Data skills

This skill helps you implement accurate, validated JSON-LD schema markup to boost search visibility and rich results.

This skill helps you obtain AI-synthesized research with citations in structured JSON for pipelines, saving time and ensuring grounded web sources.

This skill helps you discover and compare skills from the skills.sh registry directly from your terminal, revealing installs and sources.

This skill helps you implement PCI DSS compliance, tokenization, encryption, and audit readiness for secure payment processing and data minimization.

This skill helps automate data visualization for exploratory data analysis, model performance, and business reporting, delivering publication-quality plots and

This skill guides roadmap planning and feature prioritization using RICE, MoSCoW, and Kano to maximize ROI and stakeholder alignment.

This skill helps you integrate Kafka with n8n for event-driven workflows, covering trigger, producer, retries, error handling, and no-code enrichment.

This skill designs Confluent Cloud architecture patterns including eCKU sizing, cluster linking, multi-region strategies, and Schema Registry HA.

This skill helps you design and optimize ksqlDB stream processing workflows with real-time queries, windowing, and materialized views across Kafka topics.

This skill detects diagram requests and delegates generation to the diagrams-architect agent, coordinating load context and saving results to the correct

This skill builds end-to-end computer vision pipelines for classification, detection, and segmentation using PyTorch/TensorFlow and transfer learning.

This skill automates browser tasks such as web scraping, form filling, and screenshot generation using Playwright, Puppeteer, and Selenium for reliable

This skill helps you compare and estimate cloud costs across AWS, Azure, and GCP using current 2025 pricing data.

This skill helps you design and troubleshoot Kafka Connect pipelines with source and sink connectors, Debezium CDC, and SMT transforms.

This skill helps manage machine learning model lifecycles by enabling versioning, staging, promotion, rollback, and lineage tracking.

This skill helps you design and optimize Kafka Streams topologies, including KStream, KTable, joins, windowing, and exactly-once semantics.

This skill helps you manage Confluent Schema Registry for Avro, Protobuf, and JSON Schema with evolution, compatibility, and validation guidance.

This skill analyzes increments by age, status, and activity to recommend archiving and keep workspace clean.

This skill helps you design and analyze experiments, perform causal inference, and forecast business metrics across time-series data.

This skill detects anomalies and outliers across data streams using statistical methods, isolation forests, and autoencoders to improve fraud, security, and

This skill guides building platform-agnostic DAG-based ML pipelines with Airflow, Dagster, Kubeflow, or Prefect for scalable ML workflows.