Skill Creator

Donaldshen27

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

change-point-detection

Donaldshen27's avatarfrom Donaldshen27

Use when segmenting time-series into regimes, detecting structural breaks, or constructing context sets for few-shot learning. Covers GP-CPD algorithms, Matérn kernels, likelihood ratio tests, regime identification, market state transitions, volatility regime changes, and trend reversals in financial markets.

codex-review

Donaldshen27's avatarfrom Donaldshen27

AUTOMATICALLY run Codex review after writing security-sensitive code (auth, crypto, SQL) - get a second opinion from OpenAI Codex

few-shot-learning-finance

Donaldshen27's avatarfrom Donaldshen27

Use when implementing models that learn from minimal data or need to adapt to new market regimes rapidly. Covers episodic learning, context sets, support and query sequences, zero-shot vs few-shot learning, meta-learning for finance, transfer learning across assets and regimes, and quick adaptation to market changes.

financial-time-series

Donaldshen27's avatarfrom Donaldshen27

Use when working with price data, trading signals, or implementing momentum strategies. Covers returns calculation, volatility targeting, momentum factors, MACD indicators, time-series momentum (TSMOM), portfolio construction, futures contracts, and risk-adjusted returns for trend-following strategies.

x-trend-architecture

Donaldshen27's avatarfrom Donaldshen27

Use when implementing X-Trend or attention-based trading models. Covers LSTM encoders, cross-attention, self-attention, sequence representations, entity embeddings, Variable Selection Networks, encoder-decoder patterns, Deep Momentum Networks, and interpretable predictions for trend-following strategies.