Back to Details

grill-me

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Grill Me

Grill Me

Thoroughly vet plans and designs through systematic, relentless questioning.
通过系统性、高强度的提问全面审查计划与设计。

When to use this skill

适用场景

  • Before committing to an architectural decision
  • When a design feels right but hasn't been challenged
  • Stress-testing assumptions before implementation begins
  • Exploring edge cases and failure modes in a proposal
  • 在敲定架构决策之前
  • 当设计看似合理但尚未经过质疑时
  • 在开始实施前对假设进行压力测试
  • 探索方案中的边缘情况与故障模式

When not to use this skill

不适用场景

  • Quick clarifying questions → just ask directly
  • Validating against domain docs → use 
    grill-with-docs
  • Writing implementation tickets → use 
    to-issues
  • 快速澄清问题→直接提问即可
  • 对照领域文档验证→使用
    grill-with-docs
  • 编写实施工单→使用
    to-issues

Process

流程

Interview relentlessly about every aspect of the plan until shared understanding is reached. Walk down each branch of the decision tree, resolving dependencies between decisions one by one.
Rules:
  • Ask one question at a time
  • Wait for feedback before continuing
  • Provide a recommended answer with each question
  • Explore the codebase instead of asking when the answer is findable there
  • Keep going until all branches of the decision tree are resolved
针对计划的各个方面进行深度问询，直到达成共识。逐一梳理决策树的每个分支，逐个解决决策之间的依赖关系。
规则：
  • 一次只提一个问题
  • 等待反馈后再继续
  • 每个问题附带推荐答案
  • 若答案可在代码库中找到，则直接查看代码库而非提问
  • 持续进行直到决策树的所有分支都梳理完毕

What gets covered

覆盖内容

The grilling session explores:
  • Why this approach? — What alternatives were considered and rejected?
  • What breaks first? — Edge cases, failure modes, error states
  • What are the dependencies? — What must be true for this to work?
  • What changes later? — Which parts are likely to evolve?
  • What can't change? — Which decisions are load-bearing and hard to reverse?
  • Who is affected? — Callers, consumers, downstream systems
拷问环节将探索以下内容：
  • 为何选择此方案？——考虑过哪些替代方案并为何被否决？
  • 哪部分最先失效？——边缘情况、故障模式、错误状态
  • 依赖项有哪些？——方案生效的必要前提是什么？
  • 后续会有哪些变化？——哪些部分可能会演进？
  • 哪些内容不可更改？——哪些决策是核心且难以逆转的？
  • 会影响哪些对象？——调用方、消费者、下游系统

Output

输出结果

By the end of the session:
  • Every major decision point has been examined
  • Dependencies between decisions have been resolved in order
  • Remaining open questions are documented
  • Shared understanding exists about trade-offs made
会话结束时：
  • 所有主要决策点均已审查完毕
  • 决策之间的依赖关系已按顺序梳理清楚
  • 记录剩余未解决的问题
  • 各方对所做的权衡达成共识

Activation

触发方式

User says: "grill me", "stress-test this plan", "challenge my design", "ask me hard questions about this"
用户输入："grill me"、"stress-test this plan"、"challenge my design"、"ask me hard questions about this"

Instructions

操作说明

  1. Identify the task trigger and expected output.
  2. Follow the workflow steps in this skill from top to bottom.
  3. Validate outputs before moving to the next step.
  4. Capture blockers and fallback path if any step fails.
  1. 识别任务触发条件与预期输出。
  2. 从上到下遵循本skill的工作流程步骤。
  3. 进入下一步前验证输出结果。
  4. 记录阻塞点及若步骤失败时的回退路径。

Examples

示例

  • Example: Apply this skill to a small scope first, then scale to full scope after validation passes.
  • 示例：先将此skill应用于小范围场景，验证通过后再扩展至全范围。

Best practices

最佳实践

  • Keep outputs deterministic and auditable.
  • Prefer small reversible changes over broad risky edits.
  • Record assumptions explicitly.
  • 保持输出结果可确定、可审计。
  • 优先选择小范围可逆转的变更，而非大范围高风险的修改。
  • 明确记录假设条件。

References

参考资料

  • Project standards: 
    .agent-skills/skill-standardization/SKILL.md
  • Validator script: 
    .agent-skills/skill-standardization/scripts/validate_skill.sh
  • 项目标准：
    .agent-skills/skill-standardization/SKILL.md
  • 验证脚本：
    .agent-skills/skill-standardization/scripts/validate_skill.sh