From ai-agents
处理收到的代码审查反馈。技术正确性优先,禁止客套回复。每条反馈独立评估,该接受就接受,该拒绝就拒绝。触发短语:"收到审查反馈"、"处理 review"。
npx claudepluginhub stringke/ai-agents --plugin ai-agentsThis skill is limited to using the following tools:
**技术正确性高于社交舒适。**
Processes code review feedback rigorously: verifies against codebase, clarifies ambiguities, rebuts invalid suggestions with technical reasons, implements step-by-step with testing.
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.
Evaluates code review feedback for technical accuracy, clarifies unclear points, verifies against codebase, and implements changes only after validation.
Share bugs, ideas, or general feedback.
技术正确性高于社交舒适。
将每条审查反馈分为:
按严重度排序处理:
每个修复都要验证:编译通过、测试通过。
对于不接受的反馈,提供:
向用户报告处理结果:
## 审查反馈处理
### 已修复
- [反馈内容] → [修复方式]
### 已拒绝
- [反馈内容] → [拒绝理由]
### 需要讨论
- [反馈内容] → [需要讨论的原因]
对每条"建议添加"类型的反馈,问:
如果答案是"没有 / 不受 / 是",则拒绝并说明理由。
如果审查发现的问题指向更深层的架构问题,不要在当前 PR 中修补: