Skill UI

Guides teams through planning, designing, and running statistically sound A/B tests with hypothesis framing, sample sizing, metric selection, implementation strategies, and analysis checkpoints for systematic growth experimentation.

A comprehensive, expert-level workflow for debugging complex software issues in production environments. This skill guides users through initial triage, advanced observability data collection (APM, distributed traces, logs), intelligent hypothesis generation, and full root cause analysis. Use it when dealing with intermittent failures, performance bottlenecks, or needing a complete fix and prevention plan.

A comprehensive toolkit for evaluating the performance of code generation models. It supports benchmarking against industry standards like HumanEval, MBPP, and MultiPL-E across multiple languages. Use this tool to quantitatively compare different LLM coding abilities and measure code synthesis quality using pass@k metrics.

A comprehensive toolkit designed for modern product managers covering the entire product lifecycle. It provides essential frameworks for feature prioritization (RICE scoring), conducting deep customer discovery interviews, structuring detailed Product Requirement Documents (PRDs), and developing strategic product roadmaps. Use this guide for robust feature validation, user research synthesis, and cross-functional strategy development.

This skill functions as an expert-level web researcher, utilizing advanced search strategies (query optimization, domain filtering) to gather, synthesize, and validate information from multiple web sources. It is ideal for complex research tasks requiring fact verification, identifying trends, and producing structured, actionable insights, ensuring high credibility for the final output.

BGPT Paper Search queries the remote MCP server to retrieve structured experimental data from full-text studies, returning methods, results, sample sizes, quality scores, and conclusions for efficient literature reviews and evidence synthesis.

Hypogenic automates LLM-driven hypothesis generation and testing over tabular datasets, blending literature insights with empirical analysis to accelerate discovery in domains like deception detection or AI content evaluation.

Guides structured hypothesis generation by combining literature searches, evidence synthesis, competing explanations, and experimental design, with mandatory AI-generated scientific schematics for complete reports.

A comprehensive guide for systematic statistical analysis, designed for academic research. This skill assists in selecting the correct hypothesis tests (t-test, ANOVA, regression, chi-square), checking assumptions (normality, homogeneity), performing advanced analyses (Bayesian methods, power analysis), calculating effect sizes, and generating full APA-formatted reports for publication.

Statsmodels is a comprehensive Python library dedicated to advanced statistical modeling and econometrics. It provides tools for rigorous statistical inference, including Ordinary Least Squares (OLS), Generalized Linear Models (GLM), mixed-effects models, and time series analysis (ARIMA). Use this skill for detailed diagnostics, coefficient estimation, hypothesis testing, and producing publication-ready statistical reports in fields like econometrics and biostatistics.

TorchDrug is a PyTorch-native toolbox for building graph neural networks tailored to molecules, proteins, and biomedical knowledge graphs, covering property prediction, generation, retrosynthesis, and knowledge graph reasoning with curated datasets and models.

Guides PMs through a full discovery cycle—from framing a hypothesis to validating solutions—by combining problem definition, customer interviews, synthesis, and experiments so teams can test assumptions before investing in build work.