"Use when implementation is done and you need a structured pre-PR review workflow. Triggers: 'ready for review', 'review my changes before PR', 'pre-merge check', 'is this ready', 'submit for review'. Orchestrates multi-phase review (planning, context assembly, dispatch, triage, fix, gate). Dispatches code-review internally. NOT the same as finishing-a-development-branch (which handles merge/PR decisions after review passes)."
Resources
1Install
npx skillscat add axiomantic/spellbook/requesting-code-review Install via the SkillsCat registry.
Requesting Code Review
Self-review orchestrator. Coordinates pre-PR code review workflow. Your reputation depends on every Critical finding being fixed before merge — a missed Critical is a production defect you signed off on. Before starting review workflow, analyze: 1. What is the scope of changes? (files, lines, complexity) 2. Is there a plan/spec document to review against? 3. What is the current git state? (branch, merge base) 4. What phase should we resume from if this is a re-review?Invariant Principles
- Phase gates are blocking - Never proceed to next phase without meeting exit criteria
- Evidence over opinion - Every finding must cite specific code location and behavior
- Critical findings are non-negotiable - No Critical finding may be deferred or ignored
- SHA persistence - Always use reviewed_sha from manifest, never current HEAD
- Traceable artifacts - Each phase produces artifacts for resume and audit capability
Phase-Gated Workflow
Reference: patterns/code-review-formats.md for output schemas.
Phases 1-2: Planning + Context
Determine git range, list changed files, identify plan/spec, estimate complexity. Assemble reviewer context bundle: plan excerpts, related code, prior findings.
Execute: /request-review-plan
Outputs: Review scope definition, reviewer context bundle
Self-Check: Git range defined, file list confirmed, context bundle ready for dispatch.
Phases 3-6: Dispatch + Triage + Execute + Gate
Invoke code-reviewer agent, triage findings by severity, fix in Critical-first order, apply quality gate for proceed/block decision.
Execute: /request-review-execute
Outputs: Review findings, triage report, fix report, gate decision
Self-Check: Valid findings received, triaged, blocking findings addressed, clear verdict.
Artifact Contract
Directory structure, phase artifact table, manifest schema, and SHA persistence rule.
Reference: /request-review-artifacts
Gate Rules
Reference: patterns/code-review-taxonomy.md for severity definitions.
Blocking Rules
| Condition | Result |
|---|---|
| Any Critical unfixed | BLOCKED - must fix before proceed |
| Any High unfixed without rationale | BLOCKED - fix or document deferral |
| >=3 High unfixed | BLOCKED - systemic issues |
| Only Medium/Low/Nit unfixed | MAY PROCEED |
Deferral rationale must be written justification citing the specific constraint (risk acceptance, blocked dependency, or explicit product decision) — "will fix later" does not qualify.
Always use `reviewed_sha` from manifest for inline comments. Never query current HEAD - commits may have been pushed since review started. Every gate in this workflow exists because defects discovered post-merge cost 10x more to fix. Do not skip phases. Do not defer Criticals. Do not let SHA drift corrupt inline comments. A review that lets one Critical through is worse than no review at all. </FINAL_EMPHASIS>