What problem does it solve? Hard bugs and performance regressions resist casual code reading; without a tight, reproducible pass/fail signal, debugging devolves into guessing. This Skill enforces a disciplined diagnosis loop that builds a red-capable feedback command first, then reproduces, minimizes, hypothesizes, instruments, fixes, and cleans up. ## Core Features & Use Cases - Feedback Loop Construction: Ten ranked strategies for building a tight pass/fail signal, from failing tests and curl scripts to headless browser runs, trace replay, fuzz loops, bisection harnesses, and differential comparisons. - Structured Six-Phase Workflow: Reproduce and minimize, generate 3-5 ranked falsifiable hypotheses, instrument with tagged debug logs, write regression tests at correct seams, and finish with cleanup and a post-mortem. - Non-Deterministic Bug Handling: Raise reproduction rates via repetition, parallelism, stress, and timing injection until flaky bugs become debuggable. - Use Case: A user reports an intermittent export failure in a web app. The Skill guides building a Playwright loop that reproduces the error, minimizing the scenario, testing ranked hypotheses one variable at a time, and landing a fix with a regression test. ## Quick Start Ask the agent to diagnose the bug where the export button throws an error, and have it build a reproducible failing test before proposing any fix.
