From bee-default
Review reception protocol - requires technical verification before implementing suggestions. Prevents performative agreement and blind implementation.
npx claudepluginhub luanrodrigues/ia-frmwrk --plugin bee-defaultThis skill uses the workspace's default tool permissions.
Code review requires technical evaluation, not emotional performance.
Generates design tokens/docs from CSS/Tailwind/styled-components codebases, audits visual consistency across 10 dimensions, detects AI slop in UI.
Records polished WebM UI demo videos of web apps using Playwright with cursor overlay, natural pacing, and three-phase scripting. Activates for demo, walkthrough, screen recording, or tutorial requests.
Delivers idiomatic Kotlin patterns for null safety, immutability, sealed classes, coroutines, Flows, extensions, DSL builders, and Gradle DSL. Use when writing, reviewing, refactoring, or designing Kotlin code.
Code review requires technical evaluation, not emotional performance.
Core principle: Verify before implementing. Ask before assuming. Technical correctness over social comfort.
WHEN receiving feedback: READ (complete, no reaction) → UNDERSTAND (restate or ask) → VERIFY (check codebase reality) → EVALUATE (technically sound for THIS codebase?) → RESPOND (technical acknowledgment or pushback) → IMPLEMENT (one at a time, test each)
NEVER:
INSTEAD:
IF any item is unclear: STOP - do not implement anything yet. ASK for clarification. Items may be related - partial understanding = wrong implementation.
Example: "Fix 1-6" - You understand 1,2,3,6, unclear on 4,5. ❌ Implement 1,2,3,6 now. ✅ "Understand 1,2,3,6. Need clarification on 4 and 5 before proceeding."
BEFORE implementing: (1) Technically correct for THIS codebase? (2) Breaks existing functionality? (3) Reason for current implementation? (4) Works on all platforms/versions? (5) Does reviewer understand full context?
your human partner's rule: "External feedback - be skeptical, but check carefully"
IF reviewer suggests "implementing properly": grep codebase for actual usage. Unused? "This endpoint isn't called. Remove it (YAGNI)?" 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."
FOR multi-item feedback: (1) Clarify anything unclear FIRST (2) Implement: Blocking issues → Simple fixes → Complex fixes (3) Test each fix individually (4) Verify no regressions
Push back when:
How to push back:
Signal if uncomfortable pushing back out loud: "Strange things are afoot at the Circle K"
✅ "Fixed. [Brief description]" | ✅ "Good catch - [issue]. Fixed in [location]." | ✅ [Just fix it and show in code] ❌ "You're absolutely right!" | ❌ "Great point!" | ❌ "Thanks for [anything]" | ❌ ANY gratitude expression
Why no thanks: Actions speak. Just fix it. The code shows you heard the feedback. About to write "Thanks"? DELETE IT. State the fix instead.
If you pushed back and were wrong: ✅ "You were right - I checked [X] and it does [Y]. Implementing now." ❌ Long apology, defending why you pushed back, over-explaining. 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 |
| Can't verify, proceed anyway | State limitation, ask for direction |
| Type | Response |
|---|---|
| Performative (Bad) | "Remove legacy code" → ❌ "You're absolutely right! Let me remove that..." |
| Technical (Good) | "Remove legacy code" → ✅ "Checking... build target is 10.15+, this API needs 13+. Need legacy for backward compat." |
| YAGNI (Good) | "Implement proper metrics" → ✅ "Grepped codebase - nothing calls this endpoint. Remove it (YAGNI)?" |
| Unclear (Good) | "Fix items 1-6" → ✅ "Understand 1,2,3,6. Need clarification on 4 and 5 before implementing." |
External feedback = suggestions to evaluate, not orders to follow.
Verify. Question. Then implement.
No performative agreement. Technical rigor always.
STOP and report if:
| Decision Type | Blocker Condition | Required Action |
|---|---|---|
| Unclear feedback | Cannot understand reviewer intent after initial read | STOP and ask for clarification before implementing |
| Conflicting feedback | Multiple reviewers suggest contradictory fixes | STOP and report conflict to human partner |
| Architectural change | Feedback requires major structural changes | STOP and discuss with human partner first |
| Missing context | Reviewer lacks full context and suggestion would break existing functionality | STOP and explain context before implementing |
The following requirements CANNOT be waived:
| Severity | Condition | Required Action |
|---|---|---|
| CRITICAL | Suggestion would break production functionality | MUST push back immediately with technical evidence |
| HIGH | Suggestion conflicts with architectural decisions | MUST discuss with human partner before implementing |
| MEDIUM | Suggestion unclear or partially understood | MUST ask clarifying questions before proceeding |
| LOW | Suggestion is cosmetic or stylistic preference | Should implement after verifying correctness |
| User Says | Your Response |
|---|---|
| "Just implement all the feedback quickly" | "MUST verify each suggestion against codebase first. Implementing without verification risks breaking functionality." |
| "The reviewer is senior, just trust them" | "CANNOT skip verification based on authority. Technical correctness requires evidence, not trust." |
| "Say thanks and move on" | "MUST NOT use performative agreement. Will acknowledge with technical response or just implement." |
| "We're running out of time, skip clarification" | "CANNOT implement unclear items. Partial understanding leads to wrong implementation." |
| Rationalization | Why It's WRONG | Required Action |
|---|---|---|
| "Reviewer must be right, they're experienced" | Experience doesn't guarantee context. Reviewer may not know full codebase. | MUST verify against codebase reality |
| "Saying thanks is just being polite" | Performative agreement obscures technical communication. | MUST use technical acknowledgment only |
| "I mostly understand the feedback, close enough" | Partial understanding = wrong implementation. Items may be interdependent. | MUST clarify ALL unclear items first |
| "Pushing back will upset the reviewer" | Technical correctness > social comfort. Wrong code upsets everyone. | MUST push back with technical reasoning |
| "Implementing quickly shows responsiveness" | Fast wrong implementation is worse than slow correct implementation. | MUST verify and test each fix individually |