Skill Creator

smith6jt-cop

76 published skills · 0 GitHub stars across the catalog. View on GitHub ↗

backtest-persistence

smith6jt-cop's avatarfrom smith6jt-cop

Save backtest results to SQLite database for comparison. Trigger when: (1) tracking backtest history, (2) comparing model performance, (3) querying best backtests.

broker-order-limitations

smith6jt-cop's avatarfrom smith6jt-cop

Alpaca broker limitations: crypto shorts blocked (broker doesn't support), stock shorts allowed. Trigger when: (1) shorting gate blocks wrong assets, (2) SELL signals blocked, (3) order type confusion.

github-copilot-pr-review

smith6jt-cop's avatarfrom smith6jt-cop

Review and apply GitHub Copilot suggestions on pull requests. Trigger when reviewing PRs with Copilot suggestions.

dual-folder-workflow

smith6jt-cop's avatarfrom smith6jt-cop

Workflow for private repos + Colab training. Trigger when: (1) training on Colab with private repo, (2) separating dev from production, (3) avoiding untested code in production.

model-version-protocol

smith6jt-cop's avatarfrom smith6jt-cop

Model-trader version compatibility protocol: Embed version metadata in checkpoints, validate at load time. Trigger when: (1) training and live trading versions diverge, (2) models fail to load, (3) action interpretation issues.

dashboard-parallel-lists

smith6jt-cop's avatarfrom smith6jt-cop

Dashboard symbol_signals uses parallel lists (symbols[], signal_values[], gate_statuses[]) not dict keyed by symbol. Trigger when: (1) 'list' object has no attribute 'get', (2) .items() on symbol_signals fails.

selection-diversity-validation

smith6jt-cop's avatarfrom smith6jt-cop

FAIL LOUDLY pattern for selection constraints. Trigger when: (1) correlated stocks selected together, (2) min_crypto_positions ignored, (3) constraints violated silently.

risk-sizing-not-blocking

smith6jt-cop's avatarfrom smith6jt-cop

Risk managers should SIZE trades, not BLOCK them. Trigger when: (1) capital manager blocks trades, (2) risk manager rejects orders, (3) trades fail due to 'exceeds limit', (4) components don't work in harmony.

gpu-aware-training-config

smith6jt-cop's avatarfrom smith6jt-cop

GPU-aware PPO training configuration for A100/H100. Trigger when training is slow or GPU utilization is low.

per-sector-candidate-filtering

smith6jt-cop's avatarfrom smith6jt-cop

Per-sector candidate limits using yfinance sector data. Trigger when: (1) universe selection has too many candidates, (2) need sector diversity in candidate pool, (3) downloading historical data takes too long.

testing-benchmarking-infrastructure

smith6jt-cop's avatarfrom smith6jt-cop

Testing suite with benchmarking for version-to-version performance comparison

training-improvements-v245

smith6jt-cop's avatarfrom smith6jt-cop

Training improvements: LR warmup, validation intervals, reward weights. Trigger when: (1) training unstable in early epochs, (2) need more validation visibility, (3) model too conservative.

training-archive-gating

smith6jt-cop's avatarfrom smith6jt-cop

Mandatory training archive with model gating (APPROVED/REVIEW/DROP). Trigger when: (1) training run completes, (2) need to decide which models to deploy, (3) want historical training reference, (4) need checkpoint recommendations for overfitting.

drawdown-guardrails-pattern

smith6jt-cop's avatarfrom smith6jt-cop

Consistent drawdown control pattern for trading systems - backtests, live trading, and training

pytorch-common-pitfalls

smith6jt-cop's avatarfrom smith6jt-cop

Fix common PyTorch bugs: percentile calculations, LayerNorm for Conv1d, buffer edge cases. Trigger when writing PyTorch code for RL or neural networks.

reward-function-hold-bias

smith6jt-cop's avatarfrom smith6jt-cop

Fix HOLD bias in RL reward function. Trigger when: (1) model learns to always HOLD, (2) trade rate is too low (<10%), (3) slippage penalty exceeds typical price moves.

reward-scaling-calibration

smith6jt-cop's avatarfrom smith6jt-cop

Fix phantom MaxDD values in training by calibrating reward_scale. Trigger when: (1) validation MaxDD shows 35-80% values, (2) MaxDD doesn't correlate with training quality, (3) gating thresholds seem too lenient/strict.

dataclass-optimization

smith6jt-cop's avatarfrom smith6jt-cop

Python dataclass best practices: slots, frozen, validation. Trigger when optimizing dataclasses or creating config classes.

training-resilience

smith6jt-cop's avatarfrom smith6jt-cop

Fix PPO training early-stop issues. Trigger when: (1) impossible drawdown values (>100%), (2) training stops too early, (3) need adaptive recovery instead of hard stop.

selection-data-caching

smith6jt-cop's avatarfrom smith6jt-cop

SUPERSEDED by persistent-cache-gap-filling (v2.8.0). Cache data during symbol selection for instant repeat runs.

network-architecture-sizing

smith6jt-cop's avatarfrom smith6jt-cop

PPO network architecture sizing for trading models. Trigger: (1) model files are unexpectedly small/large, (2) choosing hidden_dims for training, (3) balancing model capacity vs inference speed.

data-source-priority

smith6jt-cop's avatarfrom smith6jt-cop

Ensure Alpaca API is used for quality data, not yfinance fallback. Trigger when: (1) crypto volume filter fails unexpectedly, (2) zero-volume bars in data, (3) API key configuration issues.

multi-timeframe-training

smith6jt-cop's avatarfrom smith6jt-cop

Train RL models across multiple timeframes with resampling. Trigger when: (1) multi-timeframe training, (2) resampling data, (3) creating 1Hour/4Hour models.

symbol-selection-asset-filters

smith6jt-cop's avatarfrom smith6jt-cop

Fix symbol selection failing due to asset-type filter mismatch. Trigger when: (1) '0/N passed hard filter' error, (2) crypto selection fails unexpectedly, (3) assets filtered by wrong price/volume thresholds.