strategy-pivot-designer

Detect stagnation in backtest iteration loops and generate structurally different pivot proposals.

Updated Mar 25, 2026
One-click install
npx skills add https://github.com/MileniumTick/skills --skill strategy-pivot-designer-mileniumtick
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: strategy-pivot-designer
Source: https://github.com/MileniumTick/skills/tree/main/skills/strategy-pivot-designer
Command: npx skills add https://github.com/MileniumTick/skills --skill strategy-pivot-designer-mileniumtick

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyYAML, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Detect stagnation in a backtest iteration loop and generate structurally different pivot proposals to escape local optima, enabling strategy evolution beyond parameter tuning.

Core Features & Use Cases

  • Detect stagnation via multiple triggers (plateau, overfitting proxy, cost defeat, tail risk) on iteration histories.
  • Generate diverse pivot directions including inversion, archetype switches, and objective reframing, with scoring for quality and novelty.
  • Produce exportable pivot drafts and tickets for downstream execution, plus research-only pivots for rapid prototyping.

Quick Start

Run the stagnation detector on your iteration history to generate pivot diagnoses and review the top pivots.

Frequently Asked Questions about strategy-pivot-designer

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

FAQPage Schema
How do I detect stagnation in a backtest iteration loop?

Stagnation in a backtest iteration loop is detected by evaluating iteration histories against multiple triggers such as performance plateaus, overfitting proxies, cost defeat, and tail risk indicators.

What is a pivot strategy for escaping local optima?

A pivot strategy escapes local optima by generating structurally different proposals like inversion, archetype switches, and objective reframing, rather than relying on parameter tuning within the existing architecture.

How do I generate diverse quant strategy proposals during stagnation?

You generate diverse quant strategy proposals by applying a pivot proposal engine that scores directions for quality and novelty, producing both exportable execution tickets and research-only prototypes.

Can I export pivot tickets for downstream execution from a backtest pipeline?

Yes, the system produces exportable pivot drafts and tickets for downstream execution, enabling strategy evolution beyond parameter tuning when your backtest pipeline plateaus.

When should I pivot a trading strategy instead of tuning parameters?

You should pivot a trading strategy instead of tuning parameters when overfitting risk is present, tail risk suggests architecture shifts, or iteration histories show sustained performance plateaus.