Back to Details

stanley-druckenmiller-investment

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Druckenmiller Strategy Synthesizer

Druckenmiller策略合成器

Purpose

用途

Synthesize outputs from 8 upstream analysis skills (5 required + 3 optional) into a single composite conviction score (0-100), classify the market into one of 4 Druckenmiller patterns, and generate actionable allocation recommendations. This is a meta-skill that consumes structured JSON outputs from other skills — it requires no API keys of its own.
将8项上游分析技能（5项必填+3项可选）的输出整合为单一的综合信心评分（0-100），将市场归类为4种Druckenmiller模式之一，并生成可执行的配置建议。这是一项元技能，会调用其他技能生成的结构化JSON输出——自身无需API密钥。

When to Use This Skill

何时使用此技能

English:
  • User asks "What's my overall conviction?" or "How should I be positioned?"
  • User wants a unified view synthesizing breadth, uptrend, top risk, macro, and FTD signals
  • User asks about Druckenmiller-style portfolio positioning
  • User requests strategy synthesis after running individual analysis skills
  • User asks "Should I increase or decrease exposure?"
  • User wants pattern classification (policy pivot, distortion, contrarian, wait)
Japanese:
  • 「総合的な市場判断は？」「今のポジショニングは？」
  • ブレッドス、アップトレンド、天井リスク、マクロの統合判断
  • 「エクスポージャーを増やすべき？減らすべき？」
  • 「ドラッケンミラー分析を実行して」
  • 個別スキル実行後の戦略統合レポート
英文场景：
  • 用户询问“我的整体信心如何？”或“我应该如何布局？”
  • 用户需要整合广度、上涨趋势、顶部风险、宏观和FTD信号的统一视图
  • 用户询问Druckenmiller风格的投资组合定位
  • 用户在运行单个分析技能后请求策略合成
  • 用户询问“我应该增加还是减少敞口？”
  • 用户需要模式分类（政策转向、扭曲、逆向、观望）
日文场景：
  • 「総合的な市場判断は？」「今のポジショニングは？」
  • ブレッドス、アップトレンド、天井リスク、マクロの統合判断
  • 「エクスポージャーを増やすべき？減らすべき？」
  • 「ドラッケンミラー分析を実行して」
  • 個別スキル実行後の戦略統合レポート

Input Requirements

输入要求

Required Skills (5)

必填技能（5项）

#SkillJSON PrefixRole
1Market Breadth Analyzer
market_breadth_
Market participation breadth
2Uptrend Analyzer
uptrend_analysis_
Sector uptrend ratios
3Market Top Detector
market_top_
Distribution / top risk (defense)
4Macro Regime Detector
macro_regime_
Macro regime transition (1-2Y structure)
5FTD Detector
ftd_detector_
Bottom confirmation / re-entry (offense)
序号技能JSON前缀作用
1Market Breadth Analyzer
market_breadth_
市场参与广度
2Uptrend Analyzer
uptrend_analysis_
行业上涨趋势比率
3Market Top Detector
market_top_
派发/顶部风险（防御）
4Macro Regime Detector
macro_regime_
宏观 regime 转换（1-2年结构）
5FTD Detector
ftd_detector_
底部确认/重新入场（进攻）

Optional Skills (3)

可选技能（3项）

#SkillJSON PrefixRole
6VCP Screener
vcp_screener_
Momentum stock setups (VCP)
7Theme Detector
theme_detector_
Theme / sector momentum
8CANSLIM Screener
canslim_screener_
Growth stock setups + M(Market Direction)
Run the required skills first. The synthesizer reads their JSON output from 
reports/
.
序号技能JSON前缀作用
6VCP Screener
vcp_screener_
动量股票形态（VCP）
7Theme Detector
theme_detector_
主题/行业动量
8CANSLIM Screener
canslim_screener_
成长股形态 + M(市场方向)
先运行必填技能。合成器会从
reports/
目录读取它们的JSON输出。

Execution Workflow

执行流程

Phase 1: Verify Prerequisites

阶段1：验证前置条件

Check that the 5 required skill JSON reports exist in 
reports/
and are recent (< 72 hours). If any are missing, run the corresponding skill first.
检查
reports/
目录中是否存在5项必填技能的JSON报告，且报告为近期生成（<72小时）。若有缺失，先运行对应的技能。

Phase 2: Execute Strategy Synthesizer

阶段2：执行策略合成器

bash
python3 skills/stanley-druckenmiller-investment/scripts/strategy_synthesizer.py \
  --reports-dir reports/ \
  --output-dir reports/ \
  --max-age 72
The script will:
  1. Load and validate all upstream skill JSON reports
  2. Extract normalized signals from each skill
  3. Calculate 7 component scores (weighted 0-100)
  4. Compute composite conviction score
  5. Classify into one of 4 Druckenmiller patterns
  6. Generate target allocation and position sizing
  7. Output JSON and Markdown reports
bash
python3 skills/stanley-druckenmiller-investment/scripts/strategy_synthesizer.py \
  --reports-dir reports/ \
  --output-dir reports/ \
  --max-age 72
该脚本将：
  1. 加载并验证所有上游技能的JSON报告
  2. 从每个技能中提取标准化信号
  3. 计算7项组件得分（加权0-100）
  4. 计算综合信心评分
  5. 归类为4种Druckenmiller模式之一
  6. 生成目标配置和仓位规模
  7. 输出JSON和Markdown报告

Phase 3: Present Results

阶段3：展示结果

Present the generated Markdown report, highlighting:
  • Conviction score and zone
  • Detected pattern and match strength
  • Strongest and weakest components
  • Target allocation (equity/bonds/alternatives/cash)
  • Position sizing parameters
  • Relevant Druckenmiller principle
展示生成的Markdown报告，重点突出：
  • 信心评分及区间
  • 检测到的模式和匹配强度
  • 最强和最弱的组件
  • 目标配置（股票/债券/另类资产/现金）
  • 仓位规模参数
  • 相关的Druckenmiller原则

Phase 4: Provide Druckenmiller Context

阶段4：提供Druckenmiller背景

Load appropriate reference documents to provide philosophical context:
  • High conviction: Emphasize concentration and "fat pitch" principles
  • Low conviction: Emphasize capital preservation and patience
  • Pattern-specific: Apply relevant case study from 
    references/case-studies.md
加载合适的参考文档以提供理念背景：
  • 高信心： 强调集中投资和“好球区”原则
  • 低信心： 强调资本保全和耐心
  • 特定模式： 应用
    references/case-studies.md
    中的相关案例研究

7-Component Scoring System

7项组件评分系统

#ComponentWeightSource Skill(s)Key Signal
1Market Structure18%Breadth + UptrendMarket participation health
2Distribution Risk18%Market Top (inverted)Institutional selling risk
3Bottom Confirmation12%FTD DetectorRe-entry signal after correction
4Macro Alignment18%Macro RegimeRegime favorability
5Theme Quality12%Theme DetectorSector momentum health
6Setup Availability10%VCP + CANSLIMQuality stock setups
7Signal Convergence12%All 5 requiredCross-skill agreement
序号组件权重来源技能关键信号
1市场结构18%Breadth + Uptrend市场参与健康度
2派发风险18%Market Top（反向）机构抛售风险
3底部确认12%FTD Detector回调后的重新入场信号
4宏观对齐18%Macro RegimeRegime 利好程度
5主题质量12%Theme Detector行业动量健康度
6形态可用性10%VCP + CANSLIM优质股票形态
7信号收敛12%所有5项必填技能跨技能一致性

4 Pattern Classifications

4种模式分类

PatternTrigger ConditionsDruckenmiller Principle
Policy Pivot AnticipationTransitional regime + high transition probability"Focus on central banks and liquidity"
Unsustainable DistortionTop risk >= 60 + contraction/inflationary regime"How much you lose when wrong matters most"
Extreme Sentiment ContrarianFTD confirmed + high top risk + bearish breadth"Most money made in bear markets"
Wait & ObserveLow conviction + mixed signals (default)"When you don't see it, don't swing"
模式触发条件Druckenmiller原则
政策转向预期过渡性regime + 高转换概率“关注央行和流动性”
不可持续扭曲顶部风险 >=60 + 收缩/通胀regime“犯错时的损失规模才是关键”
极端情绪逆向FTD确认 + 高顶部风险 + 看跌广度“熊市中赚的钱最多”
观望低信心 + 信号混杂（默认）“看不清时不要出手”

Conviction Zone Mapping

信心区间映射

ScoreZoneExposureGuidance
80-100Maximum Conviction90-100%Fat pitch - swing hard
60-79High Conviction70-90%Standard risk management
40-59Moderate Conviction50-70%Reduce position sizes
20-39Low Conviction20-50%Preserve capital, minimal risk
0-19Capital Preservation0-20%Maximum defense
评分区间敞口比例指导建议
80-100极高信心90-100%好球区——全力出击
60-79高信心70-90%标准风险管理
40-59中等信心50-70%降低仓位规模
20-39低信心20-50%保全资本，最小化风险
0-19资本保全0-20%极致防御

Output Files

输出文件

  • druckenmiller_strategy_YYYY-MM-DD_HHMMSS.json
    — Structured analysis data
  • druckenmiller_strategy_YYYY-MM-DD_HHMMSS.md
    — Human-readable report
  • druckenmiller_strategy_YYYY-MM-DD_HHMMSS.json
    — 结构化分析数据
  • druckenmiller_strategy_YYYY-MM-DD_HHMMSS.md
    — 人类可读报告

API Requirements

API要求

None. This skill reads JSON outputs from other skills. No API keys required.
无。此技能读取其他技能的JSON输出，无需API密钥。

Reference Documents

参考文档

references/investment-philosophy.md

references/investment-philosophy.md

  • Core Druckenmiller principles: concentration, capital preservation, 18-month horizon
  • Quantitative rules: daily vol targets, max position sizing
  • Load when providing philosophical context for conviction assessment
  • 核心Druckenmiller原则：集中投资、资本保全、18个月视野
  • 量化规则：每日波动目标、最大仓位规模
  • 提供信心评估的理念背景时加载

references/market-analysis-guide.md

references/market-analysis-guide.md

  • Signal-to-action mapping framework
  • Macro regime interpretation for allocation decisions
  • Load when explaining component scores or allocation rationale
  • 信号到行动的映射框架
  • 用于配置决策的宏观regime解读
  • 解释组件得分或配置理由时加载

references/case-studies.md

references/case-studies.md

  • Historical examples: 1992 GBP, 2000 tech bubble, 2008 crisis
  • Pattern classification examples with actual market conditions
  • Load when user asks about historical parallels
  • 历史案例：1992年英镑危机、2000年科技泡沫、2008年金融危机
  • 结合实际市场情况的模式分类案例
  • 用户询问历史参照时加载

references/conviction_matrix.md

references/conviction_matrix.md

  • Quantitative signal-to-action mapping tables
  • Market Top Zone x Macro Regime matrix
  • Load when user needs precise exposure numbers for specific signal combinations
  • 量化信号到行动的映射表
  • 顶部风险区间 × 宏观Regime矩阵
  • 用户需要特定信号组合的精确敞口数值时加载

When to Load References

何时加载参考文档

  • First use: Load 
    investment-philosophy.md
    for framework understanding
  • Allocation questions: Load 
    market-analysis-guide.md
    + 
    conviction_matrix.md
  • Historical context: Load 
    case-studies.md
  • Regular execution: References not needed — script handles scoring
  • 首次使用： 加载
    investment-philosophy.md
    以理解框架
  • 配置问题： 加载
    market-analysis-guide.md
    + 
    conviction_matrix.md
  • 历史背景： 加载
    case-studies.md
  • 常规执行： 无需参考文档——脚本自动处理评分

Relationship to Other Skills

与其他技能的关系

SkillRelationshipTime Horizon
Market Breadth AnalyzerInput (required)Current snapshot
Uptrend AnalyzerInput (required)Current snapshot
Market Top DetectorInput (required)2-8 weeks tactical
Macro Regime DetectorInput (required)1-2 years structural
FTD DetectorInput (required)Days-weeks event
VCP ScreenerInput (optional)Setup-specific
Theme DetectorInput (optional)Weeks-months thematic
CANSLIM ScreenerInput (optional)Setup-specific
This SkillSynthesizerUnified conviction
技能关系时间视野
Market Breadth Analyzer输入（必填）当前快照
Uptrend Analyzer输入（必填）当前快照
Market Top Detector输入（必填）2-8周战术层面
Macro Regime Detector输入（必填）1-2年结构层面
FTD Detector输入（必填）数天至数周事件层面
VCP Screener输入（可选）特定形态层面
Theme Detector输入（可选）数周至数月主题层面
CANSLIM Screener输入（可选）特定形态层面
本技能合成器统一信心评估