Skill UI

Feature Engineering Toolkit automates creating, selecting, and transforming dataset features to improve machine learning models; use it whenever you need new interactions, automatic selection, scaling, or encoding to boost accuracy and interpretability.

This guide provides comprehensive error handling and debugging steps for the OpenEvidence API. It covers common failure points—including authentication issues (401, 403), query validation errors (422), rate limiting (429), and service timeouts (408). Users can learn how to diagnose the root cause of connection failures and refine their clinical queries to maximize data retrieval accuracy.

Optimizes deep learning models by analyzing architecture, data, and metrics to select optimizers, learning rate schedules, and regularization strategies, then outputs optimized code and evaluates accuracy, time, and resource usage.

A comprehensive toolkit designed to manage the complex data flow associated with Perplexity search workflows. This skill implements critical security measures, including PII sanitization in user queries, validates external citations for accuracy, optimizes performance via result caching with freshness policies, and manages conversation context to maintain coherence and reliability. Essential for building robust, compliance-aware AI applications.

A comprehensive guide to identifying and avoiding common integration mistakes and anti-patterns when using the Perplexity Sonar API. It covers critical best practices such as correctly handling citations, setting maximum token limits, utilizing recency filters, and optimizing API calls to ensure cost efficiency and data accuracy. Essential for code review and developer onboarding.

A practical decision framework for determining whether to use regular expressions or Large Language Models (LLMs) when parsing structured text (e.g., forms, quizzes, invoices). It recommends starting with deterministic, low-cost regex for 95-98% of structured data, and only invoking expensive LLM calls for identifying and validating ambiguous edge cases, optimizing both cost and accuracy.

This skill provides sophisticated project estimation by adapting to human-only, hybrid, or agent-first development modes. It uses research-backed PERT statistics and confidence bands (P50, P75, P90) to forecast development timelines for tasks, backlogs, and capacity planning. It continuously calibrates estimates based on actual completion data, ensuring accuracy in AI-assisted and hybrid development environments.

This skill guides SOC analysts and detection engineers on how to correlate complex, multi-stage attacks within the IBM QRadar SIEM platform. It covers advanced usage of AQL (Ariel Query Language) for deep event investigation, building custom correlation rules (Building Blocks and Offenses), and cross-source data correlation (e.g., auth failures with network flows). It is essential for reducing false positives and improving threat detection accuracy.

A comprehensive guide for Security Operations Center (SOC) analysts on reducing false positive alerts in SIEM systems. Techniques include systematic threshold tuning, refining correlation logic, implementing allowlisting, and enriching data with threat intelligence to combat alert fatigue and improve detection accuracy.

An automated verification system designed for critical healthcare application deployments (EMR/EHR). This harness enforces stringent patient safety standards by running multiple mandatory test gates, including Clinical Decision Support System (CDSS) accuracy, Protected Health Information (PHI) leakage prevention, and data integrity checks. A single failure in critical gates automatically blocks deployment, ensuring regulatory compliance and optimal patient safety in the CI/CD pipeline.

This tool is designed to enhance lead intelligence by processing and analyzing prospect data. It helps users gain deep insights into potential customers, improving targeting accuracy, optimizing sales pipelines, and refining marketing strategies for business growth.

This skill provides comprehensive commands to manage the entire AI model evaluation lifecycle using Arize. Users can list, retrieve metadata, and export results from experiments. It is ideal for comparing multiple model runs, benchmarking performance against a dataset, and analyzing model accuracy using structured evaluation workflows (CRUD operations).