بنقرة واحدة
code-review-protocol
Use when reviewing or requesting code review. Two-stage protocol with fresh-reviewer enforcement.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Use when reviewing or requesting code review. Two-stage protocol with fresh-reviewer enforcement.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | code-review-protocol |
| description | Use when reviewing or requesting code review. Two-stage protocol with fresh-reviewer enforcement. |
| version | 1.0.0 |
| tags | ["process","review"] |
∀ code reviews (spec compliance ∨ code quality).
Stage 1 (spec compliance) MUST pass before Stage 2 (code quality) runs.
| Stage | Role | Checks | Verdict |
|---|---|---|---|
| 1: Spec | spec reviewer | ∀ criteria implemented? Extra work? Correct interpretation? | PASS ∨ FAIL |
| 2: Quality | code quality reviewer | Correctness, tests (edge cases), patterns, YAGNI, readability | APPROVE ∨ REQUEST_CHANGES |
Before requesting review, verify:
| Level | Meaning | Blocks? |
|---|---|---|
| Critical | Bug, security, data loss | Yes |
| Important | Pattern violation, missing tests, unclear logic | Yes |
| Minor | Style, naming, comment | No |
Core Principle: Only flag issues that cause real problems. Not theoretical concerns, not style preferences.
| Question | If Yes | If No |
|---|---|---|
| Bug ∈ prod? | Critical | Continue |
| Confuses next dev? | Important | Continue |
| ¬noticed ∈ 1000-line diff? | Skip | Continue |
| Blocks merge? | Flag | Skip |
| Just cosmetic? | Skip | Skip |
Anti-Pattern: Nitpicking wastes time and erodes trust. Prefer clear, blocking issues over style commentary.
¬agent reviews code it wrote. Verify reviewer hasn't authored the code under review.
Use when reviewing architecture decisions. C4 model, dependency inversion, hexagonal boundaries.
Use during discuss-slice and plan-slice to stress-test a spec or plan against domain vocabulary before approval.
Use during research-slice to build disposable experiments that answer technical uncertainty.
Use during project:init to scaffold repo-level agent configuration (CLAUDE.md, AGENTS.md, tracker labels).
Use when debugging. 4-phase investigation, root cause, minimal fix.
Use when implementing features/fixes. Iron law: ¬∃ production code without failing test.