Claude Skills

Statistical and quality drift detection for LLM applications. Use when monitoring model quality degradation, input distribution shifts, or output pattern changes over time.

Building MCP (Model Context Protocol) servers for Claude extensibility. Use when creating MCP servers, building custom Claude tools, extending Claude with external integrations, or developing tool packages for Claude Desktop.

API versioning strategies including URL path, header, and content negotiation. Use when migrating v1 to v2, handling breaking changes, implementing deprecation or sunset policies, or managing backward compatibility.

Data visualization with Recharts 3.x including responsive charts, custom tooltips, animations, and accessibility for React applications. Use when building charts or dashboards with Recharts.

Multi-PR development for large features. Stack dependent PRs, manage rebases, and get faster reviews on smaller changes. Use when creating stacked PRs.

Use when building Next.js 16+ apps with React Server Components. Covers App Router, streaming SSR, Server Actions, and React 19 patterns for server-first architecture.

SQLAlchemy 2.0 async patterns with AsyncSession, async_sessionmaker, and FastAPI integration. Use when implementing async database operations, connection pooling, or async ORM queries.

Strawberry GraphQL library for Python with FastAPI integration, type-safe resolvers, DataLoader patterns, and subscriptions. Use when building GraphQL APIs with Python, implementing real-time features, or creating federated schemas.

Advanced pytest patterns including custom markers, plugins, hooks, parallel execution, and pytest-xdist. Use when implementing custom test infrastructure, optimizing test execution, or building reusable test utilities.

HyDE (Hypothetical Document Embeddings) for improved semantic retrieval. Use when queries don't match document vocabulary, retrieval quality is poor, or implementing advanced RAG patterns.

Code splitting and lazy loading with React.lazy, Suspense, route-based splitting, intersection observer, and preload strategies for optimal bundle performance. Use when implementing lazy loading or preloading.

Comprehensive test execution with parallel analysis and coverage reporting. Use when running test suites or troubleshooting failures with the run-tests workflow.

Multi-PR development for large features. Stack dependent PRs, manage rebases, and get faster reviews on smaller changes. Use when creating stacked PRs.

Automatic GitHub issue progress updates from commits and sub-task completion. Use when tracking issue progress from commits or automating status updates.

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

Create Manim animations for demo videos. Use when visualizing agent workflows, skill pipelines, or architecture diagrams as animated MP4 overlays

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

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

Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, constructing context from retrieved documents, adding citations, or implementing hybrid search.