reflect
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseReflect — Mid-Conversation Reassessment
Reflect——对话中途重评估
Portability: Pure-reasoning skill. No external tools required. Works in Claude Code CLI + Claude.ai web natively. Most portable in the v2 collection.
When invoked mid-conversation, this skill pauses execution and produces a frank reassessment of where the conversation has been heading. Output is flowing analysis (no headers, conversational tone) covering macro perspective, gap analysis, reflective inquiry, bias check, and contextual alignment. The skill ends with a clear directional recommendation: continue, pivot, or pause to answer a specific question.
可移植性: 纯推理Skill，无需外部工具。原生支持Claude Code CLI + Claude.ai网页端，是v2集合中可移植性最强的Skill之一。
当在对话中途调用该Skill时，它会暂停当前任务执行，并针对对话的发展方向给出坦诚的重评估结果。输出为流畅的分析内容（无标题，采用对话语气），涵盖宏观视角、差距分析、反思式探究、偏见检查以及上下文对齐。Skill结束时会给出明确的方向性建议：继续当前方向、转向新方向，或暂停以解答特定问题。
Invocation Triggers
触发条件
Explicit phrases:
- "reflect"
- "take a step back" / "step back"
- "zoom out"
- "are we missing something"
- "bigger picture"
- "what are we missing"
- "let's pause"
- "sanity check this"
- "are we on track"
- "are we overthinking this"
- "forest for the trees"
Implicit signals (no phrase needed):
- Conversation has gone 10+ turns deep on implementation details without strategic check-in
- User shows signs of frustration or stuck-ness
- Repeated dead-ends or pivots within a short span
When you detect an implicit trigger, don't auto-invoke — ask the user if they want to step back. Implicit signals are a prompt to OFFER reflection, not to unilaterally run it.
显式短语:
- "reflect"
- "take a step back" / "step back"
- "zoom out"
- "are we missing something"
- "bigger picture"
- "what are we missing"
- "let's pause"
- "sanity check this"
- "are we on track"
- "are we overthinking this"
- "forest for the trees"
隐式信号（无需特定短语）:
- 对话已深入10轮以上的实现细节，但未进行战略检查
- 用户表现出沮丧或陷入困境的迹象
- 短时间内反复出现死胡同或多次转向
当检测到隐式信号时，不要自动触发——需询问用户是否想要退一步审视。隐式信号是触发反思提议的提示，而非单方面执行反思的指令。
Stop Directive (Before Reassessing)
停止指令（重评估前）
Halt the current thread. Don't continue execution of the in-progress task. Reflection is a pause, not a side-quest.
This matters because:
- Continuing detail work while "reflecting on the side" defeats the purpose — you'll over-weight the current direction
- The user expects a clear break in cadence
- The reassessment needs full attention to the conversation history
终止当前线程。不要继续执行正在进行的任务。反思是暂停，而非支线任务。
这一点至关重要，原因如下：
- 在“边反思边继续细节工作”会违背反思的初衷——你会过度偏向当前方向
- 用户期望节奏有明确的中断
- 重评估需要全神贯注于对话历史
Grill-Me Optional Clarifier
可选澄清提问
This skill is intentionally low-intake — most invocations should run the 5-dimension analysis immediately without questions. The grill-me discipline applies only when the invocation is ambiguous (e.g., user pastes "step back" at the start of a fresh conversation with no prior context to reassess).
该Skill特意设计为低输入模式——大多数调用应立即执行五维度分析，无需提问。仅当调用存在歧义时（例如，用户在无任何前置上下文的新对话开头发送"step back"），才会启用澄清提问机制。
Q1 (optional, asked only when context is too thin to reassess)
Q1（可选，仅当上下文过于单薄无法重评估时提出）
What specifically should I reassess? Pick one:
- The goal — are we solving the right problem?
- The approach — is the path we're on the best one?
- The assumptions — what are we taking for granted?
- All of the above (default if you have time)
Why I'm asking: I'm seeing limited prior context to reassess, so I want to focus the reflection rather than guess. If you'd rather I do all three, that's fine — say so.
Forcing choice with default. Asked only when context is genuinely thin; otherwise skip and run the full analysis on existing conversation.
Stop condition: One question max. If the user invokes mid-conversation with normal context, no questions are asked — the skill runs directly.
我具体应重评估哪项内容？请选择一项：
- 目标——我们是否在解决正确的问题？
- 方法——我们当前的路径是否是最优选择？
- 假设——我们默认认为正确但未验证的内容是什么？
- 以上全部（若你时间充足则为默认选项）
提问原因： 我发现可用于重评估的前置上下文有限，因此希望聚焦反思内容而非猜测。若你希望我对以上三项都进行分析，也没问题——直接说明即可。
提供带默认选项的强制选择。仅当上下文确实单薄时才提出该问题；否则跳过提问，直接基于现有对话执行完整分析。
停止条件： 最多提出一个问题。若用户在有正常上下文的对话中途调用该Skill，则无需提问，直接执行Skill。
The 5-Dimension Analysis Framework
五维度分析框架
Re-read the full conversation from the original goal forward — not just recent turns. The discipline that distinguishes real reflection from local-context summary.
重新阅读从初始目标开始的完整对话——而非仅最近几轮内容。这是区分真正反思与局部上下文总结的关键准则。
1. Macro Perspective
1. 宏观视角
- Original goal: What did the user actually start trying to do?
- Drift detection: Has the conversation moved away from that goal? Toward something better or worse?
- Connection check: How does current work connect to the larger objective?
Anchor with specific evidence: "At turn 3 the goal was X; by turn 12 we're working on Y. Is Y a productive narrowing of X, or a drift away?"
- 初始目标: 用户最初实际想要达成的目标是什么？
- 偏移检测: 对话是否偏离了该目标？是朝向更好还是更差的方向？
- 关联性检查: 当前工作与更大目标的关联是什么？
需结合具体证据："在第3轮对话中目标是X；到第12轮我们正在处理Y。Y是对X的有效细化，还是偏离了X？"
2. Gap Analysis
2. 差距分析
- Unverified assumptions — what are we taking for granted that we haven't checked?
- Missing stakeholders / audiences / users — who needs this beyond the immediate context?
- Skipped constraints — technical, regulatory, resource limits not addressed
- Dismissed alternatives — paths considered but rejected; revisit briefly
- External factors — timing, market, dependencies not in scope
- 未验证的假设——我们默认认为正确但未核实的内容是什么？
- 缺失的利益相关者/受众/用户——除当前上下文外，还有谁需要这项成果？
- 被忽略的约束条件——未提及的技术、监管、资源限制
- 被否决的替代方案——曾考虑但被放弃的路径；简要重新审视
- 外部因素——未纳入范围的时间、市场、依赖关系
3. Reflective Inquiry
3. 反思式探究
- Is the problem framed correctly?
- Solving the right problem vs. an adjacent easier one?
- Simpler path being overcomplicated?
- Harder but more valuable path being avoided?
- Fresh-eyes perspective: would someone else approach this differently?
- 问题的框架是否正确？
- 我们是在解决正确的问题，还是一个相邻的更简单问题？
- 是否将简单路径复杂化了？
- 是否在回避更困难但更有价值的路径？
- 旁观者视角: 其他人会以不同方式处理这个问题吗？
4. Bias Check
4. 偏见检查
Five biases — recognize each through specific conversation patterns:
| Bias | Recognition cue |
|---|---|
| Confirmation bias | Evidence cited only supports the working hypothesis; counter-evidence absent or dismissed |
| Sunk cost fallacy | "We've already invested X" / "we're far enough in to..." instead of fresh cost/benefit |
| Anchoring | Stuck on first option mentioned; new options compared against it rather than evaluated independently |
| Complexity bias | Adding features / steps / safeguards without specific justification for each |
| Recency bias | Over-weighting last few turns; older but important context being ignored |
For each detected bias: name it, cite the specific evidence, suggest a corrective move.
See for the full canon.
references/cognitive_bias_canon.md五种偏见——通过对话中的特定模式识别：
| 偏见 | 识别线索 |
|---|---|
| 确认偏差 | 仅引用支持当前假设的证据；未提及或否定相反证据 |
| 沉没成本谬误 | 以“我们已经投入了X”/“我们已经进行到这个阶段了”为由，而非重新进行成本/收益分析 |
| 锚定效应 | 局限于第一个提到的选项；新选项仅与该选项对比，而非独立评估 |
| 复杂性偏差 | 无具体理由地添加功能/步骤/保障措施 |
| 近因偏差 | 过度重视最近几轮对话；忽略早期但重要的上下文 |
对于检测到的每种偏见：指明其名称，引用对话中的具体证据，并提出纠正措施。
详见 中的完整偏见规范。
references/cognitive_bias_canon.md5. Contextual Alignment
5. 上下文对齐
- Does the direction serve the user's actual goals (as known from context)?
- Are external factors being ignored?
- Is this the best use of the user's time and energy right now?
- Connection to other known projects or priorities?
- 当前方向是否符合用户的实际目标（从上下文可知的目标）？
- 是否忽略了外部因素？
- 这是否是当前用户时间和精力的最佳利用方式？
- 与其他已知项目或优先级的关联是什么？
Tone and Format Rules
语气与格式规则
The skill must produce:
- Flowing prose — no headers, no bullet lists, no structured-report formatting
- Tight but thorough — neither a one-liner nor a wall of text
- Direct critique when warranted — with specific evidence from the conversation
- Validation when warranted — with specific reasoning for why the path is solid
- No vague reassurance — "looks good!" without reasoning is rejected
- No manufactured problems — when the path is genuinely solid, say so with specific reasons; don't invent issues
See for the anti-manufactured-problems framing.
references/honest_output_discipline.md该Skill的输出必须满足：
- 流畅的散文式表达——无标题、无项目符号、无结构化报告格式
- 简洁但全面——既不是一句话总结，也不是冗长的文字墙
- 必要时直接提出批评——结合对话中的具体证据
- 必要时给出认可——说明路径可靠的具体理由
- 无模糊的安慰——仅说“看起来不错！”但无理由的输出会被拒绝
- 无虚构问题——当路径确实可靠时，明确说明并给出具体理由；不要编造问题
详见 中的反虚构问题框架。
references/honest_output_discipline.mdClosing Recommendation (Mandatory)
收尾建议（必填）
Every run ends with one of three directional recommendations:
| Recommendation | When | Format |
|---|---|---|
| Continue | Path is solid | "Continue. {specific reasoning for why}." |
| Pivot to {X} | Drift has occurred OR better path surfaced | "Pivot toward {X}, away from {what to drop}. {specific evidence}." |
| Pause for {Q} | A specific question needs answering before continuing | "Pause for {Q}. Without answering this, the next step risks {specific cost}." |
The closing is always specific — never "you should think more about this" or "consider your options."
每次执行都必须以以下三种方向性建议之一结尾：
| 建议类型 | 适用场景 | 格式 |
|---|---|---|
| 继续 | 当前路径可靠 | "继续当前方向。{具体理由}。" |
| 转向{X} | 出现偏离或发现更优路径 | "转向{X}，放弃{当前需停止的内容}。{具体证据}。" |
| 暂停以解决{Q} | 需先解答特定问题才能继续 | "暂停以解决{Q}。若不解答该问题，下一步可能会面临{具体风险}。" |
收尾建议必须具体——绝不能是“你应该多想想这个”或“考虑你的选项”。
Error Handling
错误处理
| Situation | Behavior |
|---|---|
| Conversation is very short (no real context to reassess) | Acknowledge limitation, ask user what they want reassessed (Q1 fires) |
| Current direction is genuinely solid | State this clearly with reasoning; don't manufacture problems |
| User invokes mid-task with no clear question | Default to macro perspective + bias check; offer to dig deeper |
| Implicit trigger seems possible but unclear | Don't invoke proactively; ask user if they want to step back |
| 场景 | 处理方式 |
|---|---|
| 对话非常简短（无足够重评估的上下文） | 说明局限性，询问用户想要重评估的内容（触发Q1） |
| 当前方向确实可靠 | 明确说明并给出理由；不要虚构问题 |
| 用户在任务中途调用但未提出明确问题 | 默认进行宏观视角+偏见检查，并提出可深入分析的选项 |
| 疑似存在隐式信号但不明确 | 不要主动触发；询问用户是否想要退一步审视 |
Tooling
工具支持
| Script | Role |
|---|---|
| Scan conversation text for patterns indicative of each of the 5 biases |
| Count turns + detect implicit-trigger signals (10+ detail turns, frustration markers) |
| Verify output ends with Continue / Pivot / Pause + specific reasoning |
| 脚本 | 作用 |
|---|---|
| 扫描对话文本，识别五种偏见对应的模式 |
| 统计对话轮数+检测隐式触发信号（10轮以上细节对话、沮丧标记） |
| 验证输出是否以继续/转向/暂停结尾，并包含具体理由 |
References
参考资料
- — 5 biases + recognition cues (7+ sources)
references/cognitive_bias_canon.md - — anti-manufactured-problems framing (7+ sources)
references/honest_output_discipline.md - — Schön reflective-practice canon (7+ sources)
references/conversation_reflection_practice.md
- — 五种偏见+识别线索（7+来源）
references/cognitive_bias_canon.md - — 反虚构问题框架（7+来源）
references/honest_output_discipline.md - — Schön反思实践规范（7+来源）
references/conversation_reflection_practice.md
Anti-Patterns To Reject
需避免的反模式
- Hardcoded user names or specific domain references
- Structured-report output (headers, bullet lists) when prose is required
- Manufactured problems when things are actually fine
- Vague reassurance ("looks good!") instead of specific reasoning
- Reassessing only recent turns instead of the full conversation
- Skipping the closing directional recommendation
- Continuing the in-progress task while "reflecting on the side"
Version: 1.0.0
Source spec:
Build pattern: Path B (direct conversion). Productivity light-prompt-flow sibling of capture.
megaprompts/02-reflect-megaprompt.md- 硬编码用户名或特定领域引用
- 需散文式表达时使用结构化报告格式（标题、项目符号）
- 当情况良好时虚构问题
- 用模糊的安慰（“看起来不错！”）代替具体理由
- 仅重评估最近几轮对话而非完整对话
- 省略收尾方向性建议
- “边反思边继续”当前任务
版本: 1.0.0
源规范:
构建模式: Path B（直接转换）。与capture并列的轻量生产力提示流Skill。
megaprompts/02-reflect-megaprompt.md