Skill
4
Agent
All Skills
Search
Tools
中文
|
EN
Explore
Loading...
Back to Details
tech-trpc
Compare original and translation side by side
🇺🇸
Original
English
🇨🇳
Translation
Chinese
Rules
规则
See
rules index
for detailed patterns.
查看
规则索引
获取详细模式说明。
Examples
示例
Positive Trigger
正向触发场景
User: "Design tRPC procedures and router slices for the checkout flow."
Expected behavior: Use
tech-trpc
guidance, follow its workflow, and return actionable output.
用户:"为结账流程设计tRPC过程与路由切片。"
预期行为:遵循
tech-trpc
指导规范,按照其工作流执行,并返回可落地的输出结果。
Non-Trigger
非触发场景
User: "Implement Vitest fake timer tests for debounce utilities."
Expected behavior: Do not prioritize
tech-trpc
; choose a more relevant skill or proceed without it.
用户:"为防抖工具实现Vitest假计时器测试。"
预期行为:无需优先使用
tech-trpc
;选择更相关的技能或直接执行任务。
Troubleshooting
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:技能未按预期被选中。
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导说明存在冲突。
原因:已加载的技能存在范围重叠。
解决方案:明确指定当前步骤遵循的权威技能,并优先应用其工作流。
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)后重新执行。
Workflow
工作流
Identify whether the request clearly matches
tech-trpc
scope and triggers.
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
tech-trpc
的适用范围与触发条件。
应用技能规则及参考指导生成具体结果。
根据约束条件验证输出质量;若存在信息缺口,基于明确假设优化一次。