skills/workflow/receiving-review-feedback/SKILL.md
Use when receiving code review feedback from CodeRabbit, PR reviewers, or human reviewers — before implementing any suggested changes.
npx skillsauth add faysilalshareef/dotnet-ai-kit receiving-review-feedbackInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Verify before implementing. Ask before assuming. Technical correctness over social comfort.
Code review requires technical evaluation, not emotional performance.
WHEN receiving code review feedback:
1. READ → Complete feedback without reacting
2. UNDERSTAND → Restate the requirement in your own words (or ask)
3. VERIFY → Check the suggestion against codebase reality
4. EVALUATE → Is it technically sound for THIS codebase?
5. RESPOND → Technical acknowledgment or reasoned pushback
6. IMPLEMENT → One item at a time, test each
NEVER say:
INSTEAD:
If you catch yourself about to write "Thanks" or "Great point": DELETE IT. State the fix instead.
GOOD: "Fixed. Added null check in OrderHandler.cs:45."
GOOD: "Good catch — sequence validation was missing. Fixed in EventProcessor.cs."
GOOD: [Just fix it and show the diff]
BAD: "You're absolutely right! Great catch!"
BAD: "Thanks for catching that! Let me fix it right away!"
BAD: "Excellent point, I should have thought of that!"
GOOD: "You were right — I checked the EF migration and it does require the index. Implementing now."
GOOD: "Verified and you're correct. My initial read of the middleware was wrong. Fixing."
BAD: Long apology
BAD: Defending why you pushed back
BAD: Over-explaining
State the correction factually and move on.
Handle feedback differently based on its source:
Conflict resolution: If a suggestion from a lower-priority source contradicts a higher one, stop and flag to the user.
BEFORE implementing any external suggestion:
1. Is this technically correct for THIS codebase?
2. Does it break existing functionality?
3. Is there a reason for the current implementation?
4. Does it work on all target platforms?
5. Does the reviewer understand the full context?
Program.cs or Startup.cs?When a reviewer suggests "implementing properly" or adding extra features:
1. Grep the codebase for actual usage of the thing being improved
2. IF unused → "This isn't called anywhere. Remove it (YAGNI)?"
3. IF used → Implement properly
Do NOT gold-plate code just because a reviewer suggests it.
IF any item in the feedback is unclear:
STOP — do not implement anything yet
ASK for clarification on ALL unclear items
WHY: Items may be related. Partial understanding = wrong implementation.
Example:
Reviewer gives 6 items. You understand 1, 2, 3, 6. Unclear on 4, 5.
BAD: Implement 1, 2, 3, 6 now — ask about 4, 5 later
GOOD: "I understand items 1, 2, 3, 6. Need clarification on 4 and 5 before proceeding."
Push back when:
How to push back:
| Excuse | Reality | |--------|---------| | "Reviewer is senior, they must be right" | Seniority is not proof. Verify technically. | | "It's easier to just implement it" | Easy implementation of wrong suggestion = tech debt | | "I don't want to seem difficult" | Social comfort is not a codebase concern | | "They probably know something I don't" | Ask, don't assume. Verify, don't comply. | | "It's just a small change" | Small wrong changes compound | | "CodeRabbit flagged it so it must matter" | CodeRabbit lacks project context. Verify. | | "I'll push back later if it causes issues" | Prevent issues now, not debug later |
| Mistake | Fix | |---------|-----| | Performative agreement | State the requirement or just act | | Blind implementation | Verify against codebase first | | Implementing all at once | One at a time, test each | | Assuming reviewer is right | Check if it breaks things | | Avoiding pushback | Technical correctness > comfort | | Partial implementation | Clarify all items first |
External feedback = suggestions to evaluate, not orders to follow.
Verify. Question. Then implement. No performative agreement. Technical rigor always.
data-ai
Use when about to claim work is complete, fixed, passing, or ready — before committing, creating PRs, or moving to the next task. Requires running verification commands and confirming output before making any success claims.
development
Use when encountering any bug, test failure, build error, or unexpected behavior — before proposing fixes or making changes.
development
Use when checkpointing, wrapping up, or handing off an AI-assisted development session.
development
Use when following the Specification-Driven Development lifecycle from plan through ship.