Ab Iterative Refinement

Runs review-fix-review cycles on a change until quality converges: a deslop pass, then per iteration an ab-review-swarm review, findings routed by tier, fixes through ab-resolve-in-parallel, tests, build and a commit, until the convergence mode is met (fast: no P1, deep: no P1 or P2, perfect: none) or max_iterations (default 3) runs out. Use when ab-ship-pipeline or ab-build-pipeline reaches review, or when the user wants code polished past a single review pass. Not for a trivial change (one ab-review-swarm pass) or findings that need an architecture change (re-plan).

Ninety2UA Updated

File contents

Ninety2UA/agent-blueprint commit 237afc05ee Runs: ninety2ua/ab-review-swarm

Frequently asked questions

npx get-skill add ninety2ua/ab-iterative-refinement