Skill Creator
smith6jt-cop
76 published skills · 0 GitHub stars across the catalog. View on GitHub ↗
backtest-persistence
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
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
Review and apply GitHub Copilot suggestions on pull requests. Trigger when reviewing PRs with Copilot suggestions.
dual-folder-workflow
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
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
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
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
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
GPU-aware PPO training configuration for A100/H100. Trigger when training is slow or GPU utilization is low.
per-sector-candidate-filtering
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
Testing suite with benchmarking for version-to-version performance comparison
training-improvements-v245
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
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
Consistent drawdown control pattern for trading systems - backtests, live trading, and training
pytorch-common-pitfalls
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
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
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
Python dataclass best practices: slots, frozen, validation. Trigger when optimizing dataclasses or creating config classes.
training-resilience
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
SUPERSEDED by persistent-cache-gap-filling (v2.8.0). Cache data during symbol selection for instant repeat runs.
network-architecture-sizing
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
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
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
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.