Claude Skills

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

Use when backing up, restoring, or validating golden datasets. Prevents data loss and ensures test data integrity for AI/ML evaluation systems.

Use when validating golden dataset quality. Runs schema checks, duplicate detection, and coverage analysis to ensure dataset integrity for AI evaluation.

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.

Visualize local knowledge graph as a Mermaid diagram with 8 entity types and 8 relation types from the decisions memory store.

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.

LangGraph Functional API with @entrypoint and @task decorators. Use when building workflows with the modern LangGraph pattern, enabling parallel execution, persistence, and human-in-the-loop.

LangGraph human-in-the-loop patterns. Use when implementing approval workflows, manual review gates, user feedback integration, or interactive agent supervision.

LangGraph parallel execution patterns. Use when implementing fan-out/fan-in workflows, map-reduce over tasks, or running independent agents concurrently.

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

Use when deploying to Cloudflare Workers, Vercel Edge, or Deno Deploy. Covers edge middleware, streaming, runtime constraints, and globally distributed low-latency patterns.

Security patterns for LLM integrations including prompt injection defense and hallucination prevention. Use when implementing context separation, validating LLM outputs, or protecting against prompt injection attacks.

LLM streaming response patterns. Use when implementing real-time token streaming, Server-Sent Events for AI responses, or streaming with tool calls.

Testing patterns for LLM-based applications. Use when testing AI/ML integrations, mocking LLM responses, testing async timeouts, or validating structured outputs from LLMs.

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

CLIP, SigLIP 2, Voyage multimodal-3 patterns for image+text retrieval, cross-modal search, and multimodal document chunking. Use when building RAG with images, implementing visual search, or hybrid retrieval.

[GIT] PR review with parallel specialized agents. Use when reviewing pull requests or code.

5 Whys, Fishbone diagrams, Fault Tree Analysis, and systematic debugging approaches. Use when investigating bugs, analyzing incidents, or identifying root causes of problems.

Video rhythm and timing for maximum engagement. Use when planning cut frequency, optimizing retention, or adapting pacing for different platforms