convex-self-hosting
Guides self-hosted Convex deployment, authentication setup, environment configuration, troubleshooting, and production deployment considerations.
ml-engineering
Use when "deploying ML models", "MLOps", "model serving", "feature stores", "model monitoring", or asking about "PyTorch deployment", "TensorFlow production", "RAG systems", "LLM integration", "ML infrastructure"
google-cloud-configs
Google Cloud Platform configuration templates for BigQuery ML and Vertex AI training with authentication setup, GPU/TPU configs, and cost estimation tools. Use when setting up GCP ML training, configuring BigQuery ML models, deploying Vertex AI training jobs, estimating GCP costs, configuring cloud authentication, selecting GPUs/TPUs for training, or when user mentions BigQuery ML, Vertex AI, GCP training, cloud ML setup, TPU training, or Google Cloud costs.
stagehand-expert
Master Architect in Stagehand V3. Expert in proactive code research, resilient automation, and high-precision AI agent orchestration.
aws-sagemaker
Amazon SageMaker for building, training, and deploying machine learning models. Use for SageMaker AI endpoints, model training, inference, MLOps, and AWS machine learning services.
ml-ops-engineer
Expert MLOps engineering covering model deployment, ML pipelines, model monitoring, feature stores, and infrastructure automation.
kubectl-ai
Especialista em Kubernetes com integração kubectl-ai para gerar, explicar e otimizar recursos Kubernetes usando IA
auto-claude-build
Auto-Claude autonomous build system. Use when running builds, understanding agent workflow, managing parallel execution, or troubleshooting build issues.
railway-troubleshooting
Railway Docker cache troubleshooting for Dr. Sophia AI deployments. Covers cache detection, force rebuild methods, version verification, deployment validation. Use when Railway shows old code after deployment, deployments not updating, Docker cache issues, or version mismatches between local and deployed code.
moai-baas-vercel-ext
Enterprise Vercel Edge Platform with AI-powered deployment, Context7 integration
cloudrun-development
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.
adr-creation
Orchestrator skill for the Architecture Decision Record (ADR) creation process based on OODA Loop. Representative use cases include (1) Defining the specific scope and components of the system to be implemented next, (2) Evaluating technical trade-offs and selecting the optimal implementation strategy (e.g., library choice or data patterns), and (3) Formalizing architectural decisions as a mandatory blueprint before proceeding to structural design (arch-creation).
oracle-intelligence
Oracle Cloud Infrastructure expertise for enterprise AI and cloud architecture
ralph-prompt-project
Generate Ralph-compatible prompts for entire projects from scratch. Creates comprehensive prompts with architecture phase, implementation phases, testing, and documentation. Use when building complete applications, libraries, CLI tools, or any greenfield project requiring end-to-end development.
project-manager
Orchestrate multi-agent development workflows. Use when starting a new feature to coordinate architecture design, implementation, code review, and release through specialized sub-agents.
claude-code-telemetry-enable
Enable and configure Claude Code OTEL telemetry for local or Railway observability stacks. Use when setting up Claude Code to send metrics, logs, and traces to observability backends.
runpod-deployment
Deploy GPU workloads to RunPod serverless and pods - vLLM endpoints, A100/H100 setup, scale-to-zero, cost optimization. Use when: deploy to RunPod, GPU serverless, vLLM endpoint, scale to zero, A100 deployment, H100 setup, serverless handler, GPU cost optimization.
adr
Research architecture decisions and create Architecture Decision Records (ADRs). Use when facing complex technical choices requiring deep research, options analysis, and formal documentation. Treats user as CTO for collaborative decision-making. Supports evolutionary architecture - can challenge prior decisions when evidence warrants.
dispatching-parallel-agents
This skill should be used when managing "concurrent agent execution", "parallel task processing", "load balancing across agents", "resource optimization", "high-throughput workflows", or when orchestrating multiple agents working simultaneously on different aspects of complex projects.
testing
Test and verify AI orchestrator features using CLI runner, unit tests, and E2E tests. ALWAYS use this skill when: implementing new features, fixing bugs, making changes to agents/orchestrator/TUI, or when asked to verify something works. Claude MUST test changes before marking tasks complete.
guardian
Automatic quality gate and session health monitor. Spawns focused Haiku agents for code review and task planning when degradation detected. Validates suggestions against Oracle knowledge. Learns from user feedback to adjust sensitivity. Uses minimal context passing. Integrates with oracle and evaluator.
