Back to Workflow & Productivity
receiving-code-review
code reviewfeedbacksoftware developmenttechnical communicationworkflowdeveloper toolscoding assistantai agent
Install this skill
npx skills add obra/superpowersWorks across Claude Code, Cursor, Codex, Copilot & Antigravity
The receiving-code-review skill defines a strict, technical framework for processing feedback on a codebase. It prioritizes objective validation over social pleasantries, mandating that the agent verify every suggestion against the existing codebase before execution. The process prohibits performative language such as gratitude or agreement, replacing it with factual confirmation or reasoned technical pushback. By enforcing a systematic approach—read, restate, verify, evaluate, and act—the agent ensures changes maintain architectural integrity. It emphasizes the YAGNI principle, requiring the agent to grep for actual usage before implementing features suggested by reviewers. This methodology treats code review as a data-validation task rather than a conversational one, maintaining focus on technical correctness and preventing the implementation of unnecessary or breaking changes.
When to Use This Skill
- •Processing pull request comments from external contributors
- •Integrating feedback from a lead developer during architectural reviews
- •Refining implementation logic after a failed automated test suite
- •Filtering out redundant feature requests during maintenance cycles
How to Invoke This Skill
Example prompts that trigger this skill in Claude Code, Cursor, or Antigravity:
- “Review these comments and apply changes
- “Implement the requested fixes from the code review
- “Address the feedback provided in the PR
- “Evaluate and resolve the code review points
- “Here is the feedback; please update the code accordingly
Pro Tips
- 💡Always restate the reviewer's suggestion in your own words to confirm understanding before proceeding.
- 💡Don't hesitate to ask clarifying questions; incomplete information leads to incorrect implementations.
- 💡When pushing back, always provide concrete technical reasoning or link to relevant code sections/documentation.
- 💡Implement and test each verified suggestion individually to isolate potential regressions.
What this skill does
- •Validates suggestions against current codebase logic
- •Performs YAGNI analysis via grep on proposed feature additions
- •Structures implementation sequences by priority: blocking, simple, then complex
- •Executes methodical individual testing for each modification
- •Constructs evidence-based technical pushback for incorrect feedback
When not to use it
- ✕When human-to-human social rapport is required for team bonding
- ✕During creative brainstorming sessions where technical verification is premature
- ✕When handling feedback that is purely administrative or non-technical
Example workflow
- Read all incoming feedback without immediate reaction
- Restate requirements to confirm understanding of all points
- Grep the codebase to verify the necessity or impact of each point
- Clarify any ambiguous instructions with the reviewer before acting
- Implement fixes one by one, verifying each individually
- Provide a factual summary of completed changes without using emotive language
Prerequisites
- –Active codebase access
- –PR or feedback comment thread
Pitfalls & limitations
- !Accidentally using performative phrases like 'thanks' or 'great point'
- !Implementing partially understood requirements leading to regressions
- !Neglecting to push back when a reviewer suggestion violates project scope
FAQ
Why is saying 'thank you' forbidden?
The goal is to focus entirely on technical precision. Gratitude is considered non-functional noise that obscures the actual status of the work.
What do I do if I am not sure if a suggestion is correct?
Stop immediately. Verify the code, and if you cannot determine the technical validity, ask the reviewer for clarification before touching the codebase.
Should I implement all requested changes in one go?
No. Implement each item individually and test the code after every single change to ensure no regressions are introduced.
How should I handle a suggestion that breaks existing code?
Document the conflict with technical evidence and push back. State specifically why the change is problematic for the current architecture.
How it compares
Unlike manual code adjustment which is prone to emotional bias or blind compliance, this skill applies a rigid, evidence-based filter that prioritizes codebase stability and YAGNI adherence.
📄 Full skill instructions — original source: obra/superpowers
# Code Review Reception
## Overview
Code review requires technical evaluation, not emotional performance.
**Core principle:** Verify before implementing. Ask before assuming. Technical correctness over social comfort.
## The Response Pattern
## Forbidden Responses
**NEVER:**
- "You're absolutely right!" (explicit CLAUDE.md violation)
- "Great point!" / "Excellent feedback!" (performative)
- "Let me implement that now" (before verification)
**INSTEAD:**
- Restate the technical requirement
- Ask clarifying questions
- Push back with technical reasoning if wrong
- Just start working (actions > words)
## Handling Unclear Feedback
**Example:**
## Source-Specific Handling
### From your human partner
- **Trusted** - implement after understanding
- **Still ask** if scope unclear
- **No performative agreement**
- **Skip to action** or technical acknowledgment
### From External Reviewers
**your human partner's rule:** "External feedback - be skeptical, but check carefully"
## YAGNI Check for "Professional" Features
**your human partner's rule:** "You and reviewer both report to me. If we don't need this feature, don't add it."
## Implementation Order
## When To Push Back
Push back when:
- Suggestion breaks existing functionality
- Reviewer lacks full context
- Violates YAGNI (unused feature)
- Technically incorrect for this stack
- Legacy/compatibility reasons exist
- Conflicts with your human partner's architectural decisions
**How to push back:**
- Use technical reasoning, not defensiveness
- Ask specific questions
- Reference working tests/code
- Involve your human partner if architectural
**Signal if uncomfortable pushing back out loud:** "Strange things are afoot at the Circle K"
## Acknowledging Correct Feedback
When feedback IS correct:
**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.
## Gracefully Correcting Your Pushback
If you pushed back and were wrong:
State the correction factually and move on.
## Common Mistakes
| 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 |
## Real Examples
**Performative Agreement (Bad):**
**Technical Verification (Good):**
**YAGNI (Good):**
**Unclear Item (Good):**
## GitHub Thread Replies
When replying to inline review comments on GitHub, reply in the comment thread (
## The Bottom Line
**External feedback = suggestions to evaluate, not orders to follow.**
Verify. Question. Then implement.
No performative agreement. Technical rigor always.
## Overview
Code review requires technical evaluation, not emotional performance.
**Core principle:** Verify before implementing. Ask before assuming. Technical correctness over social comfort.
## The Response Pattern
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## Forbidden Responses
**NEVER:**
- "You're absolutely right!" (explicit CLAUDE.md violation)
- "Great point!" / "Excellent feedback!" (performative)
- "Let me implement that now" (before verification)
**INSTEAD:**
- Restate the technical requirement
- Ask clarifying questions
- Push back with technical reasoning if wrong
- Just start working (actions > words)
## Handling Unclear Feedback
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."## Source-Specific Handling
### From your human partner
- **Trusted** - implement after understanding
- **Still ask** if scope unclear
- **No performative agreement**
- **Skip to action** or technical acknowledgment
### From External Reviewers
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"
## YAGNI Check for "Professional" Features
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."
## Implementation Order
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## When To Push Back
Push back when:
- Suggestion breaks existing functionality
- Reviewer lacks full context
- Violates YAGNI (unused feature)
- Technically incorrect for this stack
- Legacy/compatibility reasons exist
- Conflicts with your human partner's architectural decisions
**How to push back:**
- Use technical reasoning, not defensiveness
- Ask specific questions
- Reference working tests/code
- Involve your human partner if architectural
**Signal if uncomfortable pushing back out loud:** "Strange things are afoot at the Circle K"
## Acknowledging Correct Feedback
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.
## Gracefully Correcting Your Pushback
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-explainingState the correction factually and move on.
## Common Mistakes
| 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 |
## Real Examples
**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."## GitHub Thread Replies
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.## The Bottom Line
**External feedback = suggestions to evaluate, not orders to follow.**
Verify. Question. Then implement.
No performative agreement. Technical rigor always.
How to Use This Skill Unit
Option A: Project-Specific (Recommended)
- Click "Download" above
- In your project, create the directory:
.agent/skills/receiving-code-review/ - Save the file as
SKILL.md - The agent will automatically discover the skill based on its description.
Option B: Global Installation (All Agents)
Save the file to these locations to make it available across all projects:
- Claude Code:
~/.claude/skills/obra/superpowers/receiving-code-review/SKILL.md - Cursor:
~/.cursor/skills/obra/superpowers/receiving-code-review/SKILL.md - Antigravity:
~/.gemini/antigravity/skills/obra/superpowers/receiving-code-review/SKILL.md
🚀 Install with CLI:npx skills add obra/superpowers
Recommended Rules
View more rules →📝 Code Review Agent - Thorough & Constructive Reviewer
Agentic AICode ReviewQuality Assurance
You are an expert code review agent that provides thorough, constructive, and actionable feedback. Apply systematic reasoning to evaluate code quality...
Advanced AWS Integration (EventBridge, Step Functions)
AWSIntegrationServerless
You are an expert in advanced AWS integration services and patterns. Key Principles: - Choreography (Events) vs Orchestration (Workflows) - Decouplin...
Antigravity Workflow Fundamentals
WorkflowsAutomationBest Practices
You are an expert in creating Antigravity Workflows. Key Principles: - Workflows are step-by-step recipes for complex tasks - Must be in .agent/workf...
Recommended Workflows
View more workflows →Setup Monorepo with Turborepo
MonorepoTurborepoBuild
--- description: Configure Turborepo for fast monorepo builds --- 1. **Install Turborepo**: - Initialize in existing repo. // turbo - Run `n...
Debug 'Cannot Find Module' TypeScript Errors
TypeScriptDebuggingModules
--- description: Fix TypeScript module resolution issues --- 1. **Check tsconfig.json Paths**: - Verify path mappings are correct. ```json {...
Undo a "Bad" Public Push
GitRevertSafety
--- description: Safely revert a pushed commit without breaking history --- 1. **Find the Bad Commit Hash**: - Identify the commit that caused the...
