checkpoint

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Checkpoint

Pause, assess, and surface intelligent next-step options to the user.

暂停执行、评估当前情况，并为用户呈现智能的下一步选项。

When to Trigger Proactively

主动触发时机

Suggest this skill (without being asked) when detecting:

Completion signal: A feature, fix, or milestone just finished
Uncertainty signal: Requirements unclear, multiple valid paths, or low confidence in current direction
Complexity signal: Scope expanded, unexpected dependencies emerged, or task is taking longer than expected
Drift signal: Work may have diverged from user's original intent
Quality signal: Code works but may benefit from review, testing, or refactoring

当检测到以下信号时，主动建议使用该技能（无需用户请求）：

完成信号：某个功能、修复任务或里程碑刚完成
不确定信号：需求不明确、存在多种可行路径，或对当前方向信心不足
复杂度信号：范围扩大、出现意外依赖，或任务耗时超出预期
偏离信号：工作可能与用户最初的意图产生偏差
质量信号：代码可运行，但可能需要评审、测试或重构

Workflow

工作流程

1. Context Assessment

1. 上下文评估

Silently evaluate the current state across these dimensions (do not output this analysis):

Progress: What has been accomplished? What remains?
Quality: Is the work solid, or are there rough edges?
Alignment: Does recent work match what the user actually wants?
Uncertainty: What assumptions were made? What's unclear?
Risk: What could go wrong? What hasn't been tested?
Efficiency: Is there a better path forward?

静默评估当前状态的以下维度（无需输出该分析过程）：

进度：已完成哪些工作？还剩余哪些？
质量：当前工作是否扎实，还是存在不完善之处？
对齐度：近期工作是否符合用户的实际需求？
不确定性：做出了哪些假设？哪些内容不明确？
风险：可能会出现哪些问题？哪些内容尚未测试？
效率：是否有更优的后续路径？

2. Generate Options

2. 生成选项

Based on assessment, generate 2-5 contextually-appropriate options. Draw from (but don't limit to) these archetypes:

Archetype	When Relevant
Commit progress	Meaningful progress made, good stopping point
Systems audit	Complex changes, potential for bugs or regressions
Prioritize/plan	Multiple pending tasks, unclear what matters most
Re-evaluate decisions	Low confidence in recent choices, new information available
Clarify with user	Assumptions made, requirements ambiguous
Test/verify	Code works but edge cases untested
Refactor/clean up	Code functional but messy
Document	Complex logic that needs explanation
Step back	May be overcomplicating or missing simpler solution
Continue current path	Clear next step, no reason to pause

Option generation principles:

Options should be meaningfully different, not variations of the same thing
Include at least one "continue forward" option when momentum is valuable
Include at least one "pause and verify" option when risk is present
Avoid analysis paralysis - fewer sharp options beat many vague ones

基于评估结果，生成2-5个符合上下文的选项。可参考（但不限于）以下类型：

选项类型	适用场景
提交当前进度	已取得有意义的进展，是合适的暂停节点
系统审计	进行了复杂变更，存在潜在Bug或回归风险
优先级排序/规划	存在多个待办任务，不清楚哪些更重要
重新评估决策	对近期的选择信心不足，或有新信息可用
与用户澄清	做出了假设，需求存在模糊之处
测试/验证	代码可运行，但边缘场景未测试
重构/清理	代码可正常运行，但结构混乱
文档编写	存在需要解释的复杂逻辑
退一步思考	可能过度复杂化，或遗漏了更简单的解决方案
继续当前路径	下一步明确，无需暂停

选项生成原则：

选项之间应有显著差异，而非同一内容的变体
当保持推进节奏有价值时，至少包含一个“继续推进”选项
当存在风险时，至少包含一个“暂停并验证”选项
避免分析瘫痪：少而精准的选项优于多而模糊的选项

3. Select Recommendation

3. 选择推荐选项

Choose one option as recommended. The recommendation should reflect:

What would a thoughtful senior engineer do here?
What reduces risk of wasted effort or rework?
What serves the user's underlying goals (not just stated requests)?

选择一个选项作为推荐项。推荐应遵循以下原则：

一位资深工程师在此场景下会如何选择？
如何减少无效工作或返工的风险？
如何服务于用户的核心目标（而非仅仅是明确提出的需求）？

4. Present via AskUserQuestion

4. 通过AskUserQuestion呈现

Use AskUserQuestion with this structure:

Question: "What would you like to do next?"
Header: "Next step" (or contextually appropriate 1-2 words)
Options: [generated options with descriptions]

Option format:

```
label
```
: Action verb phrase (e.g., "Commit current progress", "Run systems audit")
```
description
```
: 1 sentence explaining what this involves and why it might be valuable

Recommendation:

Place recommended option FIRST in the list
Append "(Recommended)" to its label
Include rationale in the description

使用AskUserQuestion，遵循以下结构：

Question: "What would you like to do next?"
Header: "Next step" (or contextually appropriate 1-2 words)
Options: [generated options with descriptions]

选项格式：

```
label
```
: 动作动词短语（例如："Commit current progress", "Run systems audit"）
```
description
```
: 用一句话说明该选项的内容及价值

推荐项处理：

将推荐选项放在列表首位
在其label后追加"(Recommended)"
在description中包含推荐理由

Example Output

示例输出

For a scenario where a feature was just implemented but with some shortcuts:

AskUserQuestion:
  question: "Feature implementation complete. What would you like to do next?"
  header: "Next step"
  options:
    - label: "Review and refactor (Recommended)"
      description: "Clean up the shortcuts taken during implementation before they become technical debt. The core logic works but could be more maintainable."
    - label: "Add test coverage"
      description: "Write tests for the new feature to catch edge cases and prevent regressions."
    - label: "Commit and move on"
      description: "The feature works - commit it and tackle the next task. Can refactor later if needed."
    - label: "Walk me through what was built"
      description: "Explain the implementation so you can verify it matches your expectations before proceeding."

假设场景：某个功能刚实现，但存在一些临时简化处理：

AskUserQuestion:
  question: "Feature implementation complete. What would you like to do next?"
  header: "Next step"
  options:
    - label: "Review and refactor (Recommended)"
      description: "Clean up the shortcuts taken during implementation before they become technical debt. The core logic works but could be more maintainable."
    - label: "Add test coverage"
      description: "Write tests for the new feature to catch edge cases and prevent regressions."
    - label: "Commit and move on"
      description: "The feature works - commit it and tackle the next task. Can refactor later if needed."
    - label: "Walk me through what was built"
      description: "Explain the implementation so you can verify it matches your expectations before proceeding."

Anti-Patterns

反模式

Don't overthink: This skill should take seconds, not minutes
Don't list every possible option: Curate the most valuable 2-5
Don't recommend "ask user" when the situation is clear: Have a point of view
Don't trigger too frequently: Reserve for genuine decision points, not every minor step
Don't explain the assessment process: Just present the options naturally

不要过度思考：该技能的执行应仅需数秒，而非数分钟
不要列出所有可能的选项：精选最有价值的2-5个即可
不要在情况明确时推荐“询问用户”：要有明确的观点
不要过于频繁触发：仅在真正的决策点使用，而非每一个小步骤
不要解释评估过程：自然呈现选项即可