stanley-druckenmiller-investment

Synthesize upstream market analysis JSON reports into a conviction score and allocation recommendation.

Updated Apr 17, 2026
One-click install
npx skills add https://github.com/pasie15/claude-trading-skills-marketplace --skill stanley-druckenmiller-investment-pasie15
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: stanley-druckenmiller-investment
Source: https://github.com/pasie15/claude-trading-skills-marketplace/tree/main/plugins/trading-portfolio-risk/skills/stanley-druckenmiller-investment
Command: npx skills add https://github.com/pasie15/claude-trading-skills-marketplace --skill stanley-druckenmiller-investment-pasie15

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

Synthesize disparate structured outputs from multiple market-analysis skills into a single, actionable conviction score and allocation recommendation so portfolio managers and traders can make consistent position-sizing and allocation decisions without manual signal aggregation.

Core Features & Use Cases

  • Multi-skill synthesis: Aggregates normalized JSON outputs from Market Breadth, Uptrend, Market Top, Macro Regime, and FTD detectors, with optional VCP, Theme, and CANSLIM inputs.
  • Conviction & pattern classification: Produces a 0-100 conviction score, identifies one of four Druckenmiller patterns, and highlights strongest/weakest components.
  • Allocation & sizing guidance: Maps conviction and pattern to target allocations (equity/bonds/alternatives/cash) and position sizing rules using quantitative matrices and rule-based overrides.
  • Use Case: After running upstream analyzers, run this synthesizer to get a single Markdown and JSON report that recommends exposure levels and explains the rationale in Druckenmiller terms.

Quick Start

Run the Druckenmiller Strategy Synthesizer with the latest reports in the reports/ folder to generate a conviction dashboard and allocation recommendation.

Frequently Asked Questions about stanley-druckenmiller-investment

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I aggregate multiple market analysis signals into a single portfolio allocation recommendation?

To aggregate market analysis signals into a portfolio allocation recommendation, synthesize structured JSON outputs from breadth, uptrend, and macro analyzers into a composite 0-100 conviction score. This eliminates manual signal aggregation by mapping conviction levels to target equity, bond, and cash allocations.

What is a conviction score and how does it guide position sizing?

A conviction score is a 0-100 quantitative measure synthesized from multiple market analysis inputs. It guides position sizing by mapping higher conviction levels to increased target allocations across equities, bonds, alternatives, and cash using quantitative matrices and rule-based overrides.

How do I generate a Druckenmiller market pattern classification from JSON reports?

To generate a Druckenmiller market pattern classification, run the strategy synthesizer with recent structured JSON reports in your reports directory. The process identifies one of four market patterns and outputs both structured JSON and Markdown dashboard reports explaining the strongest and weakest portfolio components.

Do I need specific upstream reports to run the strategy synthesizer?

Yes, you need recent JSON outputs from five required upstream skills: Market Breadth, Uptrend, Market Top, Macro Regime, and FTD detectors. You can also optionally incorporate VCP, Theme, and CANSLIM reports to enrich the signal aggregation and allocation guidance.

Can I use this synthesizer without macro regime and market breadth data?

No, the synthesizer requires Market Breadth, Uptrend, Market Top, Macro Regime, and FTD JSON reports to function. Without these five mandatory upstream inputs in the reports directory, the composite conviction score and allocation matrix cannot be calculated.