Back to Details

advanced-elicitation

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Advanced Elicitation

高级启发式推理

Overview

概述

Meta-cognitive reasoning applied to AI outputs. Makes AI reconsider its own work through 15+ systematic methods.
Core Principle: First-pass responses are often good but not great. Elicitation forces deeper thinking.
将元认知推理应用于AI输出。通过15种以上的系统化方法让AI重新审视自身的工作成果。
核心原则：首次生成的响应通常不错但不够出色。启发法会促使AI进行更深入的思考。

When to Use

使用场景

Use when:
  • Making important decisions (architecture, security, major features)
  • Solving complex problems (multiple stakeholders, unclear requirements)
  • Producing critical outputs (specs, plans, designs)
  • Quality matters more than speed
Don't use when:
  • Simple queries ("What is X?")
  • Routine tasks (formatting, simple refactoring)
  • Time-sensitive (emergency fixes)
  • Budget-constrained (2x cost)
适用场景：
  • 做出重要决策（架构、安全、核心功能）
  • 解决复杂问题（多方干系人、需求不明确）
  • 生成关键输出（规格说明、计划、设计方案）
  • 质量优先于速度的场景
不适用场景：
  • 简单查询（如“X是什么？”）
  • 常规任务（格式调整、简单重构）
  • 时间敏感场景（紧急修复）
  • 预算受限场景（成本翻倍）

How It Works

工作原理

  1. Generate Initial Response: Agent produces first-pass answer
  2. Apply Elicitation Method: Pick 1-3 methods based on context
  3. Reconsider: Agent re-evaluates using method
  4. Synthesize: Combine insights, produce improved output
  1. 生成初始响应：Agent生成首次输出结果
  2. 应用启发式方法：根据上下文选择1-3种方法
  3. 重新审视：Agent使用选定方法重新评估初始响应
  4. 综合优化：整合新见解，生成改进后的输出

Elicitation Methods

启发式方法

1. First Principles Thinking

1. 第一性原理思考

Description: Break down to fundamental truths, rebuild reasoning from ground up
When to Use:
  • Complex system design
  • Architecture decisions
  • Innovation challenges
Prompt Template:
You are applying First Principles Thinking to:

---
{content}
---

Steps:
1. List all underlying assumptions
2. Question each assumption: "Is this fundamentally true?"
3. Identify fundamental truths (cannot be broken down further)
4. Rebuild solution from fundamentals only
5. Compare rebuilt solution to original - what changed?

Output:
说明：拆解至最基础的事实，从底层重构推理过程
适用场景：
  • 复杂系统设计
  • 架构决策
  • 创新挑战
提示模板：
You are applying First Principles Thinking to:

---
{content}
---

Steps:
1. List all underlying assumptions
2. Question each assumption: "Is this fundamentally true?"
3. Identify fundamental truths (cannot be broken down further)
4. Rebuild solution from fundamentals only
5. Compare rebuilt solution to original - what changed?

Output:

First Principles Analysis

First Principles Analysis

Fundamental Truths:
  • [Truth 1]
  • [Truth 2]
Assumptions Challenged:
  1. [Assumption] - [Why it might be wrong]
Improvements:
  • [Improvement based on fundamentals]
Confidence Level: [HIGH/MEDIUM/LOW]

---
Fundamental Truths:
  • [Truth 1]
  • [Truth 2]
Assumptions Challenged:
  1. [Assumption] - [Why it might be wrong]
Improvements:
  • [Improvement based on fundamentals]
Confidence Level: [HIGH/MEDIUM/LOW]

---

2. Pre-Mortem Analysis

2. 事前验尸分析

Description: Imagine the solution failed. Work backward to identify causes.
When to Use:
  • Planning major changes
  • Risk mitigation
  • Launch preparations
Prompt Template:
You are applying Pre-Mortem Analysis to:

---
{content}
---

Steps:
1. Fast-forward 6 months: the solution has failed spectacularly
2. List 5 reasons why it failed
3. For each reason, assess likelihood (Low/Medium/High)
4. For each high-likelihood failure, propose mitigation
5. Revise original solution with mitigations

Output:
说明：假设解决方案已失败，反向推导失败原因。
适用场景：
  • 重大变更规划
  • 风险缓解
  • 上线准备
提示模板：
You are applying Pre-Mortem Analysis to:

---
{content}
---

Steps:
1. Fast-forward 6 months: the solution has failed spectacularly
2. List 5 reasons why it failed
3. For each reason, assess likelihood (Low/Medium/High)
4. For each high-likelihood failure, propose mitigation
5. Revise original solution with mitigations

Output:

Pre-Mortem Analysis

Pre-Mortem Analysis

Failure Scenarios:
  1. [Scenario] - Likelihood: [L/M/H]
  2. [Scenario] - Likelihood: [L/M/H]
Mitigations:
  • [Mitigation for high-likelihood failures]
Revised Solution:
  • [Changes to prevent failures]
Confidence Level: [HIGH/MEDIUM/LOW]

---
Failure Scenarios:
  1. [Scenario] - Likelihood: [L/M/H]
  2. [Scenario] - Likelihood: [L/M/H]
Mitigations:
  • [Mitigation for high-likelihood failures]
Revised Solution:
  • [Changes to prevent failures]
Confidence Level: [HIGH/MEDIUM/LOW]

---

3. Socratic Questioning

3. 苏格拉底式提问

Description: Challenge every assumption with "why?" until reaching bedrock.
When to Use:
  • Requirements analysis
  • Specification review
  • Clarifying ambiguity
Prompt Template:
You are applying Socratic Questioning to:

---
{content}
---

Steps:
1. Identify 5 key claims in the content
2. For each claim, ask "Why is this true?"
3. For the answer, ask "Why?" again
4. Repeat until you hit a contradiction or fundamental truth
5. Revise claims that don't survive questioning

Output:
说明：用“为什么？”质疑每一个假设，直至触及核心本质。
适用场景：
  • 需求分析
  • 规格说明评审
  • 消除歧义
提示模板：
You are applying Socratic Questioning to:

---
{content}
---

Steps:
1. Identify 5 key claims in the content
2. For each claim, ask "Why is this true?"
3. For the answer, ask "Why?" again
4. Repeat until you hit a contradiction or fundamental truth
5. Revise claims that don't survive questioning

Output:

Socratic Analysis

Socratic Analysis

Claim 1: [Claim]
  • Why? [Answer]
  • Why? [Answer]
  • Why? [Answer]
  • Verdict: [Survives/Needs revision]
Improvements:
  • [Changes after questioning]
Confidence Level: [HIGH/MEDIUM/LOW]

---
Claim 1: [Claim]
  • Why? [Answer]
  • Why? [Answer]
  • Why? [Answer]
  • Verdict: [Survives/Needs revision]
Improvements:
  • [Changes after questioning]
Confidence Level: [HIGH/MEDIUM/LOW]

---

4. Red Team vs Blue Team

4. 红队vs蓝队分析

Description: Attack the solution (Red Team), defend it (Blue Team), synthesize improvements.
When to Use:
  • Security reviews
  • Risk assessment
  • Adversarial testing
Prompt Template:
You are applying Red Team vs Blue Team to:

---
{content}
---

Steps:
1. **Red Team**: List 5 ways to attack/break this solution
2. **Blue Team**: For each attack, propose a defense
3. **Red Team**: For each defense, find the weakness
4. **Blue Team**: Strengthen defenses
5. Synthesize: What changes make the solution more robust?

Output:
说明：攻击解决方案（红队）、防御解决方案（蓝队），综合优化改进点。
适用场景：
  • 安全评审
  • 风险评估
  • 对抗性测试
提示模板：
You are applying Red Team vs Blue Team to:

---
{content}
---

Steps:
1. **Red Team**: List 5 ways to attack/break this solution
2. **Blue Team**: For each attack, propose a defense
3. **Red Team**: For each defense, find the weakness
4. **Blue Team**: Strengthen defenses
5. Synthesize: What changes make the solution more robust?

Output:

Red Team vs Blue Team

Red Team vs Blue Team

Attack 1: [How to break it]
  • Defense: [Blue team response]
  • Counter-attack: [Red team finds weakness]
  • Final defense: [Blue team strengthens]
Improvements:
  • [Robust changes from adversarial testing]
Confidence Level: [HIGH/MEDIUM/LOW]

---
Attack 1: [How to break it]
  • Defense: [Blue team response]
  • Counter-attack: [Red team finds weakness]
  • Final defense: [Blue team strengthens]
Improvements:
  • [Robust changes from adversarial testing]
Confidence Level: [HIGH/MEDIUM/LOW]

---

5. Inversion

5. 逆向思维

Description: Instead of "How to succeed?", ask "How to fail?" and avoid those.
When to Use:
  • Risk identification
  • Avoiding common pitfalls
  • Negative space analysis
Prompt Template:
You are applying Inversion to:

---
{content}
---

Steps:
1. Invert the goal: "How could we make this FAIL?"
2. List 5 ways to guarantee failure
3. For each failure mode, identify the opposite (success mode)
4. Check if original solution addresses success modes
5. Revise to explicitly avoid failure modes

Output:
说明：不问“如何成功？”，而是问“如何失败？”，然后避免这些情况。
适用场景：
  • 风险识别
  • 规避常见陷阱
  • 负面空间分析
提示模板：
You are applying Inversion to:

---
{content}
---

Steps:
1. Invert the goal: "How could we make this FAIL?"
2. List 5 ways to guarantee failure
3. For each failure mode, identify the opposite (success mode)
4. Check if original solution addresses success modes
5. Revise to explicitly avoid failure modes

Output:

Inversion Analysis

Inversion Analysis

How to Fail:
  1. [Failure mode]
  2. [Failure mode]
How to Succeed (inverses):
  1. [Success mode]
Improvements:
  • [Changes to avoid failures]
Confidence Level: [HIGH/MEDIUM/LOW]

---
How to Fail:
  1. [Failure mode]
  2. [Failure mode]
How to Succeed (inverses):
  1. [Success mode]
Improvements:
  • [Changes to avoid failures]
Confidence Level: [HIGH/MEDIUM/LOW]

---

6. Second-Order Thinking

6. 二阶思维

Description: Consider consequences of consequences. Long-term effects.
When to Use:
  • Strategic decisions
  • Long-term planning
  • Trade-off analysis
Prompt Template:
You are applying Second-Order Thinking to:

---
{content}
---

Steps:
1. Identify immediate consequences (1st order)
2. For each consequence, identify follow-on effects (2nd order)
3. For each 2nd order effect, identify further effects (3rd order)
4. Assess whether long-term effects align with goals
5. Revise solution to optimize for 2nd/3rd order effects

Output:
说明：考虑后果的后果，即长期影响。
适用场景：
  • 战略决策
  • 长期规划
  • 权衡分析
提示模板：
You are applying Second-Order Thinking to:

---
{content}
---

Steps:
1. Identify immediate consequences (1st order)
2. For each consequence, identify follow-on effects (2nd order)
3. For each 2nd order effect, identify further effects (3rd order)
4. Assess whether long-term effects align with goals
5. Revise solution to optimize for 2nd/3rd order effects

Output:

Second-Order Analysis

Second-Order Analysis

1st Order: [Immediate effect]
  • 2nd Order: [Consequence of consequence]
    • 3rd Order: [Further consequence]
Long-Term Implications:
  • [Good/Bad long-term effects]
Improvements:
  • [Changes optimizing for long-term]
Confidence Level: [HIGH/MEDIUM/LOW]

---
1st Order: [Immediate effect]
  • 2nd Order: [Consequence of consequence]
    • 3rd Order: [Further consequence]
Long-Term Implications:
  • [Good/Bad long-term effects]
Improvements:
  • [Changes optimizing for long-term]
Confidence Level: [HIGH/MEDIUM/LOW]

---

7. SWOT Analysis

7. SWOT分析

Description: Strengths, Weaknesses, Opportunities, Threats.
When to Use:
  • Strategic planning
  • Competitive analysis
  • Decision-making
Prompt Template:
You are applying SWOT Analysis to:

---
{content}
---

Steps:
1. **Strengths**: What are the advantages?
2. **Weaknesses**: What are the disadvantages?
3. **Opportunities**: What external factors could help?
4. **Threats**: What external factors could harm?
5. Synthesize: How to leverage S+O, mitigate W+T?

Output:
说明：优势、劣势、机会、威胁分析。
适用场景：
  • 战略规划
  • 竞争分析
  • 决策制定
提示模板：
You are applying SWOT Analysis to:

---
{content}
---

Steps:
1. **Strengths**: What are the advantages?
2. **Weaknesses**: What are the disadvantages?
3. **Opportunities**: What external factors could help?
4. **Threats**: What external factors could harm?
5. Synthesize: How to leverage S+O, mitigate W+T?

Output:

SWOT Analysis

SWOT Analysis

Strengths:
  • [Internal advantage]
Weaknesses:
  • [Internal disadvantage]
Opportunities:
  • [External positive factor]
Threats:
  • [External negative factor]
Strategy:
  • [Leverage strengths/opportunities, mitigate weaknesses/threats]
Confidence Level: [HIGH/MEDIUM/LOW]

---
Strengths:
  • [Internal advantage]
Weaknesses:
  • [Internal disadvantage]
Opportunities:
  • [External positive factor]
Threats:
  • [External negative factor]
Strategy:
  • [Leverage strengths/opportunities, mitigate weaknesses/threats]
Confidence Level: [HIGH/MEDIUM/LOW]

---

8. Opportunity Cost Analysis

8. 机会成本分析

Description: What are we NOT doing? What are we giving up?
When to Use:
  • Prioritization
  • Resource allocation
  • Trade-off decisions
Prompt Template:
You are applying Opportunity Cost to:

---
{content}
---

Steps:
1. List what this solution requires (time, money, people)
2. List 3 alternative uses for those resources
3. For each alternative, estimate value
4. Compare: Is this solution the highest-value use?
5. If not, propose reallocation

Output:
说明：我们放弃了什么？我们没有做的事情是什么？
适用场景：
  • 优先级排序
  • 资源分配
  • 权衡决策
提示模板：
You are applying Opportunity Cost to:

---
{content}
---

Steps:
1. List what this solution requires (time, money, people)
2. List 3 alternative uses for those resources
3. For each alternative, estimate value
4. Compare: Is this solution the highest-value use?
5. If not, propose reallocation

Output:

Opportunity Cost Analysis

Opportunity Cost Analysis

Resources Required:
  • [Time/Money/People]
Alternatives:
  1. [Alternative use] - Estimated value: [X]
  2. [Alternative use] - Estimated value: [Y]
Verdict:
  • [Is this the best use? Why/why not?]
Improvements:
  • [Reallocations or justifications]
Confidence Level: [HIGH/MEDIUM/LOW]

---
Resources Required:
  • [Time/Money/People]
Alternatives:
  1. [Alternative use] - Estimated value: [X]
  2. [Alternative use] - Estimated value: [Y]
Verdict:
  • [Is this the best use? Why/why not?]
Improvements:
  • [Reallocations or justifications]
Confidence Level: [HIGH/MEDIUM/LOW]

---

9. Analogical Reasoning

9. 类比推理

Description: How have others solved similar problems? Learn from analogies.
When to Use:
  • Innovation
  • Learning from history
  • Cross-domain insights
Prompt Template:
You are applying Analogical Reasoning to:

---
{content}
---

Steps:
1. Identify the core problem (abstract it)
2. Find 3 analogous situations (other domains/times)
3. How was the analogous problem solved?
4. What lessons transfer to this situation?
5. Adapt the solution based on analogies

Output:
说明：他人如何解决类似问题？从类比中学习。
适用场景：
  • 创新
  • 从历史中学习
  • 跨领域洞察
提示模板：
You are applying Analogical Reasoning to:

---
{content}
---

Steps:
1. Identify the core problem (abstract it)
2. Find 3 analogous situations (other domains/times)
3. How was the analogous problem solved?
4. What lessons transfer to this situation?
5. Adapt the solution based on analogies

Output:

Analogical Analysis

Analogical Analysis

Core Problem: [Abstract problem statement]
Analogy 1: [Domain/situation]
  • How they solved it: [Solution]
  • Lesson: [What transfers]
Improvements:
  • [Adapted solution from analogies]
Confidence Level: [HIGH/MEDIUM/LOW]

---
Core Problem: [Abstract problem statement]
Analogy 1: [Domain/situation]
  • How they solved it: [Solution]
  • Lesson: [What transfers]
Improvements:
  • [Adapted solution from analogies]
Confidence Level: [HIGH/MEDIUM/LOW]

---

10. Constraint Relaxation

10. 约束松弛法

Description: What if constraint X didn't exist? How would that change the solution?
When to Use:
  • Innovation
  • Breaking assumptions
  • Finding creative solutions
Prompt Template:
You are applying Constraint Relaxation to:

---
{content}
---

Steps:
1. List all constraints (explicit and implicit)
2. For each constraint, ask: "What if this wasn't true?"
3. Design solution without that constraint
4. Assess: Can we actually relax this constraint?
5. If yes, propose new solution. If no, learn from the thought experiment.

Output:
说明：如果约束X不存在会怎样？这会如何改变解决方案？
适用场景：
  • 创新
  • 打破假设
  • 寻找创造性解决方案
提示模板：
You are applying Constraint Relaxation to:

---
{content}
---

Steps:
1. List all constraints (explicit and implicit)
2. For each constraint, ask: "What if this wasn't true?"
3. Design solution without that constraint
4. Assess: Can we actually relax this constraint?
5. If yes, propose new solution. If no, learn from the thought experiment.

Output:

Constraint Relaxation

Constraint Relaxation

Constraint: [Constraint]
  • If removed: [Solution without constraint]
  • Can we actually relax it? [Yes/No + reasoning]
Improvements:
  • [Creative solutions from relaxation]
Confidence Level: [HIGH/MEDIUM/LOW]

---
Constraint: [Constraint]
  • If removed: [Solution without constraint]
  • Can we actually relax it? [Yes/No + reasoning]
Improvements:
  • [Creative solutions from relaxation]
Confidence Level: [HIGH/MEDIUM/LOW]

---

11. Failure Modes and Effects Analysis (FMEA)

11. 失效模式与影响分析（FMEA）

Description: What could go wrong? How likely? How bad? Prioritize fixes.
When to Use:
  • Engineering design
  • Risk assessment
  • Safety-critical systems
Prompt Template:
You are applying FMEA to:

---
{content}
---

Steps:
1. List all components/steps in the solution
2. For each, identify potential failure modes
3. Rate each: Severity (1-10), Likelihood (1-10)
4. Calculate Risk Priority Number (RPN = Severity × Likelihood)
5. Address high-RPN failures first

Output:
说明：可能出现哪些问题？发生概率？影响程度？优先修复高风险项。
适用场景：
  • 工程设计
  • 风险评估
  • 安全关键系统
提示模板：
You are applying FMEA to:

---
{content}
---

Steps:
1. List all components/steps in the solution
2. For each, identify potential failure modes
3. Rate each: Severity (1-10), Likelihood (1-10)
4. Calculate Risk Priority Number (RPN = Severity × Likelihood)
5. Address high-RPN failures first

Output:

FMEA

FMEA

Failure Mode 1: [What fails]
  • Severity: [1-10]
  • Likelihood: [1-10]
  • RPN: [Product]
  • Mitigation: [How to prevent/detect/recover]
Improvements:
  • [Prioritized mitigations for high-RPN failures]
Confidence Level: [HIGH/MEDIUM/LOW]

---
Failure Mode 1: [What fails]
  • Severity: [1-10]
  • Likelihood: [1-10]
  • RPN: [Product]
  • Mitigation: [How to prevent/detect/recover]
Improvements:
  • [Prioritized mitigations for high-RPN failures]
Confidence Level: [HIGH/MEDIUM/LOW]

---

12. Bias Check

12. 偏见检查

Description: What cognitive biases might affect this? Correct for them.
When to Use:
  • Decision-making
  • Review processes
  • Self-critique
Prompt Template:
You are applying Bias Check to:

---
{content}
---

Steps:
1. Review common cognitive biases (confirmation, anchoring, sunk cost, availability, etc.)
2. For each bias, ask: "Is this affecting my reasoning?"
3. Find evidence of bias in the original content
4. Correct for identified biases
5. Re-evaluate the solution bias-free

Output:
说明：哪些认知偏见可能影响结果？纠正这些偏见。
适用场景：
  • 决策制定
  • 评审流程
  • 自我批判
提示模板：
You are applying Bias Check to:

---
{content}
---

Steps:
1. Review common cognitive biases (confirmation, anchoring, sunk cost, availability, etc.)
2. For each bias, ask: "Is this affecting my reasoning?"
3. Find evidence of bias in the original content
4. Correct for identified biases
5. Re-evaluate the solution bias-free

Output:

Bias Check

Bias Check

Bias Detected: [Bias name]
  • Evidence: [Where it appears]
  • Correction: [Adjusted reasoning]
Improvements:
  • [Bias-free solution]
Confidence Level: [HIGH/MEDIUM/LOW]

---
Bias Detected: [Bias name]
  • Evidence: [Where it appears]
  • Correction: [Adjusted reasoning]
Improvements:
  • [Bias-free solution]
Confidence Level: [HIGH/MEDIUM/LOW]

---

13. Base Rate Thinking

13. 基础比率思维

Description: What usually happens in similar situations? Are we being overconfident?
When to Use:
  • Estimation
  • Risk assessment
  • Reality-checking optimism
Prompt Template:
You are applying Base Rate Thinking to:

---
{content}
---

Steps:
1. Identify the reference class (similar past situations)
2. What's the base rate (average outcome for reference class)?
3. Why might this case be different?
4. Adjust estimates toward base rate (Bayesian update)
5. Revise solution with realistic expectations

Output:
说明：类似情况下通常会发生什么？我们是否过于自信？
适用场景：
  • 估算
  • 风险评估
  • 乐观预期的现实校验
提示模板：
You are applying Base Rate Thinking to:

---
{content}
---

Steps:
1. Identify the reference class (similar past situations)
2. What's the base rate (average outcome for reference class)?
3. Why might this case be different?
4. Adjust estimates toward base rate (Bayesian update)
5. Revise solution with realistic expectations

Output:

Base Rate Analysis

Base Rate Analysis

Reference Class: [Similar situations]
  • Base Rate: [Typical outcome]
  • Our Estimate: [Original estimate]
  • Adjusted Estimate: [Reality-checked estimate]
Improvements:
  • [More realistic solution]
Confidence Level: [HIGH/MEDIUM/LOW]

---
Reference Class: [Similar situations]
  • Base Rate: [Typical outcome]
  • Our Estimate: [Original estimate]
  • Adjusted Estimate: [Reality-checked estimate]
Improvements:
  • [More realistic solution]
Confidence Level: [HIGH/MEDIUM/LOW]

---

14. Steelmanning

14. 钢人辩论法

Description: What's the strongest version of an opposing view? Address that, not a strawman.
When to Use:
  • Proposal review
  • Debate preparation
  • Intellectual honesty
Prompt Template:
You are applying Steelmanning to:

---
{content}
---

Steps:
1. Identify the opposing view (or alternative approach)
2. Strengthen it: What's the BEST argument against your solution?
3. Address the strong version (not a weak strawman)
4. If the steelman wins, adopt that approach
5. If your solution survives, it's stronger

Output:
说明：对立观点的最强版本是什么？回应这个版本，而非稻草人版本。
适用场景：
  • 提案评审
  • 辩论准备
  • 学术诚实性校验
提示模板：
You are applying Steelmanning to:

---
{content}
---

Steps:
1. Identify the opposing view (or alternative approach)
2. Strengthen it: What's the BEST argument against your solution?
3. Address the strong version (not a weak strawman)
4. If the steelman wins, adopt that approach
5. If your solution survives, it's stronger

Output:

Steelman Analysis

Steelman Analysis

Opposing View: [Alternative]
  • Strongest Argument: [Best case for alternative]
  • Response: [Addressing the strong version]
  • Verdict: [Which approach is better?]
Improvements:
  • [Refined solution after facing steelman]
Confidence Level: [HIGH/MEDIUM/LOW]

---
Opposing View: [Alternative]
  • Strongest Argument: [Best case for alternative]
  • Response: [Addressing the strong version]
  • Verdict: [Which approach is better?]
Improvements:
  • [Refined solution after facing steelman]
Confidence Level: [HIGH/MEDIUM/LOW]

---

15. Time Horizon Shift

15. 时间视野转换

Description: How does this look in 1 hour? 1 day? 1 month? 1 year? 5 years?
When to Use:
  • Long-term planning
  • Trade-off analysis
  • Strategy evaluation
Prompt Template:
You are applying Time Horizon Shift to:

---
{content}
---

Steps:
1. Evaluate solution at 1 hour: [Impact]
2. Evaluate at 1 day: [Impact]
3. Evaluate at 1 month: [Impact]
4. Evaluate at 1 year: [Impact]
5. Evaluate at 5 years: [Impact]
6. Identify time-horizon-dependent trade-offs
7. Optimize for the right time horizon

Output:
说明：1小时后？1天后？1个月后？1年后？5年后？这个方案看起来会如何？
适用场景：
  • 长期规划
  • 权衡分析
  • 战略评估
提示模板：
You are applying Time Horizon Shift to:

---
{content}
---

Steps:
1. Evaluate solution at 1 hour: [Impact]
2. Evaluate at 1 day: [Impact]
3. Evaluate at 1 month: [Impact]
4. Evaluate at 1 year: [Impact]
5. Evaluate at 5 years: [Impact]
6. Identify time-horizon-dependent trade-offs
7. Optimize for the right time horizon

Output:

Time Horizon Analysis

Time Horizon Analysis

1 Hour: [Short-term effect] 1 Day: [Effect] 1 Month: [Effect] 1 Year: [Effect] 5 Years: [Long-term effect]
Trade-Offs:
  • [Short vs long-term conflicts]
Improvements:
  • [Optimized for appropriate horizon]
Confidence Level: [HIGH/MEDIUM/LOW]

---
1 Hour: [Short-term effect] 1 Day: [Effect] 1 Month: [Effect] 1 Year: [Effect] 5 Years: [Long-term effect]
Trade-Offs:
  • [Short vs long-term conflicts]
Improvements:
  • [Optimized for appropriate horizon]
Confidence Level: [HIGH/MEDIUM/LOW]

---

Usage Patterns

使用模式

Pattern 1: Single Method (Quick)

模式1：单一方法（快速）

javascript
Skill({ skill: 'advanced-elicitation', args: 'first-principles' });
javascript
Skill({ skill: 'advanced-elicitation', args: 'first-principles' });

Pattern 2: Multiple Methods (Thorough)

模式2：多种方法（全面）

javascript
Skill({ skill: 'advanced-elicitation', args: 'first-principles,pre-mortem,red-team-blue-team' });
javascript
Skill({ skill: 'advanced-elicitation', args: 'first-principles,pre-mortem,red-team-blue-team' });

Pattern 3: Auto-Select (Recommended)

模式3：自动选择（推荐）

javascript
Skill({ skill: 'advanced-elicitation', args: 'auto' });
// Automatically picks 2-3 methods based on content analysis
javascript
Skill({ skill: 'advanced-elicitation', args: 'auto' });
// 基于内容分析自动选择2-3种方法

Integration with spec-critique

与spec-critique的集成

Advanced Elicitation can enhance spec-critique:
javascript
// After generating spec
Skill({ skill: 'spec-critique', args: 'with-elicitation' });
// Applies elicitation to critique process
高级启发式推理可以增强spec-critique的能力：
javascript
// 生成规格说明后
Skill({ skill: 'spec-critique', args: 'with-elicitation' });
// 在评审过程中应用启发式推理

Cost Control (per ADR-053)

成本控制（依据ADR-053）

  • Opt-in only: Never applied automatically
  • Budget limit: Configurable via ELICITATION_BUDGET_LIMIT
  • Cost tracking: Integrates with cost-tracking hook
Config:
yaml
features:
  advancedElicitation:
    enabled: true
    costBudget: 10.0 # USD per session
    minConfidence: 0.7 # Skip if confidence high
    maxMethodsPerInvocation: 5 # SEC-AE-001
    maxInvocationsPerSession: 10 # SEC-AE-003
  • 仅可主动启用：绝不会自动应用
  • 预算限制：可通过ELICITATION_BUDGET_LIMIT配置
  • 成本追踪：与成本追踪钩子集成
配置:
yaml
features:
  advancedElicitation:
    enabled: true
    costBudget: 10.0 # 每次会话美元上限
    minConfidence: 0.7 # 若置信度高则跳过
    maxMethodsPerInvocation: 5 # SEC-AE-001
    maxInvocationsPerSession: 10 # SEC-AE-003

Security Controls

安全控制

SEC-AE-001: Input Validation
  • Method names must match 
    /^[a-z][a-z0-9-]*$/
  • Max 5 methods per invocation
  • Invalid methods rejected with error
SEC-AE-002: Cost Budget Enforcement
  • Check session budget before elicitation
  • Track cumulative cost
  • Fail gracefully if budget exceeded
SEC-AE-003: Rate Limiting
  • Max 10 elicitations per session
  • Prevent runaway elicitation loops
  • Clear error message on limit
SEC-AE-001：输入验证
  • 方法名称必须匹配正则表达式
    /^[a-z][a-z0-9-]*$/
  • 每次调用最多使用5种方法
  • 无效方法会被拒绝并返回错误
SEC-AE-002：成本预算强制执行
  • 在执行启发式推理前检查会话预算
  • 追踪累计成本
  • 若预算超支则优雅终止
SEC-AE-003：速率限制
  • 每个会话最多执行10次启发式推理
  • 防止出现失控的启发式推理循环
  • 达到限制时返回清晰的错误信息

Examples

示例

Example 1: Architecture Decision

示例1：架构决策

Before Elicitation:
We should use microservices with 12 services communicating via REST.
After First Principles:
Fundamental truths: Services must communicate, data must be consistent.
Challenged assumption: "12 services" - is this the right granularity?
Could 6 bounded contexts suffice?

Improvement: Consolidate to 6-8 services by bounded context.
Use gRPC internally (40% latency reduction vs REST).
启发式推理前：
我们应采用微服务架构，包含12个通过REST通信的服务。
第一性原理分析后：
基础事实：服务必须通信，数据必须保持一致。
被挑战的假设：“12个服务”——这个粒度是否合适？
是否可以用6个限界上下文来替代？

优化方案：按限界上下文合并为6-8个服务。
内部使用gRPC（相比REST延迟降低40%）。

Example 2: Security Review

示例2：安全评审

Before Elicitation:
JWT tokens for authentication across services.
After Red Team/Blue Team:
Red Team Attack: Token theft via XSS, JWT validation on every call (latency).
Blue Team Defense: HttpOnly cookies, service mesh mTLS instead of JWT propagation.

Improvement: Use service mesh (Istio) for security instead of JWT propagation.
启发式推理前：
跨服务认证使用JWT令牌。
红队vs蓝队分析后：
红队攻击手段：通过XSS窃取令牌，每次调用都验证JWT（存在延迟问题）。
蓝队防御方案：使用HttpOnly Cookie，服务网格mTLS替代JWT传播。

优化方案：使用服务网格（Istio）实现安全，而非JWT传播。

Example 3: Spec Validation

示例3：规格说明验证

Before Elicitation:
Feature: User can delete their account.
After Pre-Mortem:
Failure Scenario: 6 months later, GDPR compliance audit fails.
Cause: Deletion didn't cascade to all systems (analytics, backups).

Improvement: Add "Data Retention Audit" requirement.
Specify cascade delete to all systems within 30 days.
启发式推理前：
功能：用户可删除自己的账户。
事前验尸分析后：
失败场景：6个月后，GDPR合规审计未通过。
原因：删除操作未同步至所有系统（分析、备份）。

优化方案：添加“数据保留审计”要求。
明确规定需在30天内完成所有系统的级联删除。

Performance

性能表现

  • Quality Improvement: +30% (measured on critical decisions)
  • Cost: 2x LLM usage
  • Time: +50% (worth it for important work)
  • 质量提升：+30%（基于关键决策的测量结果）
  • 成本：LLM使用量翻倍
  • 耗时：增加50%（对重要工作而言物有所值）

Memory Protocol (MANDATORY)

内存协议（强制要求）

Before starting:
bash
cat .claude/context/memory/learnings.md
After completing:
  • New pattern → 
    .claude/context/memory/learnings.md
  • Issue found → 
    .claude/context/memory/issues.md
  • Decision made → 
    .claude/context/memory/decisions.md
ASSUME INTERRUPTION: If it's not in memory, it didn't happen.
开始前：
bash
cat .claude/context/memory/learnings.md
完成后：
  • 新模式 → 写入
    .claude/context/memory/learnings.md
  • 发现问题 → 写入
    .claude/context/memory/issues.md
  • 做出决策 → 写入
    .claude/context/memory/decisions.md
假设会被中断：若未存入内存，则视为未发生。

Related Skills

相关技能

  • spec-critique
    - Specification validation (can invoke elicitation)
  • security-architect
    - Security reviews (can use elicitation methods)
  • verification-before-completion
    - Pre-completion checks
  • spec-critique
    - 规格说明验证（可调用启发式推理）
  • security-architect
    - 安全评审（可使用启发式推理方法）
  • verification-before-completion
    - 完成前验证

Assigned Agents

可使用该技能的Agent

This skill can be used by:
  • planner
    - For strategic decisions
  • architect
    - For architecture review
  • security-architect
    - For threat modeling
  • developer
    - For complex technical decisions
  • pm
    - For product strategy
Version: 1.0.0 Status: Production Author: developer agent (Task #6) Date: 2026-01-28
该技能可由以下Agent使用：
  • planner
    - 用于战略决策
  • architect
    - 用于架构评审
  • security-architect
    - 用于威胁建模
  • developer
    - 用于复杂技术决策
  • pm
    - 用于产品策略
版本：1.0.0 状态：已投产 作者：开发者Agent（任务#6） 日期：2026-01-28