Menu
Use when receiving code review feedback, before implementing suggestions - requires technical rigor and verification, not performative agreement
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | receiving-code-review |
| description | Use when receiving code review feedback, before implementing suggestions - requires technical rigor and verification, not performative agreement |
| applies_to | ["orchestrator","backend","frontend","qa"] |
| mandatory | true |
Triggered By: Prodige Reviewer Agent returning findings
Applies To: All agents (Orchestrator, Backend, Frontend, QA)
Severity Handling: Critical (🚫 blocks merge) | Important (⚠️ blocks next task) | Minor (💡 document)
When Prodige Reviewer Agent returns review findings, use this skill to:
.ai/context/ARCHITECTURE.md and .ai/context/DECISIONS.mdCode review requires technical evaluation, not emotional performance.
Core principle: Verify before implementing. Ask before assuming. Technical correctness over social comfort.
WHEN receiving code review feedback:
1. READ: Complete feedback without reacting
2. UNDERSTAND: Restate requirement in own words (or ask)
3. VERIFY: Check against codebase reality
4. EVALUATE: Technically sound for THIS codebase?
5. RESPOND: Technical acknowledgment or reasoned pushback
6. IMPLEMENT: One item at a time, test each
NEVER:
INSTEAD:
Critical Issues (🚫):
Important Issues (⚠️):
Minor Issues (💡):
technical-debt.mdExample Response:
## Review Findings: Task 3
**Critical:** SQL injection in login endpoint
- Stopping work immediately
- Fixing with parameterized queries
- Will request re-review after fix
**Important:** Missing error handling in payment flow
- Noted for fixing before Task 4
- Task 3 marked as conditionally complete
**Minor:** Magic number (5000) for timeout
- Recorded in technical-debt.md
- Will extract to constant when refactoring timeout logic
IF any item is unclear:
STOP - do not implement anything yet
ASK for clarification on unclear items
WHY: Items may be related. Partial understanding = wrong implementation.
Example:
your human partner: "Fix 1-6"
You understand 1,2,3,6. Unclear on 4,5.
❌ WRONG: Implement 1,2,3,6 now, ask about 4,5 later
✅ RIGHT: "I understand items 1,2,3,6. Need clarification on 4 and 5 before proceeding."
BEFORE implementing:
1. Check: Technically correct for THIS codebase?
2. Check: Breaks existing functionality?
3. Check: Reason for current implementation?
4. Check: Works on all platforms/versions?
5. Check: Does reviewer understand full context?
IF suggestion seems wrong:
Push back with technical reasoning
IF can't easily verify:
Say so: "I can't verify this without [X]. Should I [investigate/ask/proceed]?"
IF conflicts with your human partner's prior decisions:
Stop and discuss with your human partner first
your human partner's rule: "External feedback - be skeptical, but check carefully"
Before implementing reviewer suggestions, check:
.ai/context/ARCHITECTURE.md
.ai/context/DECISIONS.md
.ai/context/PRD.md
Example:
Reviewer: "Use microservices for user service"
Check ARCHITECTURE.md:
→ Line 45: "Monolith-first approach, extract services only when scaling requires"
Check DECISIONS.md:
→ Decision #12 (2026-05-10): "Start with monolith, defer microservices"
Response:
"This conflicts with architectural Decision #12 (monolith-first).
Keeping current implementation unless user wants to revise that decision."
IF reviewer suggests "implementing properly":
grep codebase for actual usage
IF unused: "This endpoint isn't called. Remove it (YAGNI)?"
IF used: Then implement properly
your human partner's rule: "You and reviewer both report to me. If we don't need this feature, don't add it."
FOR multi-item feedback:
1. Clarify anything unclear FIRST
2. Then implement in this order:
- Blocking issues (breaks, security)
- Simple fixes (typos, imports)
- Complex fixes (refactoring, logic)
3. Test each fix individually
4. Verify no regressions
Push back when:
How to push back:
If you're uncomfortable pushing back out loud: Name that tension, then tell your partner about the issue you've seen. They'll appreciate your honesty.
When feedback IS correct:
✅ "Fixed. [Brief description of what changed]"
✅ "Good catch - [specific issue]. Fixed in [location]."
✅ [Just fix it and show in the code]
❌ "You're absolutely right!"
❌ "Great point!"
❌ "Thanks for catching that!"
❌ "Thanks for [anything]"
❌ ANY gratitude expression
Why no thanks: Actions speak. Just fix it. The code itself shows you heard the feedback.
If you catch yourself about to write "Thanks": DELETE IT. State the fix instead.
If you pushed back and were wrong:
✅ "You were right - I checked [X] and it does [Y]. Implementing now."
✅ "Verified this and you're correct. My initial understanding was wrong because [reason]. Fixing."
❌ Long apology
❌ Defending why you pushed back
❌ Over-explaining
State the correction factually and move on.
| Mistake | Fix |
|---|---|
| Performative agreement | State requirement or just act |
| Blind implementation | Verify against codebase first |
| Batch without testing | One at a time, test each |
| Assuming reviewer is right | Check if breaks things |
| Avoiding pushback | Technical correctness > comfort |
| Partial implementation | Clarify all items first |
| Can't verify, proceed anyway | State limitation, ask for direction |
Performative Agreement (Bad):
Reviewer: "Remove legacy code"
❌ "You're absolutely right! Let me remove that..."
Technical Verification (Good):
Reviewer: "Remove legacy code"
✅ "Checking... build target is 10.15+, this API needs 13+. Need legacy for backward compat. Current impl has wrong bundle ID - fix it or drop pre-13 support?"
YAGNI (Good):
Reviewer: "Implement proper metrics tracking with database, date filters, CSV export"
✅ "Grepped codebase - nothing calls this endpoint. Remove it (YAGNI)? Or is there usage I'm missing?"
Unclear Item (Good):
your human partner: "Fix items 1-6"
You understand 1,2,3,6. Unclear on 4,5.
✅ "Understand 1,2,3,6. Need clarification on 4 and 5 before implementing."
When replying to inline review comments on GitHub, reply in the comment thread (gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies), not as a top-level PR comment.
Used With:
Workflow:
Orchestrator:
Request review (requesting-code-review)
↓
Reviewer returns findings
↓
Apply this skill (receiving-code-review)
↓
If Critical/Important: Dispatch fix agent
↓
Re-review cycle
External feedback = suggestions to evaluate, not orders to follow.
Verify. Question. Then implement.
No performative agreement. Technical rigor always.
Communicate efficiently without sacrificing clarity - natural, concise, actionable. Global skill loaded for every command and agent.
Use when reviewing or building UI components - ensures keyboard, screen-reader, and visual accessibility (WCAG 2.1 AA) so a11y is built in, not retrofitted.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Manages context caching to optimize token usage and cost by creating, incrementally updating, and invalidating caches while verifying integrity before reuse.
Clean code and engineering discipline: modularity, readability, sizing, naming, duplication, separation of concerns, plus the four behavioral principles - think before coding, simplicity first, surgical changes, and goal-driven execution. Global skill applied to all coding work.
Detects and resolves drift between code, documentation, and contextual knowledge, classifying each drift and recommending concrete sync actions to keep artifacts consistent.