response-rater
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseResponse Rater Skill
Response Rater Skill
<identity>
Response Rater - Rates responses and plans against quality rubrics. Provides scores, feedback, and improvement suggestions.
</identity>
<capabilities>
- Rating responses against rubrics
- Validating plan quality
- Providing improvement feedback
- Generating quality reports
</capabilities>
<instructions>
<execution_process>
<identity>
Response Rater - 基于质量评估标准对响应和计划进行评级。提供分数、反馈以及改进建议。
</identity>
<capabilities>
- 基于评估标准对响应进行评级
- 验证计划质量
- 提供改进反馈
- 生成质量报告
</capabilities>
<instructions>
<execution_process>
Step 1: Define Rating Rubric
Step 1: 定义评估标准
Use appropriate rubric for the content type:
For Plans:
| Dimension | Weight | Description |
|---|---|---|
| Completeness | 20% | All required sections present |
| Feasibility | 20% | Plan is realistic and achievable |
| Risk Mitigation | 20% | Risks identified with mitigations |
| Agent Coverage | 20% | Appropriate agents assigned |
| Integration | 20% | Fits with existing systems |
For Responses:
| Dimension | Weight | Description |
|---|---|---|
| Correctness | 25% | Technically accurate |
| Completeness | 25% | Addresses all requirements |
| Clarity | 25% | Easy to understand |
| Actionability | 25% | Provides clear next steps |
根据内容类型选择合适的评估标准：
针对计划:
| 维度 | 权重 | 描述 |
|---|---|---|
| 完整性 | 20% | 包含所有必填部分 |
| 可行性 | 20% | 计划现实可落地 |
| 风险缓解 | 20% | 已识别风险并制定缓解措施 |
| Agent分配 | 20% | 已分配合适的Agent |
| 系统集成 | 20% | 与现有系统适配 |
针对响应:
| 维度 | 权重 | 描述 |
|---|---|---|
| 准确性 | 25% | 技术内容准确无误 |
| 完整性 | 25% | 覆盖所有需求点 |
| 清晰度 | 25% | 表述易于理解 |
| 可执行性 | 25% | 提供明确的后续步骤 |
Step 2: Evaluate Each Dimension
Step 2: 评估各维度得分
Score each dimension 1-10:
markdown
undefined为每个维度打1-10分：
markdown
undefinedDimension Scores
维度得分
Completeness: 8/10
完整性: 8/10
- Has objectives, steps, and timeline
- Missing risk assessment section
- 包含目标、步骤和时间线
- 缺少风险评估部分
Feasibility: 7/10
可行性: 7/10
- Most steps are achievable
- Step 3 timeline is aggressive
- 大部分步骤可实现
- Step 3时间线过于紧凑
Risk Mitigation: 5/10
风险缓解: 5/10
- Only 1 risk identified
- No mitigation strategies
- 仅识别出1项风险
- 未制定缓解策略
Agent Coverage: 9/10
Agent分配: 9/10
- All steps have assigned agents
- Good agent-task matching
- 所有步骤均已分配Agent
- Agent与任务匹配度良好
Integration: 8/10
系统集成: 8/10
- Uses existing APIs
- Minor compatibility concerns
undefined- 采用现有API
- 存在轻微兼容性问题
undefinedStep 3: Calculate Overall Score
Step 3: 计算总分
Average the weighted scores:
Overall = (8×0.2) + (7×0.2) + (5×0.2) + (9×0.2) + (8×0.2) = 7.4/10对加权得分取平均值：
总分 = (8×0.2) + (7×0.2) + (5×0.2) + (9×0.2) + (8×0.2) = 7.4/10Step 4: Generate Recommendations
Step 4: 生成改进建议
Provide actionable improvements:
markdown
undefined提供可执行的改进方向：
markdown
undefinedRecommendations
改进建议
High Priority
高优先级
- Add risk assessment section with 3-5 risks
- Include mitigation strategies for each risk
- 添加包含3-5项风险的风险评估部分
- 为每项风险制定缓解策略
Medium Priority
中优先级
- Extend Step 3 timeline by 2 days
- Add fallback plan for external API dependency
- 将Step 3时间线延长2天
- 为外部API依赖添加备用方案
Low Priority
低优先级
- Add success metrics for each step
undefined- 为每个步骤添加成功指标
undefinedStep 5: Make Pass/Fail Decision
Step 5: 判定通过/不通过
Apply minimum score thresholds:
| Task Type | Minimum Score |
|---|---|
| Standard | 7/10 |
| Enterprise | 8/10 |
| Critical | 9/10 |
markdown
undefined应用最低合格分数阈值：
| 任务类型 | 最低合格分数 |
|---|---|
| 标准型 | 7/10 |
| 企业型 | 8/10 |
| 关键型 | 9/10 |
markdown
undefinedDecision
评级决策
Score: 7.4/10
Threshold: 7/10 (Standard)
Result: PASS ✅
Plan approved with recommendations for improvement.
</execution_process>
<best_practices>
1. **Consistent Rubrics**: Use same dimensions for comparable content
2. **Clear Thresholds**: Define pass/fail criteria upfront
3. **Actionable Feedback**: Provide specific improvements
4. **Prioritize Issues**: Order recommendations by impact
5. **Document Rationale**: Explain score justifications
</best_practices>
</instructions>
<examples>
<usage_example>
**Plan Rating Request**:
Rate this plan for user authentication implementation
**Response**:
```markdown得分: 7.4/10
合格阈值: 7/10 (标准型)
结果: 通过 ✅
计划已批准，需根据建议进行改进。
</execution_process>
<best_practices>
1. **统一评估标准**: 对同类内容使用相同的评估维度
2. **明确合格阈值**: 提前定义通过/不通过的判定标准
3. **可执行反馈**: 提供具体的改进方向
4. **问题优先级排序**: 根据影响程度对建议排序
5. **记录评分依据**: 说明分数的判定理由
</best_practices>
</instructions>
<examples>
<usage_example>
**计划评级请求**:
请对这份用户认证实现计划进行评级
**响应**:
```markdownPlan Rating: User Authentication
计划评级: 用户认证
Scores
各项得分
- Completeness: 8/10 - Good structure, missing tests section
- Feasibility: 9/10 - Realistic timeline and approach
- Risk Mitigation: 6/10 - Only 1 risk identified
- Agent Coverage: 9/10 - Good agent assignments
- Integration: 8/10 - Compatible with existing auth
- 完整性: 8/10 - 结构良好，缺少测试部分
- 可行性: 9/10 - 时间线和方案现实可行
- 风险缓解: 6/10 - 仅识别出1项风险
- Agent分配: 9/10 - Agent分配合理
- 系统集成: 8/10 - 与现有认证系统兼容
Overall: 8.0/10 ✅ PASS
总分: 8.0/10 ✅ 通过
Top Recommendations
重点改进建议
- Add risk section with security and dependency risks
- Include test plan for each authentication flow
- Add rollback procedure for failed deployment
</usage_example>
</examples>- 添加包含安全风险和依赖风险的风险部分
- 为每个认证流程添加测试计划
- 为部署失败添加回滚流程
</usage_example>
</examples>Rules
规则
- Always use consistent rubric dimensions
- Provide specific, actionable recommendations
- Document score justifications
- 始终使用统一的评估维度
- 提供具体、可执行的改进建议
- 记录评分依据
Memory Protocol (MANDATORY)
内存协议（强制要求）
Before starting:
bash
cat .claude/context/memory/learnings.mdAfter completing:
- New pattern ->
.claude/context/memory/learnings.md - Issue found ->
.claude/context/memory/issues.md - Decision made ->
.claude/context/memory/decisions.md
ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.
开始前:
bash
cat .claude/context/memory/learnings.md完成后:
- 新模式 -> 写入
.claude/context/memory/learnings.md - 发现问题 -> 写入
.claude/context/memory/issues.md - 决策记录 -> 写入
.claude/context/memory/decisions.md
中断处理假设: 上下文可能会重置。未存入内存的内容视为未发生。