langsmith-observability

This skill queries Railway service metrics including CPU, memory, network, and disk usage to monitor performance and debug issues. It's triggered when developers ask about resource utilization or service performance, and requires environment and service IDs from the Railway CLI. The skill provides actionable insights through Bash commands that fetch real-time analytics data.

This skill benchmarks code generation models using industry-standard evaluations like HumanEval and MBPP across multiple programming languages. It calculates pass@k metrics for comparing model performance, testing multi-language support, and measuring code quality. Developers should use it when rigorously evaluating or comparing coding models, as it's the same tool powering HuggingFace's code leaderboards.

This skill provides high-performance tokenization using HuggingFace's Rust-based library, processing 1GB of text in under 20 seconds. It supports BPE, WordPiece, and Unigram algorithms while enabling custom tokenizer training and alignment tracking. Use it when you need production-fast tokenization or to build custom tokenizers integrated with the transformers ecosystem.

The qdrant-vector-search skill provides a high-performance vector similarity search engine for building production RAG systems. It enables fast nearest neighbor search, hybrid search with filtering, and scalable vector storage powered by Rust. Use it when you need low-latency semantic search with horizontal scaling capabilities and full data control.