skills/review-remediation/SKILL.md
Fix local review (Codex, Zen, notes) w/ verify. Not gh-pr-review-fix or passive PR monitoring.
npx skillsauth add bjornmelin/dev-skills review-remediationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill to normalize review inputs, turn them into an actionable checklist, and then fix the valid findings with repo-native verification.
local-review: ingest a local review note filecodex-review: ingest local Codex review outputzen-review: ingest local Zen review outputAGENTS.md.codex-dev --json review ingest --source <file> --kind codex|zen|manual --out <json>codex-dev --json review render --worklist <json>codex-dev --json pr readiness plus GitHub status checks.references/local-review.mdreferences/verification.mddevelopment
Pre-PR multi-model review, parallel opus and codex exec adversarial lanes, then adversarial verification of merged findings. Read-only. Use before shipping nontrivial diffs.
tools
Independent gpt-5.6 diff review via the Codex CLI, normal or steerable adversarial with JSON findings. Use before shipping nontrivial changes.
development
Delegate implementation, investigation, or bulk work to gpt-5.6 codex via pinned codex exec. Use for clear-spec builds, migrations, debugging, or any task MODELS.md routes to codex.
development
Adversarial pre-mortem: imagine the plan failed, work backwards to surface risky assumptions + irreversible bets, then harden them. Proactively offer it (after the current request; confirm first) before a hard-to-reverse or one-way-door call (API, schema, framework, a hire), an all-upside plan, or unvalidated assumptions. Also on request.