Guides agents through Delta Lake and medallion-style lakehouse design. Use when building or modifying bronze, silver, and gold layers, Delta Lake mutation patterns, streaming-to-batch lakehouse flows, or Databricks-centered serving architectures.
Guides agents through DuckDB-based local analytics and development workflows. Use when prototyping models locally, validating transformations, reproducing data issues quickly, or building lightweight analytical tooling without a full warehouse.
Guides agents through operating, hardening, and modernizing enterprise ETL and integration stacks such as Informatica, Talend, DataStage, SSIS, and Matillion. Use when legacy mappings, job orchestration, migration, or coexistence with modern lakehouse patterns must be handled safely.
Guides agents through ESG, sustainability, and regulatory reporting data products. Use when building governed metrics, traceable evidence, and audit-ready data pipelines for frameworks such as CSRD/ESRS, BRSR, climate disclosures, or similar sustainability reporting obligations.
Guides agents through ETL, ELT, and transformation-modernization decisions. Use when choosing execution boundaries, redesigning transformation layers, or moving from legacy ETL estates to warehouse- or lakehouse-centered ELT patterns.
Guides agents through machine-learning data pipelines and feature serving workflows. Use when designing feature generation, offline and online consistency, training-serving parity, point-in-time correctness, or ML-oriented data product contracts.
Guides agents through file-based and partner-feed ingestion workflows. Use when landing data from SFTP, managed file transfer, shared buckets, recurring flat files, manifests, or externally supplied feeds that need validation, replay safety, and publish discipline.
Guides agents through AWS-native data catalog and lake governance workflows. Use when designing or reviewing Glue Data Catalog, Lake Formation permissions, governed sharing, metadata quality, and access boundaries for S3, Athena, Redshift, EMR, or Glue pipelines.
Guides agents through data-quality frameworks such as Great Expectations, Deequ, and Cuallee. Use when implementing framework-based validation suites, reusable checks, or evidence-driven data-quality enforcement.
Guides agents through production data incidents. Use when a pipeline fails, publishes bad data, misses an SLA, partially loads, corrupts state, or requires rollback, replay, or stakeholder communication.
Guides agents through Java-based data engineering services and processors. Use when building connectors, ingestion services, stream processors, metadata services, JVM batch tools, or operational integrations in Java.
Enforces production Kafka guardrails including non-breaking schema evolution, dead-letter queues for poison messages, and acks=all producer durability. Use when designing or changing Kafka topics, producers, consumers, schema registry policies, or streaming recovery paths.
Security middleware for MCP servers protecting LLM agents from prompt injection, resource exhaustion, and PII leakage. Runs locally from the mcp-bastion-python Python package.
Guides work on the kafka-mcp-enterprise reference server (KIP-1318 / KAFKA-20436): run tests, stdio MCP, security pipeline, examples, and PyPI packaging. Use when the user mentions Kafka MCP, KIP-1318, kafkamcp, tools/call, DLP, approval tokens, or this repository.
Creates or fixes production-grade examples under examples/0N/ with README, run.py, and real-world data/ fixtures for the Kafka MCP KIP-1318 reference. Use when adding demos, scenarios, or sample JSONL data.
Reviews Kafka MCP changes against the KIP-1318 fail-closed pipeline, DLP, approval, taint honesty, scopes, breakers, and secure-by-default tool exposure. Use when reviewing PRs, security questions, or hardening this repo.
Instructions for vaquarkhan/kafka-mcp-enterprise-server, covering agents.md - kafka mcp enterprise (kip-1318 reference), what this repo is, non-negotiables, layout and commands agents should run.
Load skills/using-platform-engineering-agent-skills/SKILL.md and produce a platform contract: tenants, SLOs, compliance tier, RBAC boundaries, and GitOps promotion path.