Skill UI

Scikit-learn is the industry-standard Python library for classical machine learning. It provides comprehensive tools for supervised and unsupervised learning tasks, including classification, regression, clustering, and dimensionality reduction. Use it to build robust, production-ready ML pipelines, perform rigorous model evaluation, and preprocess complex datasets for various data science applications.

Seaborn is a high-level Python visualization library designed for creating publication-quality statistical graphics. It facilitates dataset-oriented plotting, multivariate analysis, and complex statistical visualizations (like KDEs, distributions, and relationships) directly from Pandas DataFrames with minimal code. It builds upon Matplotlib to provide semantic mapping and statistical awareness.

The Azure CLI command group for managing Azure Container Registry (ACR). This tool allows users to perform the entire ACR lifecycle, including creating registries, authenticating credentials, building and pushing container images (using cloud builds), importing images from other sources, and configuring advanced features like geo-replication, private endpoints, and webhooks. Essential for CI/CD pipelines and container deployment workflows in Azure.

This SDK allows asynchronous Python programming to control a live web browser, simulating user interactions for web automation, testing, and data extraction. Users can navigate pages, locate elements, fill forms, click buttons, and capture snapshots of the current page's content. It enforces a 'perceive → act → verify' cycle, making it ideal for building robust web scrapers and end-to-end testing tools.

This skill helps developers and QA engineers transform vague, intermittent, or poorly documented bug reports into a minimal, reproducible, and evidence-backed brief. It guides the user to isolate the exact failure conditions, separate expected outcomes from actual errors, and reduce the issue to the smallest safe failing fixture, ensuring diagnosis occurs before premature repair.

A comprehensive, 10-phase methodology for authorized security assessment of modern APIs, including REST, GraphQL, WebSocket, and SOAP. This guide covers the entire testing lifecycle—from endpoint discovery and authentication bypass (JWT/OAuth 2.0) to sophisticated authorization flaws (BOLA/IDOR/BFLA), input validation, rate limiting, and CI/CD integration testing.

This utility packages multiple independent FHIR R4 resources into a single, valid Transaction Bundle. It automatically handles deterministic URN UUID generation and resolves internal cross-references, making the bundle immediately ready for POSTing to a FHIR server. This is crucial for maintaining data integrity and interoperability when submitting multiple related clinical resources.

This adapter provides professional AI audio generation capabilities, supporting voiceovers, music, and sound effects through OpenRouter. Designed for OpenSquilla compatibility, it handles complex API contracts, including streaming data and outputting browser-playable WAV files, making it ideal for web content enrichment.

This skill provides a comprehensive checklist for auditing de-identified Protected Health Information (PHI) against the 18 categories required by HIPAA Safe Harbor (45 CFR 164.514(b)(2)). It maps detected PII entities to these categories, identifies gaps (e.g., age > 89, rare geography), and guides the assessment of residual re-identification risk. This is essential for proving the completeness and compliance of de-identification efforts.

This skill audits OpenMed NER or de-identification models to detect performance disparities across sensitive demographic subgroups (e.g., sex, age, race). It calculates metrics like per-group recall and leakage disparity, helping users identify instances of 'under-protection' before deployment, ensuring equitable AI governance and compliance.

This skill automates the creation of comprehensive Model Cards for OpenMed clinical NER or de-identification models. It gathers data from various OpenMed evaluation reports (e.g., `GateReport`, `fairness_report`, `error_report`) to structure critical governance information, including intended use, quantitative performance metrics, subgroup analysis, limitations, and required medical-device disclaimers. It ensures documentation is reproducible and compliant for clinical AI deployment.

This skill provides an end-to-end workflow for creating a complete, local multimedia webpage project. Users only need to define the topic, target audience, visual style, and media preferences. The system automates the entire process, including requirement framing, content research, media acquisition (images, audio, video), code generation, project packaging, validation, and delivering comprehensive usage guides.