Skill UI

This skill provides comprehensive guidelines for monitoring Granola usage, tracking team meeting patterns, and building detailed analytics dashboards. It guides users in defining critical metrics (e.g., adoption rate, efficiency score) and establishing robust data pipelines. Users can stream meeting metadata from Granola to data warehouses like BigQuery, enabling deep, customizable reporting and automated weekly insights via services like Zapier and Slack.

This module provides minimal working examples for the OpenEvidence API, designed for clinical intelligence applications. Users can perform complex clinical queries to get treatment recommendations, check potential drug interactions based on patient context, and search for authoritative medical guidelines from major health organizations (e.g., ACC/AHA). Ideal for developing evidence-based healthcare decision support systems.

Provide REST API access to ClinPGx, the successor to PharmGKB, for querying gene-drug interactions, CPIC/DPWG/FDA guidelines, allele functions, and evidence that supports precision dosing and pharmacogenomics-driven clinical decisions.

Create truthful, accessible, publication-ready scientific figures using Matplotlib, Seaborn, or Plotly. Ensures data integrity, proper encoding, accessibility compliance, and journal export planning for research publications. Includes guidelines for uncertainty displays, color/contrast review, and metadata validation.

This skill provides comprehensive knowledge of the Power BI Enhanced Report (PBIR) JSON schema. It details the structured metadata for report components, including visuals, pages, themes, bookmarks, and complex formatting rules. Users learn how to read and manipulate the underlying PBIR JSON to understand how Power BI reports are built and customized, adhering to strict technical guidelines and operational best practices.

A comprehensive suite designed for AI agents to perform safe, deep, and multi-format web searches. It allows agents to retrieve current web information, analyze PDFs, extract YouTube transcripts, and access GitHub code files. Instructions include guidelines for varying search depths and using specialized tools for code context retrieval.

A comprehensive set of guidelines for generating maps, figures, and tables for academic journals. This guide emphasizes cartographic standards, statistical rigor, and maximizing the visual argument, ensuring that all exhibits are reproducible, legible in print, and adhere to strict word count limitations. It covers everything from projection choice and data normalization to model plot interpretation and handling spatial uncertainty.

Provides comprehensive guidelines for achieving scientific reproducibility in academic research, particularly for control systems, automation, and pattern recognition. It covers fixing environment dependencies, data handling, random seeds, and process pipelines, helping authors withstand rigorous peer review questioning and build verifiable research artifacts.

A comprehensive guide for structuring research artifacts (code, models, datasets, media) for ACM Multimedia conferences. It details the distinct requirements for anonymous review packages versus permanent public releases, offering guidelines on ethics, licensing, reproducibility, and track-specific documentation.

This guide provides rigorous methodological guidelines for ensuring the identification strategy in high-impact empirical economics papers (AER: Insights). It covers key areas including Difference-in-Differences (DiD), Regression Discontinuity Design (RDD), Instrumental Variables (IV), and structural parameter identification. It emphasizes the need for extreme methodological clarity, transparency, and conciseness required for top-tier academic publication.

This guide provides rigorous guidelines for creating high-quality figures and tables for complex systems manuscripts, especially in agricultural science. It emphasizes shifting focus from single-factor bar charts to systemic visualizations that reveal interactions, trade-offs (e.g., Pareto fronts), model dynamics, resource flows (Sankey diagrams), and model performance (observed-vs-simulated fit). Exhibits must be self-contained, reproducible, and convey uncertainty.

This guide provides strict guidelines for designing, auditing, and reporting empirical or simulation experiments, particularly for theoretical machine learning and statistics papers. It emphasizes mapping every empirical claim to specific evidence, ensuring statistical rigor (e.g., reporting uncertainty, baselines, seeds), and validating theoretical assumptions rather than optimizing for leaderboards. Essential for research reproducibility.