resolve-review-findings

Takes the findings an already-completed review, lint run, or audit has just produced and works them down to a verified clean pass. Reads every finding into a prioritized todo ledger, applies the smallest fix that genuinely resolves each entry, re-runs the identical check that surfaced the findings, and absorbs anything newly reported until a run comes back empty. Use when the user asks to fix, clear, resolve, or address the findings of a review that has already run and whose output is visible in the conversation. Not for performing the first review itself, for open-ended refactoring with no findings list, or for ruling findings spurious without the user deciding.

Version

v1.0.0

Size

12 KB

Updated

2026-10-11

Your client verifies the signature before reading. This explicit manual read is available on every plan. Free automatically loads five chosen skills; paid plans automatically load relevant skills across the library.