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: Builds a tight, deterministic, agent-runnable repro command using failing tests, curl scripts, CLI fixtures, headless browsers, trace replay, fuzz loops, or bisection harnesses. - Structured Hypothesis Testing: Generates 3-5 ranked, falsifiable hypotheses and maps each instrumentation probe to a specific prediction, changing one variable at a time. - Regression Test & Cleanup Discipline: Writes the regression test before the fix at a correct seam, tags debug logs with unique prefixes for grep-based removal, and ends with a post-mortem. - Use Case: A user reports an intermittent export failure in production. The Skill guides building a replay harness from a captured request, minimizing the failing scenario, testing ranked hypotheses with tagged logs, and landing a fix with a regression test. ## Quick Start Ask the agent to diagnose the bug where the export endpoint intermittently returns a 500 error, and have it build a reproducible feedback loop before proposing any fix.
