Data Engineering

Comprehensive DevOps and deployment workflow that orchestrates infrastructure automation, CI/CD pipelines, container orchestration, and cloud deployment. Handles everything from infrastructure as code and pipeline setup to monitoring, scaling, and disaster recovery.

Extract Case/Support Ticket data using the async pipeline with denormalized medallion architecture. Use this skill to extract case data into Bronze layer with proper linkages to Company and Person entities.

Use Astro's modern web development stack including TypeScript, Tailwind CSS, Content Collections, islands architecture, and performance-first deployment practices. Use this skill when selecting technologies, configuring integrations, choosing deployment platforms, or making architectural decisions about the tech stack. When working on Astro configuration and integrations setup, choosing between SSG/hybrid/SSR rendering modes, selecting UI frameworks for interactive islands (React, Vue, Svelte), configuring Tailwind CSS or styling solutions, setting up Content Collections for type-safe content, choosing deployment adapters (Vercel, Netlify, Cloudflare), configuring testing tools (Vitest, Playwright), implementing performance optimization strategies, or adding third-party integrations and plugins.

PowerShell build automation tool for creating task-based build scripts. Use when Claude needs to create, modify, or troubleshoot psake build scripts (psakefile.ps1), automate builds for .NET/Node.js/Docker projects, set up CI/CD pipelines with psake (GitHub Actions, Azure Pipelines, GitLab CI), or work with PowerShell-based build automation. Triggers include mentions of psake, psakefile, PowerShell build scripts, Invoke-psake, or build task dependencies.

Creates sophisticated workflow cascades coordinating multiple micro-skills with sequential pipelines, parallel execution, conditional branching, and Codex sandbox iteration. Enhanced with multi-model routing (Gemini/Codex), ruv-swarm coordination, memory persistence, and audit-pipeline patterns for production workflows.

Google Cloud Platform services including GKE, Cloud Run, Cloud Storage, BigQuery, and Pub/Sub. Activate for GCP infrastructure, Google Cloud deployment, and GCP integration.

Data quality testing with dbt tests, Great Expectations, and monitoring.

Expert DevOps automation consultant for building production-grade CI/CD deployment pipelines using Vercel, GitHub Actions, and Railway. Implements build/test/preview/production workflows, automated rollbacks, canary deployments, blue-green strategies, environment promotion, secrets management, health checks, smoke testing, and live monitoring. Use when deploying web applications, setting up CI/CD pipelines, configuring automated deployments, implementing deployment strategies, managing production releases, or troubleshooting deployment issues.

Expert-level Google Cloud CLI (gcloud) skill for managing GCP resources. This skill should beused when working with gcloud commands, gcp, google cloud, cloud run, cloud scheduler, alloydb,cloud storage, gcs buckets, firebase deploy, gcloud auth, gcloud config, service accounts,workload identity federation, iam permissions, or artifact registry. Use this to install gcloudon macOS, Windows, or Linux. Use this to manage multi-account configuration of GCP with gcloud.Use this to configure authentication on GCP with gcloud for OAuth, service accounts, andWorkload Identity Federation (WIF). Use this to set up IAM roles, permissions, and governance.Use this to deploy applications to Cloud Run or Firebase. Use this to manage database instancesincluding AlloyDB and Cloud SQL. Use this to configure GitHub Actions or Cloud Build CI/CDpipelines. Use this to set up Docker container deployments. Use this to write bash scripts forGCP automation. Use this to manage git-triggered deployments or configure API authent

RNBT 아키텍처 패턴에 맞는 완전한 대시보드 페이지를 생성합니다. Master/Page 레이어, 여러 컴포넌트, Mock 서버, datasetList.json을 포함한 전체 구조를 생성합니다. Use when creating dashboard pages, implementing Master/Page architecture, or setting up complete page structures with multiple components.

Diagnose Buildkite build failures by fetching build logs and analyzing errors.Use this skill when the user wants to:- Investigate why a build failed- Get logs from failed jobs- List recent builds for a pipeline- Check build status or annotationsTriggers: "why did the build fail", "check the CI", "buildkite logs", "failed build", "build is red", "what broke the build"

Apache Airflow, dbt, Prefect, Dagster, and modern data orchestration for production data pipelines

Multi-agent sistem mimarisi referansi. Use when working with agents, pipelines, or understanding the content generation workflow.

Neon serverless Postgres with autoscaling, instant database branching, and zero-downtime deployments. Use when building serverless applications, implementing database branching for dev/staging, or deploying with Vercel/Netlify.

This skill should be used when the user asks to "create MongoDB model", "define Beanie document", "write MongoDB query", "create aggregation pipeline", "run database migration", "index MongoDB collection", or mentions Beanie, Motor, MongoDB documents, or async database operations. Provides MongoDB/Beanie ODM patterns for FastAPI.

Write Python code to interact with ClickHouse using clickhouse-connect. Use when creating ETL scripts, data pipelines, analytics applications, or any Python code that needs to query or insert data into ClickHouse.

PROACTIVE skill - STOP and invoke BEFORE writing dbt SQL. Validates models against coding conventions for staging, integration, and warehouse layers. Covers naming, SQL structure, field conventions, testing, and documentation. CRITICAL - When about to write .sql files in models/, invoke this skill first, write second. Supports project-specific convention overrides and sqlfluff integration.

Comprehensive repository initialization and scaffolding for new projects. Use when setting up a new repository from scratch with git, GitHub, CI/CD workflows, branch protection, validation checks (format, lint, type-check, tests, builds), git hooks (husky/lefthook), GitHub Actions for PR and main branch validation, automated versioning and tagging, and project-specific release workflows. Ideal for solo developers who want production-ready repository setup including (1) Git initialization with main branch, (2) GitHub repository creation and configuration, (3) Branch protection rules, (4) PR workflow with squash merging and auto-delete branches, (5) Comprehensive validation checks, (6) Git hooks for pre-commit and pre-push validation, (7) GitHub Actions CI/CD pipelines, (8) Automated releases with GitHub Releases integration.

Data pipelines, ETL/ELT systems, workflow orchestration, and data modeling

Execute SQL queries against Databricks using the DBSQL MCP server. Use when querying Unity Catalog tables, running SQL analytics, exploring Databricks data, or when user mentions Databricks queries, SQL execution, Unity Catalog, or data warehouse operations. Handles query execution, result formatting, and error handling.