From oh-my-claude
Process code review feedback rigorously: read fully, understand issues, verify claims against code, evaluate fixes, respond with evidence, and implement changes. For PRs, agent reviews, external feedback.
npx claudepluginhub techdufus/oh-my-claude --plugin oh-my-claudeThis skill uses the workspace's default tool permissions.
How to handle review feedback with technical rigor, not performative agreement.
Evaluates code review feedback for technical accuracy, clarifies unclear points, verifies against codebase, and implements changes only after validation.
Guides rigorous handling of code review feedback: read fully, restate for understanding, verify technical soundness against codebase, clarify unclear items, respond with reasoning before implementing.
Processes code review feedback technically: verify suggestions against codebase, clarify unclear items, push back if questionable, implement after evaluation—not blind agreement.
Share bugs, ideas, or general feedback.
How to handle review feedback with technical rigor, not performative agreement.
READ -> UNDERSTAND -> VERIFY -> EVALUATE -> RESPOND -> IMPLEMENT
Read the full review. Don't skim, don't react immediately. Take in every comment before acting on any of them. Later comments may contradict or contextualize earlier ones.
For each issue, understand what's actually being flagged. Restate in your own words: "This comment is about X because Y." If you can't restate it, you don't understand it yet.
Check if the reviewer's claim is factually correct. Read the code they reference. Don't assume they're right or wrong -- look at the actual code at {file}:{line}.
Is this a real issue? Does the suggested fix actually improve things? Is the effort justified given the impact? Not all feedback requires action.
Technical response only:
{file}:{line} shows Y handles this case."Fix in order: clarify unclear items -> blocking issues -> simple fixes -> complex fixes. Test each fix independently before moving to the next.
These responses indicate you're people-pleasing, not engineering:
Instead: "The review identifies X. Checking... [evidence]. This is correct because [reason]. Fixing."
Or: "The review suggests X, but [counter-evidence]. Keeping current approach because [reason]."
| Source | Trust Level | Response Style |
|---|---|---|
| Human partner | High context | Clarify intent, implement thoughtfully |
| External reviewer | Medium context | Verify claims against code, ask about unknowns |
| code-reviewer agent | Systematic but no context | Cross-reference with requirements, verify specifics |
{file}:{line} shows Y"Pushing back is not adversarial. It's quality control. Reviewers benefit from knowing when their feedback misses context.
| Mistake | Why It's Wrong | Do This Instead |
|---|---|---|
| Fix everything without reading all comments | Later comments may contradict earlier ones | Read ALL comments first |
| Performative agreement | Hides misunderstanding | Respond with technical reasoning |
| Batch all fixes in one commit | Can't isolate if something breaks | One logical change per commit |
| Skip re-testing after fixes | Fixes introduce new bugs | Test after every change |
| Ignore minor issues | They accumulate | Fix or explicitly defer with reason |
Review feedback is data, not judgment. Evaluate it technically, respond with evidence, implement with discipline.