Skill UI

Automates the creation of Airflow DAGs for ETL and streaming data workflows, offering best-practice guidance, production-ready code samples, and validation against common pipeline standards.

A comprehensive guide to building production-ready Apache Airflow Directed Acyclic Graphs (DAGs). This skill covers best practices for operators, sensors, testing, deployment, and designing robust data pipelines. Use this when orchestrating complex workflows, managing ETL processes, or ensuring reliable batch job execution in a production environment.

This comprehensive guide identifies and explains common anti-patterns, gotchas, and integration mistakes when using Clay's data enrichment platform. It details the root causes of credit waste, workflow failures, and data loss, providing actionable fixes for auditing configurations, onboarding new team members, or optimizing existing pipelines.

Generates Python code and workflows for collaborative, content-based, or hybrid recommendation models, handling data prep, training, evaluation, and scalability so Claude can deliver tailored suggestions across domains.

This skill provides a comprehensive guide to configuring event-driven workflows and robust notification systems for Databricks jobs. It covers setting up various notification destinations (Slack, Teams, Email, PagerDuty) and triggering alerts based on job lifecycle events (success, failure, start). Furthermore, it demonstrates advanced monitoring using system audit tables and creating automated SQL alerts for critical data pipeline monitoring.

Enables Claude to apply anomaly-detection-system workflows for spotting outliers, fraud, or unusual patterns across datasets, selecting tailored algorithms like Isolation Forest and summarizing deviations for any data monitoring or security use case.

Automated guidance for configuring and applying early stopping callbacks across ML training workflows, covering best practices, code generation, and validation for PyTorch, TensorFlow, and scikit-learn experiments.

A comprehensive workflow for executing advanced, semantic web searches using Exa. This tool moves beyond simple keyword matching, enabling deep context retrieval by understanding the intent behind the query. Key features include RAG context retrieval, content extraction (summaries, highlights, full text), and robust filtering by date range, specific domains, and content categories. Ideal for building knowledge base search features and complex research pipelines.

This advanced workflow provides comprehensive meeting intelligence by allowing users to search across stored transcripts using keywords and date filters. It integrates the AskFred AI assistant for natural language Q&A over single or cross-meeting data. Furthermore, it aggregates detailed meeting analytics, providing key metrics such as total duration, action items, and top keywords for robust reporting and knowledge retrieval.

This skill manages the complete lifecycle of Fireflies.ai meeting transcripts. It allows users to fetch raw data, export in various formats (JSON, CSV, SRT), sanitize sensitive personal information (PII Redaction), and enforce data retention policies to ensure compliance with regulations like GDPR and CCPA. Ideal for data governance and compliance workflows.

Automated assistance for Flink job creation in data pipelines, triggered by Flink job creator requests. Guides ETL, streaming, and workflow orchestration, generates production-ready code/configurations, and validates outputs against industry standards.

Configure automated Continuous Integration and Continuous Deployment (CI/CD) pipelines for Juicebox AI data analysis integrations. This setup utilizes GitHub Actions to run comprehensive unit tests (with mocked datasets) and integration tests (connecting to live APIs) on every PR and merge to main. It ensures that data upload logic, analysis execution, and result parsing workflows are robust and reliable before deployment.