Strategy Pivot Designer

by tradermontyeab8d5cb97b9No license2.9K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 3 days ago

Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.

AI-generated overview

Detects backtest iteration stagnation and generates structurally different strategy pivot proposals for trading strategies.

What it does
This skill analyzes accumulated backtest evaluation history to detect stagnation triggers such as score plateaus, overfitting, cost defeat, and tail risk. When stagnation is found, it generates structurally different strategy pivot proposals using assumption inversion, archetype switching, and objective reframing. It produces strategy draft YAML files, a human-readable pivot report, a manifest, and a diagnosis JSON. Proposals are ranked by quality potential and novelty, with exportable drafts accompanied by ticket YAML for a candidate-agent pipeline.
When to use it
Use this skill when backtest scores have plateaued despite repeated refinement, when a strategy shows overfitting signs, when transaction costs defeat a thin edge, or when drawdown exceeds acceptable thresholds. It is also suited to exploring fundamentally different strategy architectures for the same market hypothesis.
Requirements
Python 3.9+, PyYAML, an iteration history JSON of backtest evaluations, and a source strategy draft YAML. It ships executable scripts for stagnation detection and pivot generation.

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, tail risk).
  3. If stagnation detected, 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
python3 skills/strategy-pivot-designer/scripts/detect_stagnation.py \  --append-eval reports/backtest_eval_2026-02-10_120000.json \  --history reports/iteration_history.json \  --strategy-id draft_edge_concept_breakout_behavior_riskon_core \  --changes "Widened stop_loss from 5% to 7%"

Detect stagnation:

bash
python3 skills/strategy-pivot-designer/scripts/detect_stagnation.py \  --history reports/iteration_history.json \  --output-dir reports/

Generate pivot proposals:

bash
python3 skills/strategy-pivot-designer/scripts/generate_pivots.py \  --diagnosis reports/pivot_diagnosis_*.json \  --strategy reports/edge_strategy_drafts/draft_*.yaml \  --max-pivots 3 \  --output-dir reports/

Resources

  • skills/strategy-pivot-designer/scripts/detect_stagnation.py
  • skills/strategy-pivot-designer/scripts/generate_pivots.py
  • references/stagnation_triggers.md
  • references/strategy_archetypes.md
  • references/pivot_techniques.md
  • references/pivot_proposal_schema.md
  • skills/backtest-expert/scripts/evaluate_backtest.py
  • skills/edge-strategy-designer/scripts/design_strategy_drafts.py

Source and attribution

Source:tradermonty/claude-trading-skillsinskills/strategy-pivot-designerat commiteab8d5c

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

More from tradermonty/claude-trading-skills

Weekly Performance Digest

tradermonty

Aggregates closed trading theses into a weekly performance report with metrics, pattern breakdowns, and lessons.

Includes scripts
Data & Analytics2.9Kupdated 3 days ago

Trade Performance Coach

tradermonty

Reviews recorded trades for process adherence, risk discipline, execution quality and behavior patterns, producing a coaching report.

Includes scripts
Business & Finance2.9Kupdated 3 days ago

Skill Designer

tradermonty

Design new Claude skills from structured idea specifications. Use when the skill auto-generation pipeline needs to produce a Claude CLI prompt that creates a complete skill directory (SKILL.md, references, scripts, tests) following repository conventions.

Includes scripts
Awaiting classification2.9Kupdated 3 days ago

Residual Edge Analyzer

tradermonty

Separate a strategy return series into declared baseline exposure and residual edge with returns-based OLS attribution, HAC inference, rolling stability, alternate-baseline sensitivity, and regime breakdowns. Use when evaluating whether backtest, out-of-sample, or live returns contain independent alpha beyond market, equal-weight, momentum, sector, or user-supplied factor returns; when explaining whether a drawdown came from baseline exposure or strategy-specific behavior; or when a strategy needs an attribution quality gate after backtesting. Do not use for holdings-based Brinson attribution, feature-level Shapley explanations, or analysis from summary metrics without a dated return series.

Includes scripts
Awaiting classification2.9Kupdated 3 days ago

Pre Trade Discipline Gate

tradermonty

Offline pre-trade checklist gate that approves, reviews, or blocks planned manual orders and journals the decision.

Includes scripts
Business & Finance2.9Kupdated 3 days ago

Manifoldbt Backtester

tradermonty

Runs a declarative strategy spec over OHLCV bars with the manifoldbt Rust engine, pairs the fill log into round trips, and emits the eight inputs the backtest-expert skill scores. Use when the user wants to execute a backtest, measure a rule they have described, obtain win rate / average win / average loss / max drawdown from real bars, or feed backtest-expert with measured numbers instead of estimates.

Includes scripts
Awaiting classification2.9Kupdated 3 days ago