Claude Skills

LangGraph conditional routing patterns. Use when implementing dynamic routing based on state, creating branching workflows, or building retry loops with conditional edges.

gRPC with Python using grpcio and protobuf for high-performance microservice communication. Use when implementing service-to-service APIs, streaming data, or building polyglot microservices requiring strong typing.

Event sourcing patterns for storing state as a sequence of events. Use when implementing event-driven architectures, CQRS, audit trails, or building systems requiring full history reconstruction.

Authentication and authorization patterns. Use when implementing login flows, JWT tokens, session management, password security, OAuth 2.1, Passkeys/WebAuthn, or role-based access control.

Use when completing tasks, code reviews, or deployments to verify work with evidence. Collects test results, build outputs, coverage metrics, and exit codes to prove work is complete.

SQL and NoSQL schema design with normalization, indexing, and migration patterns. Use when designing database schemas, creating tables, optimizing slow queries, or planning database migrations.

Multi-directory context patterns for monorepos. Use when working with --add-dir, per-service CLAUDE.md, or separating root vs service context

shadcn/ui component patterns including CVA variants, OKLCH theming, cn() utility, and composition. Use when adding shadcn components, building variant systems, or customizing themes.

Alembic migration patterns for SQLAlchemy 2.0 async. Use when creating database migrations, managing schema versions, handling zero-downtime deployments, or implementing reversible database changes.

GitHub release workflow with semantic versioning, changelogs, and release automation using gh CLI. Use when creating releases, tagging versions, or publishing changelogs.

Anthropic's Contextual Retrieval technique for improved RAG. Use when chunks lose context during retrieval, implementing hybrid BM25+vector search, or reducing retrieval failures.

Domain-Driven Design tactical patterns for complex business domains. Use when modeling entities, value objects, domain services, repositories, or establishing bounded contexts.

Text embeddings for semantic search and similarity. Use when converting text to vectors, choosing embedding models, implementing chunking strategies, or building document similarity features.

High-performance LLM inference with vLLM, quantization (AWQ, GPTQ, FP8), speculative decoding, and edge deployment. Use when optimizing inference latency, throughput, or memory.

LLM fine-tuning with LoRA, QLoRA, DPO alignment, and synthetic data generation. Efficient training, preference learning, data creation. Use when customizing models for specific domains.

React Hook Form v7 with Zod validation, React 19 useActionState, Server Actions, field arrays, and async validation. Use when building complex forms, validation flows, or server action forms.

Input validation and sanitization patterns. Use when validating user input, preventing injection attacks, implementing allowlists, or sanitizing HTML/SQL/command inputs.

LLM observability platform for tracing, evaluation, prompt management, and cost tracking. Use when setting up Langfuse, monitoring LLM costs, tracking token usage, or implementing prompt versioning.

LLM output evaluation and quality assessment. Use when implementing LLM-as-judge patterns, quality gates for AI outputs, or automated evaluation pipelines.