baranbingol1

Autonomous experiment loop for optimization research.

Apply when wiring validation, error handling, or framework adapters.

Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.

Diagnosis loop for bugs and performance regressions.

Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction.

Blind-test how a skill or prompt change affects agent behavior before promoting it.

Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check…

Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors…

Apply during long-running work — implementation runs, orchestration, wiki generation, verification sweeps — when context is filling up…

Implement a piece of work from a spec, bd ticket, or direct request.

Apply when reviewing or shaping code that's hard to trace.

Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files.