Analyze investment opportunities across asset classes with risk assessment, return modeling, and portfolio optimization

Intelligent code review dispatcher - automatically selects best reviewer based on context and preferences

Ensures code is understandable locally without global context. Use when reviewing code with hidden dependencies or global state.

Feature-first init: create or reuse worktree/branch and seed per-feature context. Git-aware and idempotent.

Project setup. Explore the codebase, ask about strategy and aims, write persistent context to AGENTS.md. Run when starting or when aims shift.

Molecular machine learning toolkit. Property prediction (ADMET, toxicity), GNNs (GCN, MPNN), MoleculeNet benchmarks, pretrained models, featurization, for drug discovery ML.

Molecular machine learning toolkit. Property prediction (ADMET, toxicity), GNNs (GCN, MPNN), MoleculeNet benchmarks, pretrained models, featurization, for drug discovery ML.

Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC, for rigorous statistical inference and econometric analysis.

Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC, for rigorous statistical inference and econometric analysis.

Start a new learning episode in the self-learning memory system with proper context. Use this skill when beginning a new task that should be tracked for learning from execution patterns.

Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC, for rigorous statistical inference and econometric analysis.

Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC, for rigorous statistical inference and econometric analysis.

Create Architecture Decision Records (ADR) - Layer 5 artifact documenting architectural decisions with Context-Decision-Consequences format

Use when integrating with Polza.ai API, writing code for AI model calls, configuring OpenAI-compatible clients with Polza.ai base URL, or when user mentions polza

Use when user needs ML model deployment, production serving infrastructure, optimization strategies, and real-time inference systems. Designs and implements scalable ML systems with focus on...

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

Template and guide for creating skills. Demonstrates the standard skill structure with resources, docs, examples, and templates directories. Use this as a reference when building new protocol integrations.

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

Analyze temporal data patterns including trends, seasonality, autocorrelation, and forecasting for time series decomposition, trend analysis, and forecasting models