From srnnkls-tropos
Technical evaluation of code review feedback. Use when receiving review feedback - requires verification before implementing, no performative agreement, push back when technically wrong.
npx claudepluginhub joshuarweaver/cascade-code-general-misc-2 --plugin srnnkls-troposThis skill uses the workspace's default tool permissions.
Code review requires technical evaluation, not emotional performance.
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Code 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:
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:
Feedback: "Fix items 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."
When reviewer suggests adding features:
IF reviewer suggests "implementing properly":
Search codebase for actual usage
IF unused: "This isn't called anywhere. Remove it (YAGNI)?"
IF used: Then implement properly
Push back when:
How to push back:
For multi-item feedback:
When feedback IS correct:
DO: "Fixed. [Brief description of what changed]"
DO: "Good catch - [specific issue]. Fixed in [location]."
DO: [Just fix it and show in the code]
DON'T: "You're absolutely right!"
DON'T: "Thanks for catching that!"
DON'T: ANY gratitude expression
Why no thanks: Actions speak. Just fix it.
If you pushed back and were wrong:
DO: "Verified and you're correct. My understanding was wrong. Fixing."
DON'T: Long apology or defending why you pushed back
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 |
Use with:
task-dispatch - Handle review between taskscode-test - Test each fix individuallycompletion-verify - Verify fixes actually work