platform-backend
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChinesePrinciples
原则
- Throw early with guard clauses — fail fast at the top of functions
- Never swallow errors silently — log or propagate every failure
- 使用守卫语句尽早抛出异常——在函数顶部快速失败
- 切勿静默忽略错误——记录或传播每一处故障
Rules
规则
See rules index for detailed patterns.
查看规则索引获取详细模式。
Examples
示例
Positive Trigger
触发场景
User: "Design error handling and validation strategy for this API endpoint."
Expected behavior: Use guidance, follow its workflow, and return actionable output.
platform-backend用户：“为这个API端点设计错误处理和验证策略。”
预期行为：遵循指导规范，执行其工作流程，并返回可落地的输出结果。
platform-backendNon-Trigger
非触发场景
User: "Create a Tailwind design token scale."
Expected behavior: Do not prioritize ; choose a more relevant skill or proceed without it.
platform-backend用户：“创建Tailwind设计令牌体系。”
预期行为：不优先使用；选择更相关的Skill或直接执行任务。
platform-backendTroubleshooting
故障排查
Skill Does Not Trigger
Skill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：预期情况下Skill未被选中。
- 原因：请求表述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
指导规范与其他Skill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Skill的指令存在冲突。
- 原因：已加载的Skill存在范围重叠。
- 解决方案：指定当前步骤以哪个Skill为权威，优先应用其工作流程。
Output Is Too Generic
输出过于笼统
- 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）后重新运行。
Workflow
工作流程
- Identify whether the request clearly matches scope and triggers.
platform-backend - 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范围和触发条件。
platform-backend - 应用Skill规则及参考的指导规范生成具体结果。
- 根据约束条件验证输出质量；若仍存在不足，基于明确假设优化一次。