at a correct seam, then cleans up all debug instrumentation and throwaway prototypes. - Use Case: A user reports that an export endpoint intermittently returns corrupted data. The Skill guides building a curl-based loop that reproduces the failure at a high rate, minimising the repro, ranking hypotheses, and landing a fix with a regression test. ## Quick Start Ask the agent to diagnose the failing export endpoint by building a reproduction loop and following the phased debugging workflow.
