design-frontend
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseRules
规则
See rules index for detailed patterns.
请查看规则索引获取详细模式。
Examples
示例
Positive Trigger
触发场景（正向）
User: "Design a responsive dashboard layout with clear visual hierarchy."
Expected behavior: Use guidance, follow its workflow, and return actionable output.
design-frontend用户：“设计一个具有清晰视觉层级的响应式仪表板布局。”
预期行为：遵循指导原则，按照其工作流执行，返回可落地的输出结果。
design-frontendNon-Trigger
非触发场景
User: "Write unit tests for this payment service."
Expected behavior: Do not prioritize ; choose a more relevant skill or proceed without it.
design-frontend用户：“为这个支付服务编写单元测试。”
预期行为：无需优先使用；选择更相关的技能或直接执行任务。
design-frontendTroubleshooting
故障排查
Skill Does Not Trigger
技能未触发
- Error: The skill is not selected when expected.
- Cause: Request wording does not clearly match the description trigger conditions.
- Solution: Rephrase with explicit domain/task keywords from the description and retry.
- 问题：符合预期时技能未被选中。
- 原因：请求措辞未明确匹配描述中的触发条件。
- 解决方案：使用描述中的明确领域/任务关键词重新表述请求后重试。
Guidance Conflicts With Another Skill
指导原则与其他技能冲突
- Error: Instructions from multiple skills conflict in one task.
- Cause: Overlapping scope across loaded skills.
- Solution: State which skill is authoritative for the current step and apply that workflow first.
- 问题：同一任务中多个技能的指令存在冲突。
- 原因：已加载的技能存在范围重叠。
- 解决方案：明确当前步骤以哪个技能为权威，优先应用该技能的工作流。
Output Is Too Generic
输出内容过于笼统
- Error: Result lacks concrete, actionable detail.
- Cause: Task input omitted context, constraints, or target format.
- Solution: Add specific constraints (environment, scope, format, success criteria) and rerun.
- 问题：结果缺乏具体、可落地的细节。
- 原因：任务输入遗漏了上下文、约束条件或目标格式。
- 解决方案：添加具体约束（环境、范围、格式、成功标准）后重新执行。
Workflow
工作流
- Identify whether the request clearly matches scope and triggers.
design-frontend - Apply the skill rules and referenced guidance to produce a concrete result.
- Validate output quality against constraints; if gaps remain, refine once with explicit assumptions.
- 判断请求是否明确匹配的适用范围和触发条件。
design-frontend - 应用技能规则及参考指导原则生成具体结果。
- 根据约束条件验证输出质量；若存在不足，基于明确假设优化一次。