Skill UI

bdistill transforms AI interactions into a structured, queryable knowledge base. It extracts, structures, and quality-scores domain knowledge from both closed-source AI models (in-session) and local open-source models (via Ollama). Users can build comprehensive reference datasets, Q&A pairs, or generate structured training data for traditional machine learning, ensuring validated and exportable domain expertise.

This skill automatically generates an interactive SQL Notebook designed to validate changes in dbt models or snapshots. It processes changes identified from a GitHub PR or local repository, generating comparison queries that compare 'before' (production) and 'after' (development) data states. It is essential for embedding data observability and quality checks into CI/CD pipelines.

Validates BED and universe contracts, plans Region2Vec and scEmbed runs, checks model and tokenizer compatibility, and assesses consensus universes for audited, local-only genomic-interval ML workflows.

Gtars offers local genomic interval models, set algebra, overlap/count operations, consensus and coverage, tokenization, fragment processing, and refget/BEDbase planning across Python, Rust, and CLI.

Build local, research-only computational pathology workflows with PathML: load and tile whole-slide images, run preprocessing and QC pipelines, manage h5path data, quantify multiplex images, construct spatial graphs, and plan bounded model inference.

This skill covers using the SHAP library to explain and audit machine learning predictions. It guides users on selecting explainers, computing feature attributions, and validating results. It includes workflows for local and global visualizations, handling multi-output models, and ensuring model behavior descriptions are accurate without implying causality. Requires Python 3.12+ and specific SHAP versions.

Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. It enables pKa prediction, molecular docking, conformer search, and protein-ligand cofolding without local HPC infrastructure. Ideal for batch screening and multi-step chemistry pipelines in drug discovery.

Provides expert guidance for connecting to Power BI Desktop's local tabular model using the Tabular Object Model (TOM) and ADOMD.NET via PowerShell. This skill covers model enumeration, executing DAX queries, metadata modification (tables, measures, relationships), query tracing, and model refreshing. It is specifically designed for managing the underlying data model structure when external tools like Tabular Editor CLI are unavailable.

This skill dispatches computationally intensive quantitative trading jobs (such as multi-year walk-forward analysis, large Monte-Carlo simulations, parameter sweeping, or deep model training) to a managed cloud agent runtime. It is designed for large-scale, production-grade backtesting that exceeds local machine capacity, ensuring robust execution and artifact management via Anthropic's cloud services.

This guide provides comprehensive methodological frameworks for conducting rigorous empirical analyses in international trade and macroeconomics, particularly tailored to the standards of top-tier journals like the JIE. It covers assembling bilateral trade and cross-country panels, estimating gravity models using PPML, implementing local projections, and calibrating structural open-economy models. It ensures analyses are robust, replicable, and address common referee criticisms.

A comprehensive guide detailing the quantitative and econometric standards required for submissions to top-tier monetary and macroeconomic journals. It covers advanced techniques like VAR/SVAR, Local Projections, and DSGE modeling, focusing on proper inference, robustness checks, and diagnostic reporting to ensure scholarly rigor.

This guide details the rigorous identification methods required for submitting macro-financial papers to top-tier journals like the Journal of Monetary Economics (JME). It covers techniques such as separating pure monetary shocks from information effects, implementing various Structural VARs (SVARs), using local projections, and conducting model-based identification, ensuring your claims meet the highest academic standards.