Skill UI

A structured runbook for handling Apollo.io API outages and production failures. It guides users through severity classification (P1-P4), quick diagnosis scripting, implementing circuit breakers, and graceful degradation strategies to maintain service availability during incidents.

This SDK provides comprehensive content moderation capabilities for Python applications using Azure AI. It allows developers to analyze text and images to detect harmful content across multiple categories, including hate speech, violence, sexual content, and self-harm. Key features include multi-severity classification, managing custom blocklists, and analyzing content from local files or URLs. Ideal for pre-moderating user-generated content (UGC) or AI outputs to ensure platform safety.

This SDK provides comprehensive content moderation capabilities for Python applications using Azure AI. It allows developers to analyze text and images to detect harmful content across multiple categories, including hate speech, violence, sexual content, and self-harm. Key features include multi-severity classification, managing custom blocklists, and analyzing content from local files or URLs. Ideal for pre-moderating user-generated content (UGC) or AI outputs to ensure platform safety.

Automates building and evaluating classification models by analyzing datasets, selecting features, tuning hyperparameters, and reporting metrics via the classification-model-builder plugin for supervised learning requests.

Provides comprehensive tools for managing enriched lead data in compliance with global privacy regulations like GDPR and CCPA. This skill guides practitioners through data classification (identifying PII sensitivity), input validation, deduplication, implementing data retention metadata, and anonymizing sensitive fields for secure reporting and analytics.

CLIP enables general-purpose vision-language tasks through zero-shot image classification, similarity scoring, semantic search, and content moderation using pretrained contrastive embeddings without fine-tuning.

This skill provides a comprehensive guide on implementing robust data governance patterns within Delta Lake, leveraging Unity Catalog. It covers essential compliance topics such as data classification tagging, handling GDPR 'right-to-deletion' requests for PII, and establishing automated data retention policies. Use this when designing secure, compliant, and auditable data pipelines in a data lake environment.

A comprehensive runbook for standardizing incident response to Deepgram production issues. It guides users through automated triage (checking status, API connectivity, and model performance), severity classification (SEV1-SEV4), and implementing mitigation strategies, including building fallback services and replaying failed requests to ensure business continuity during outages or degradation.

This specialist assists medical device manufacturers with FDA regulatory compliance. It helps determine submission pathways like 510(k), De Novo, and PMA based on device classification. It covers QMSR compliance, HIPAA requirements, and device cybersecurity standards. The tool runs compliance checkers and risk assessments to ensure adherence to 21 CFR regulations.

This comprehensive runbook guides incident response for Groq API failures. It covers triage steps, severity classification (P1-P4), troubleshooting decision trees (e.g., handling 429 errors or 5xx outages), and implementing immediate mitigations like model fallback or key rotation. Use this when responding to Groq outages to restore service stability.

A comprehensive framework for managing availability and reliability incidents (outages, degradations, failed deploys). It guides the entire lifecycle, from automated severity classification (SEV1-SEV4) and timeline reconstruction to multi-team coordination and structured post-incident review (PIR). Essential for SRE and DevOps teams leading major incident responses.

This skill provides a comprehensive, multi-phase guided workflow for professional incident response management. Following modern SRE principles and the Incident Command System (ICS), it guides users from initial detection and triage (P0-P3 classification) through deep investigation (observability, debugging, security checks), culminating in structured resolution and post-mortem analysis. Use this when managing critical system outages or performance degradation.