Habilidades receiving-code-review
📦

receiving-code-review

Seguro

Handle code review feedback with technical rigor

También disponible en: obra,Cygnusfear,Cycleaddict,DYAI2025,davila7,ZhanlinCui,CodingCossack

Code review requires technical evaluation, not emotional performance. This skill guides AI assistants to verify feedback before implementing, ask clarifying questions, and provide reasoned pushback when suggestions are technically unsound.

Soporta: Claude Codex Code(CC)
🥉 75 Bronce
1

Descargar el ZIP de la skill

2

Subir en Claude

Ve a Configuración → Capacidades → Skills → Subir skill

3

Activa y empieza a usar

Pruébalo

Usando "receiving-code-review". Reviewer: Remove the legacy code path for old API versions

Resultado esperado:

Checking compatibility requirements... Build target is 10.15+, but this API needs 13+. The legacy path is still needed for backward compatibility. However, the current implementation has the wrong bundle ID. I can fix the bundle ID or we can drop pre-13 support. Which direction do you prefer?

Usando "receiving-code-review". Reviewer: Fix items 1-6 in the PR

Resultado esperado:

I understand items 1, 2, 3, and 6. I need clarification on items 4 and 5 before implementing. Can you elaborate on what changes you're looking for on those two items?

Usando "receiving-code-review". Reviewer: Add proper error handling with retry logic and exponential backoff

Resultado esperado:

Fixed. Added Try/Catch with retry logic (3 attempts, exponential backoff starting at 100ms) to the API call in api_service.rb:42-58. Tests pass.

Auditoría de seguridad

Seguro
v1 • 2/24/2026

Static analysis flagged 24 instances of backtick patterns and 4 blocker patterns, but all are FALSE POSITIVES. The skill file (SKILL.md) is documentation-only markdown containing instructional text for AI behavior. No executable code, network calls, file operations, or cryptographic functions exist. The backtick patterns are markdown code blocks showing workflow examples, not shell execution. Blocker patterns are misidentified text fragments in documentation.

1
Archivos escaneados
219
Líneas analizadas
0
hallazgos
1
Auditorías totales
No se encontraron problemas de seguridad
Auditado por: claude

Puntuación de calidad

38
Arquitectura
100
Mantenibilidad
87
Contenido
50
Comunidad
100
Seguridad
100
Cumplimiento de la especificación

Lo que puedes crear

AI Assistant Receiving Human Review

An AI assistant receives code review feedback from a human developer and needs to determine which items to implement, which need clarification, and which to push back on with technical reasoning.

Junior Developer Learning Review Response

A junior developer learns how to respond to senior developer feedback with technical rigor instead of performative agreement, verifying suggestions before blind implementation.

External Contributor Handling Maintainer Feedback

An external contributor receives feedback from project maintainers and needs to evaluate whether suggestions fit the project architecture before implementing.

Prueba estos prompts

Basic Clarification Request 
I received code review feedback with 6 items. I understand items 1, 2, 3, and 6, but need clarification on items 4 and 5 before proceeding. Can you explain what changes you're looking for on those specific items?
Technical Pushback with Evidence 
Your suggestion to remove the legacy compatibility layer would break support for macOS 10.15. The current implementation targets 10.15+ but uses APIs that need 13+. Should I fix the bundle ID to maintain backward compatibility, or drop pre-13 support entirely?
YAGNI Check Before Implementation 
The reviewer suggested implementing full metrics tracking with database storage, date filters, and CSV export. I searched the codebase and found no callers for this endpoint. Should I remove it following YAGNI, or is there usage I'm missing?
Graceful Correction After Wrong Pushback 
I pushed back on your suggestion, but after checking the test results you were correct. My understanding was wrong because I missed the integration test failure. Implementing the fix now.

Mejores prácticas

  • Always verify feedback against actual codebase before implementing any changes
  • Implement changes one at a time and test each individually to catch regressions early
  • Push back with technical reasoning when suggestions would break existing functionality

Evitar

  • Saying 'You're absolutely right!' or 'Great point!' before verifying the feedback
  • Implementing feedback blindly without checking if it breaks existing functionality
  • Implementing items 1-3 and 6 while skipping unclear items 4-5 without asking first

Preguntas frecuentes

What should I do if code review feedback is unclear?
Stop and ask for clarification before implementing anything. Items may be related, and partial understanding leads to wrong implementation. State clearly which items you understand and which need clarification.
When is it appropriate to push back on reviewer feedback?
Push back when the suggestion breaks existing functionality, the reviewer lacks full context, it violates YAGNI for unused features, it is technically incorrect for your stack, or it conflicts with architectural decisions.
How do I push back without being defensive?
Use technical reasoning, ask specific questions, reference working tests or existing code, and involve your human partner if the issue is architectural. State facts, not emotions.
What if I pushed back and was later wrong?
Acknowledge the correction factually: 'You were right - I checked X and it does Y. Implementing now.' Avoid long apologies or defending why you pushed back initially.
Why should I avoid saying thanks or being performative?
Actions speak louder than words. Just fix the issue and show the change in code. Performative agreement wastes time and can mask actual technical concerns that need addressing.
How do I handle external reviewer feedback differently from my human partner?
Be more skeptical with external reviewers. Check if suggestions are technically correct for your codebase, won't break existing functionality, and that the reviewer understands full context. Push back with reasoning when needed.

Detalles del desarrollador

Autor

sickn33

Licencia

MIT

Repositorio

https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/receiving-code-review

Ref.

main

Estructura de archivos

📄 SKILL.md