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）


market_breadth_
uptrend_analysis_
market_top_
macro_regime_
ftd_detector_

#	Skill	JSON Prefix	Role
1	Market Breadth Analyzer	`market_breadth_`	Market participation breadth
2	Uptrend Analyzer	`uptrend_analysis_`	Sector uptrend ratios
3	Market Top Detector	`market_top_`	Distribution / top risk (defense)
4	Macro Regime Detector	`macro_regime_`	Macro regime transition (1-2Y structure)
5	FTD Detector	`ftd_detector_`	Bottom confirmation / re-entry (offense)


market_breadth_
uptrend_analysis_
market_top_
macro_regime_
ftd_detector_

序号	技能	JSON前缀	作用
1	Market Breadth Analyzer	`market_breadth_`	市场参与广度
2	Uptrend Analyzer	`uptrend_analysis_`	行业上涨趋势比率
3	Market Top Detector	`market_top_`	派发/顶部风险（防御）
4	Macro Regime Detector	`macro_regime_`	宏观 regime 转换（1-2年结构）
5	FTD Detector	`ftd_detector_`	底部确认/重新入场（进攻）

Optional Skills (3)

可选技能（3项）

#	Skill	JSON Prefix	Role
6	VCP Screener	`vcp_screener_`	Momentum stock setups (VCP)
7	Theme Detector	`theme_detector_`	Theme / sector momentum
8	CANSLIM 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
6	VCP Screener	`vcp_screener_`	动量股票形态（VCP）
7	Theme Detector	`theme_detector_`	主题/行业动量
8	CANSLIM 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:

Load and validate all upstream skill JSON reports
Extract normalized signals from each skill
Calculate 7 component scores (weighted 0-100)
Compute composite conviction score
Classify into one of 4 Druckenmiller patterns
Generate target allocation and position sizing
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：

加载并验证所有上游技能的JSON报告
从每个技能中提取标准化信号
计算7项组件得分（加权0-100）
计算综合信心评分
归类为4种Druckenmiller模式之一
生成目标配置和仓位规模
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

#	Component	Weight	Source Skill(s)	Key Signal
1	Market Structure	18%	Breadth + Uptrend	Market participation health
2	Distribution Risk	18%	Market Top (inverted)	Institutional selling risk
3	Bottom Confirmation	12%	FTD Detector	Re-entry signal after correction
4	Macro Alignment	18%	Macro Regime	Regime favorability
5	Theme Quality	12%	Theme Detector	Sector momentum health
6	Setup Availability	10%	VCP + CANSLIM	Quality stock setups
7	Signal Convergence	12%	All 5 required	Cross-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 Regime	Regime 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

Pattern	Trigger Conditions	Druckenmiller Principle
Policy Pivot Anticipation	Transitional regime + high transition probability	"Focus on central banks and liquidity"
Unsustainable Distortion	Top risk >= 60 + contraction/inflationary regime	"How much you lose when wrong matters most"
Extreme Sentiment Contrarian	FTD confirmed + high top risk + bearish breadth	"Most money made in bear markets"
Wait & Observe	Low 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

Score	Zone	Exposure	Guidance
80-100	Maximum Conviction	90-100%	Fat pitch - swing hard
60-79	High Conviction	70-90%	Standard risk management
40-59	Moderate Conviction	50-70%	Reduce position sizes
20-39	Low Conviction	20-50%	Preserve capital, minimal risk
0-19	Capital Preservation	0-20%	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

Skill	Relationship	Time Horizon
Market Breadth Analyzer	Input (required)	Current snapshot
Uptrend Analyzer	Input (required)	Current snapshot
Market Top Detector	Input (required)	2-8 weeks tactical
Macro Regime Detector	Input (required)	1-2 years structural
FTD Detector	Input (required)	Days-weeks event
VCP Screener	Input (optional)	Setup-specific
Theme Detector	Input (optional)	Weeks-months thematic
CANSLIM Screener	Input (optional)	Setup-specific
This Skill	Synthesizer	Unified 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