review
Review before merge. Stage-1 spec-compliance gate, then risk-selected Stage-2 review axes from the canonical set. analyst always runs, callers can pin extra always-on axes, and explicit deep review runs the full 16-axis set. Run after /test. Do NOT invoke code-qualities-assessment, doc-accuracy, golden-principles, or taste-lints directly for a full review; review can select them when requested or when deep review is explicit.
- License
- MIT
Pinned to revision 6e62f3d0a901, so it is the text this page describes rather than whatever the author pushed since.
Pre-approved tools experimental
Experimental field. Support varies between clients, so this list is what the author declared, not what your client will enforce.
- Task
- Skill
- Read
- Glob
- Grep
- Bash(*)
Files
- skills/review/SKILL.md
- skills/review/references/agent-safety.md
- skills/review/references/analyst.md
- skills/review/references/architect.md
- skills/review/references/code-quality.md
- skills/review/references/decision-rigor.md
- skills/review/references/devops.md
- skills/review/references/observability.md
- skills/review/references/qa.md
- skills/review/references/reliability.md
- skills/review/references/roadmap.md
- skills/review/references/security.md
- skills/review/references/spec-compliance.md
- skills/review/resources/axis-selection.md
- skills/review/resources/marker-and-no-task.md
- skills/review/resources/technical-review.md
- skills/review/resources/writing-style.md
- skills/review/scripts/select_axes.py
- skills/review/scripts/validate_findings_scope.py
- skills/review/scripts/validate_review_marker.py
Every link opens the file at its source, pinned to the revision this page describes.