tech-drizzle
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseRules
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: "Model a Drizzle schema and migration for invoices with relations."
Expected behavior: Use guidance, follow its workflow, and return actionable output.
tech-drizzle用户：“为带有关联关系的发票设计Drizzle模式和迁移方案。”
预期行为：遵循指南，按照其工作流程执行，并返回可落地的输出结果。
tech-drizzleNon-Trigger
非触发场景
User: "Plan an accessibility audit for keyboard navigation."
Expected behavior: Do not prioritize ; choose a more relevant skill or proceed without it.
tech-drizzle用户：“规划针对键盘导航的无障碍审计。”
预期行为：不优先使用；选择更相关的技能或直接执行任务。
tech-drizzleTroubleshooting
问题排查
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.
- 错误：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
指南与其他技能冲突
- 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.
- 错误：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：指定当前步骤的权威技能，并优先应用其工作流程。
Output Is Too Generic
输出过于通用
- 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.
- 错误：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
工作流程
- Identify whether the request clearly matches scope and triggers.
tech-drizzle - 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并触发该技能。
tech-drizzle - 应用技能规则和参考指南生成具体结果。
- 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。