Baseline: state the simplest honest solution first. Every option must beat it; the baseline stays a candidate.
Diverge: distinct options across practical, high-leverage, and unusual angles.
Challenge: weak assumptions, failure modes, tradeoffs, rejections. Always: reject speculative generality (each abstraction, layer, flag, and data copy needs a current caller) and verify load-bearing "needed" claims in the consuming code, not doc assertions.
Compare: only relevant criteria, plus deletion cost (how easily the option can be removed later). Ties go to the smaller option.
Converge: strongest 3 picks with rationale and a next step. Self-review first: for each new constant, object, layer, and flag ask "why do we need this?" Cut answers that are only messaging or future-proofing.
Formats
Use Quick by default. Use Deep only for ambiguous or high-stakes decisions. Ask at most one clarifying question only if missing context would materially change the brainstorm; otherwise state assumptions and proceed.
Avoid filler, near-duplicates, generic best practices, premature recommendations, and scope without a current caller. If asked for more ideas, explore a new axis before listing variants.
AI DevKit · Publish a ready feature branch for review. Use when the user wants to sync, push, and open or update a code review request on GitHub, GitLab, or another Git host.