About this skill
Adversarial, axis-separated code review. Runs three isolated passes — Standards (code smells + structure/logic/types/perf), Spec (does it match the issue/PRD), and Adversarial (security + failure-mode red-team) — and never merges or re-ranks their findings. Auto-detects the review target: a PR, a commit, a fixed-point ref diff, pending changes, or a single-pass codebase scan. Refuses to claim anything passes without verification evidence. Triggers on: 'review this', 'code review', 'review the PR', 'review my changes', 'review the diff', 'is this safe to merge', 'aif code review'.
Quick start
- Copy the install prompt. Use the green button above this README.
- Send it to your agent. Paste it into your coding agent’s chat and send.
- Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review, license & listing details
This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.
Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.
0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1
Content SHA-256: 5fb779b8af23210ca61795b76a8b1c49420aed24272b3714f5af640b05825620
About this listing
- Category
- Engineering
- Reported license
- MIT
- Listing language (estimated)
- English
- Review status
- Not individually reviewed
- Agent compatibility
- Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.