Build new data ingestion providers following the FF Analytics registry pattern. This skill should be used when adding new data sources (APIs, files, databases) to the data pipeline. Guides through creating provider packages, registry mappings, loader functions, storage integration, primary key tests, and sampling tools following established patterns.
Enterprise Neon Serverless PostgreSQL Platform with AI-powered database architecture, Context7 integration, and intelligent branching orchestration for scalable modern applications
Jenkins CI/CD pipelines for data platforms with Kubernetes pod agents. Use when creating Jenkinsfiles, implementing parallel linting stages (Ruff, Black, Mypy), DAG validation with DagBag, security scanning (Bandit, Safety, detect-secrets), deployment strategies (canary with error monitoring, blue-green), or setting up artifact management and DORA metrics tracking.
Manage Docker Spark infrastructure for local development or production (S3). Use this skill to start, stop, or check status of Spark clusters. Invoke with /spark-docker.
Neon serverless PostgreSQL specialist covering auto-scaling, database branching, PITR, and connection pooling. Use when building serverless apps needing PostgreSQL, implementing preview environments, or optimizing database costs.
Create CLI entrypoints for pipeline execution with local/SageMaker environment support and parallel processing. Use when user requests "CLI作成", "エントリーポイント", "entrypoint", "scripts/entrypoint.py", "コマンドライン実行", "local/sagemaker実行", "並列処理CLI", or needs to create command-line interfaces for data processing pipelines that support both local development and cloud (SageMaker) execution environments.
Interact with Dagster data orchestration platform running locally or on Kubernetes. Use when Claude needs to monitor Dagster runs, get run logs, list assets/jobs, materialize assets, launch jobs, or debug pipeline failures. Supports both local Dagster dev server and Kubernetes deployments where each job run is a separate pod.
Expert in building distributed systems using Dapr. Use this for implementing pub/sub, state management, jobs, and secrets abstraction.
Centralized management of machine learning models throughout their lifecycle, including versioning, metadata, and production deployment.
Pattern for building data source collectors that fetch, transform, and deduplicate incident data from external APIs. Use when adding new data sources, fixing collector bugs, or understanding the data pipeline.
Coordinate parallel autonomous operations. Use when running parallel features, managing concurrent work, coordinating multiple agents, or optimizing throughput.
Strategic orchestrator for PlasmaDX-Clean volumetric rendering project. Use when coordinating multi-agent tasks, making architectural decisions, enforcing quality gates, or managing complex rendering workflows across councils (rendering, materials, physics, diagnostics).
Complete deployment guide for Dr. Sophia AI on Railway. Covers environment-aware build system, frontend dist/ compilation, backend auto-deploy, Railway configuration, troubleshooting build/deployment issues. Use when deploying to Railway, building frontend for production, debugging deployment failures, or setting up environment variables.
Automatic task decomposition with parallel agent execution. Use when: breaking down complex tasks, parallel agent work, multi-file changes, optimizing execution time, task decomposition, understanding parallel execution phases.
Generate coherent stack candidates based on requirements. Use when user needs stack options, technology recommendations, or architecture patterns for their project.
Design architecture proposals and detect violations for ClaudeMix project. Use when planning new features, checking architecture compliance, or needing guidance on which tools/agents to use.
Orchestrate multi-agent development workflows. Use when starting a new feature to coordinate architecture design, implementation, code review, and release through specialized sub-agents.
Validate architecture/plan quality via claude-delegator (Plan Reviewer expert). Use after writing context.md for complex feature/refactor work.
AWS Prescriptive Guidance for best practices and architectural patterns. Use for AWS architecture recommendations, SageMaker AI endpoints guidance, deployment patterns, and AWS solution architectures.
Generate devcontainer configurations for Claude Code development environments. Use when setting up development containers with Claude Code and optional Codex CLI. Automatically detects marketplace.json for plugin marketplace configurations.
CloudBase Run backend development rules (Function mode/Container mode). Use this skill when deploying backend services that require long connections, multi-language support, custom environments, or AI agent development.
Comprehensive entity skill for breathe-together-v2. Create new entities, improve existing ones, debug issues, and systematically review all entities. Covers ECS Architecture, Triplex Integration, Performance Tuning, and Debug Tools. Includes 3 entity archetypes (Visual-Only, Simple ECS, Complex ECS), 4 guided workflows, prompt-to-update learning system, and real-world templates from the codebase.
Build AI agents with AWS Bedrock AgentCore. Use when developing agents on AWS infrastructure, creating tool-use patterns, implementing agent orchestration, or integrating with Bedrock models. Triggers on keywords like AgentCore, Bedrock Agent, AWS agent, Lambda tools.
