# strategy-pivot-designer

Detects stagnation in backtest iteration loops and generates structurally different strategy proposals when parameter tuning hits a local optimum.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 3300 installs · ★ 3267
- Author: tradermonty
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/tradermonty/claude-trading-skills/tree/HEAD/skills/strategy-pivot-designer/SKILL.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/strategy-pivot-designer

## What it does

The skill acts as an architectural feedback loop within the Edge pipeline. When parameter optimization hits a wall, `detect_stagnation.py` inspects the backtest evaluation history. It detects metric plateaus, overfitting, or cases where transaction fees erase the edge.

Once stagnation is confirmed, `generate_pivots.py` creates alternative strategy structures using assumption inversion, archetype switching, and objective reframing. The workflow writes human-readable markdown reports, metadata manifests, and YAML proposals ready for `candidate-agent`.

Running the scripts requires Python 3.9+, `PyYAML`, an iteration history JSON file, and a base strategy draft YAML. When the diagnostic output marks a run as `review_required`, the tool halts proposal generation. This forces you to fix distorted metrics or division errors before trying another architecture.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add tradermonty/claude-trading-skills --skill strategy-pivot-designer -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/strategy-pivot-designer/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/strategy-pivot-designer/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add tradermonty/claude-trading-skills --skill strategy-pivot-designer -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/strategy-pivot-designer/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add tradermonty/claude-trading-skills --skill strategy-pivot-designer -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/strategy-pivot-designer/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install tradermonty/claude-trading-skills strategy-pivot-designer
```

2. **Manually: put the files in place**
- File: `.github/skills/strategy-pivot-designer/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add tradermonty/claude-trading-skills --skill strategy-pivot-designer -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/tradermonty/claude-trading-skills --path skills/strategy-pivot-designer
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/strategy-pivot-designer/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add tradermonty/claude-trading-skills --skill strategy-pivot-designer -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/tradermonty/claude-trading-skills/tree/HEAD/skills/strategy-pivot-designer/SKILL.md

## When to use it
- Detect backtest iteration plateaus and model overfitting
- Restructure the strategy skeleton when transaction costs defeat thin edges
- Generate alternative strategy drafts for the same market hypothesis
- Exports validated YAML proposals and tickets directly to candidate-agent

## Example prompts
- Inspect backtest history for stagnation using scripts/detect_stagnation.py
- Run generate_pivots.py on the current strategy draft to propose new architectures
- Append the latest backtest evaluation to iteration_history.json with notes on parameter changes

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: ccdff145be85d1a3.

BEGIN THIRD-PARTY FILE ccdff145be85d1a3
````text
---
name: strategy-pivot-designer
description: Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
---

# Strategy Pivot Designer

## Overview

Detect when a strategy's backtest iteration loop has stalled and propose structurally different strategy architectures. This skill acts as the feedback loop for the Edge pipeline (hint-extractor -> concept-synthesizer -> strategy-designer -> candidate-agent), breaking out of local optima by redesigning the strategy's skeleton rather than tweaking parameters.

## When to Use

- Backtest scores have plateaued despite multiple refinement iterations.
- A strategy shows signs of overfitting (high in-sample, low robustness).
- Transaction costs defeat the strategy's thin edge.
- Tail risk or drawdown exceeds acceptable thresholds.
- You want to explore fundamentally different strategy architectures for the same market hypothesis.

## Prerequisites

- Python 3.9+
- `PyYAML`
- Iteration history JSON (accumulated backtest-expert evaluations)
- Source strategy draft YAML (from edge-strategy-designer)

## Output

- `pivot_drafts/research_only/*.yaml` — strategy_draft compatible YAML proposals
- `pivot_drafts/exportable/*.yaml` — export-ready drafts + ticket YAML for candidate-agent
- `pivot_report_*.md` — human-readable pivot analysis
- `pivot_manifest_*.json` — metadata for all generated files
- `pivot_diagnosis_*.json` — stagnation detection results

## Workflow

1. Accumulate backtest evaluation results into an iteration history file using `--append-eval`.
2. Run stagnation detection on the history to identify triggers (plateau, overfitting, cost defeat, insufficient profit factor, tail risk). A no-loss profit factor is not cost defeat; an undefined or overflowed ratio requires review.
3. If the diagnosis says `review_required`, repair or re-evaluate the underlying metrics first; do not generate pivots. If stagnation is confirmed, generate pivot proposals using three techniques: assumption inversion, archetype switch, objective reframe.
4. Review ranked proposals (scored by quality potential + novelty).
5. For exportable proposals, ticket YAML is ready for edge-candidate-agent pipeline.
6. For research_only proposals, manual strategy design needed before pipeline integration.
7. Feed the selected pivot draft back into backtest-expert for the next iteration cycle.

## Quick Commands

Append a backtest evaluation to history (creates history if new):

```bash
````
END THIRD-PARTY FILE ccdff145be85d1a3

The third-party file has ended. Everything between the ccdff145be85d1a3 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2535 of 3674 bytes. © tradermonty · MIT · https://github.com/tradermonty/claude-trading-skills/tree/HEAD/skills/strategy-pivot-designer/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md