Claude Skills

Production hybrid search combining PGVector HNSW with BM25 using Reciprocal Rank Fusion. Use when implementing hybrid search, semantic + keyword retrieval, vector search optimization, metadata filtering, or choosing between HNSW and IVFFlat indexes.

Provider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching system prompts, or reducing token costs for repeated prefixes.

Comprehensive prompt engineering with Chain-of-Thought, few-shot learning, prompt versioning, and optimization. Use when designing prompts, improving accuracy, managing prompt lifecycle.

Property-based testing with Hypothesis for discovering edge cases automatically. Use when testing invariants, finding boundary conditions, implementing stateful testing, or validating data transformations.

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.

Database version control and change management patterns. Use when managing schema history, coordinating database changes across environments, implementing audit trails, or versioning database objects.

CSS Scroll-Driven Animations with ScrollTimeline, ViewTimeline, parallax effects, and progressive enhancement for performant scroll effects. Use when implementing scroll-linked animations or parallax.

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.

View Transitions API for smooth page transitions, shared element animations, and SPA/MPA navigation in React applications. Use when adding view transitions or page animations.

Deep codebase exploration with parallel specialized agents. Use when exploring a repo, finding files, or discovering architecture with the explore agent.

FastAPI 2026 advanced patterns including lifespan, dependencies, middleware, and Pydantic settings. Use when configuring FastAPI lifespan events, creating dependency injection, building Starlette middleware, or managing async Python services with uvicorn.

LLM cost tracking with Langfuse for cached responses. Use when monitoring cache effectiveness, tracking cost savings, or attributing costs to agents in multi-agent systems.

Integration testing patterns for APIs and components. Use when testing component interactions, API endpoints with test databases, or service layer integration.

Enforce testing best practices - AAA pattern, naming conventions, isolation, coverage thresholds. Blocks non-compliant tests. Use when writing or reviewing tests.

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

Unit testing patterns and best practices. Use when writing isolated unit tests, implementing AAA pattern, designing test isolation, or setting coverage targets for business logic.

Consumer-driven contract testing with Pact for API compatibility. Use when testing microservice integrations, verifying API contracts, preventing breaking changes, or implementing provider verification.

LLM guardrails with NeMo, Guardrails AI, and OpenAI. Input/output rails, hallucination prevention, fact-checking, toxicity detection, red-teaming patterns. Use when building LLM guardrails, safety checks, or red-team workflows.

Vercel agent-browser CLI for headless browser automation. 93% less context than Playwright MCP. Snapshot + refs workflow with @e1 @e2 element references. Use when automating browser tasks, web scraping, form automation, or content capture.