wtk-deep-review
Deep Review
Review at CodeRabbit grade with bounded, assertive posture: funnel the diff, discover root/nested project instructions and relevant local skills, plan defect cohorts, fan out reviewers, then merge with complete hunk/rule accounting. For small selections, prefer one defect cohort when current limits permit; extra cohorts need an engine limit or a named independent high-risk boundary recorded before dispatch. Defects require causal evidence and control the verdict; advisories require a concrete improvement and always remain visible.
Steps 1–4 drive an idempotent artifact pipeline under <out>: every stage gate is a bundled-script exit 0, valid agent outputs are never re-run, and an interrupted round resumes by re-running the same commands.
<skill-dir> below means the directory containing this SKILL.md; run every bundled command from the repo root.