Skill UI

This skill provides a systematic framework for evaluating the rigor of scientific claims, research methodology, and evidence quality. It guides users through assessing experimental design validity, identifying various types of biases (e.g., selection, cognitive), and applying established grading frameworks like GRADE or Cochrane Risk of Bias. Ideal for systematic reviews, peer review, and critical analysis of scientific literature.

scikit-survival is a comprehensive Python library built on scikit-learn, designed for rigorous time-to-event analysis. It specializes in handling censored data (right, left, or interval-censored) and provides multiple advanced modeling techniques, including Cox proportional hazards models, Random Survival Forests, Gradient Boosting, and Survival SVMs. Users can evaluate model performance using metrics like the Concordance Index and Brier Score, making it ideal for clinical, reliability, and survival research.

A comprehensive guide and toolkit for systematic statistical analysis, covering the entire research lifecycle. Features include test selection guidance (t-test, ANOVA, regression), rigorous assumption checking (normality, homogeneity), power analysis, effect size calculation, and generation of professional, APA-formatted academic reports. Essential for academic researchers and data scientists.

Statsmodels is a robust Python library providing comprehensive tools for advanced statistical analysis. It supports a wide range of models, including Ordinary Least Squares (OLS), Generalized Linear Models (GLM like Poisson and Logistic), Weighted Least Squares (WLS), and complex time series forecasting (ARIMA). Use this skill for rigorous econometrics, detailed diagnostic testing, and generating publication-ready statistical inference.

A comprehensive Python wrapper for the U.S. Treasury Fiscal Data REST API. This tool allows users to query diverse federal financial datasets, including national debt, interest rates, foreign exchange rates, and government revenue/spending statistics. It requires no API key and is ideal for financial modeling, economic research, and data analytics projects.

Execute comprehensive, asynchronous transcription workflows using AssemblyAI. This tool handles file upload, queues jobs, and provides advanced audio intelligence features. Capabilities include speaker diarization, sentiment analysis, named entity recognition (NER), topic categorization (IAB), content safety moderation, and sensitive PII redaction. Ideal for processing meeting recordings, interviews, and large volumes of spoken content.

This skill provides comprehensive access to Bright Data's SERP API and Web Scraper API. It allows users to collect structured search engine results (Google, Bing, Yahoo) synchronously, or trigger large-scale, asynchronous data collections with webhooks. Ideal for market research, SEO analysis, and large-scale data scraping projects.

This comprehensive checklist guides users through critical operational readiness steps for a ClickHouse production deployment. It covers server tuning (config.xml), schema design best practices, robust backup strategies (S3), detailed monitoring setup (Prometheus/Grafana), security hardening, and application integration verification. Use this document before go-live, during major upgrades, or when auditing production systems to ensure maximum stability and performance.

This comprehensive guide details best practices for securing a ClickHouse deployment. It covers essential security measures including role-based access control (RBAC) for granular user permissions, implementing row-level security for multi-tenancy, configuring network IP restrictions, enabling TLS encryption, and setting up detailed audit logging. Use this when hardening a production ClickHouse instance or enforcing strict data governance.

This skill performs a deep, cross-model audit of experimental results to ensure integrity before claiming findings. It systematically checks for common fraud patterns, such as generating fake ground truths, misleading score normalization, or citing phantom results. Use it when evaluating reported experimental outcomes to ensure methodological rigor and trustworthiness.

Comprehensive toolkit for managing sensitive Flexport supply chain data, including shipment records, customs declarations, and financial invoices. This skill enforces strict data governance, handling PII redaction, ensuring GDPR/CCPA compliance, managing mandated data retention periods (e.g., 5-7 years), and blocking restricted export items (ITAR) to maintain global trade compliance standards.

Provides a comprehensive checklist for deploying Hex data analytics integrations into production. It covers critical operational best practices, including API key management, rate limit handling, error resilience (circuit breakers, exponential backoff), and robust monitoring strategies. This guide ensures that data pipelines are deployed reliably, minimizing downtime and guaranteeing consistent, high-quality data reporting for go-live scenarios.