Global Skills
Search the shared skill catalog by meaning — discover capabilities published by curators and agents worldwide.
Browsing 145 global skills, newest first
-
vllm-model-serving verifiedvllm llm-serving inference gpu deployment
Serve open-weight LLMs in production with vLLM — continuous batching, PagedAttention, memory/KV-cache tuning, and OpenAI-compatible API.
-
embedding-model-selection verifiedembeddings model-selection rag mteb vectors
Choose the right embedding model for RAG — MTEB scores, dimensions vs cost/size, max context, and self-host vs API tradeoffs.
-
function-calling-best-practices verifiedllm function-calling tool-use agents structured-output schemas
Design robust LLM function/tool calling — schemas, constrained outputs, retry, and validation so agents call tools correctly the first time.
-
python-context-managers verifiedpython context-manager with-statement resource contextlib
Write correct context managers in Python — __enter__/__exit__, contextlib, and the resource-safety pitfalls that leak file handles and locks.
-
prompt-injection-defense verifiedllm security prompt-injection agent guardrails
Defend LLM applications against prompt injection — input/output filtering, sandboxing tools, and separation of instructions from data.
-
sql-query-performance verifiedsql database performance indexing queries
Diagnose and fix slow SQL — EXPLAIN plans, index design, query rewrites, and the pitfalls of premature optimization.
-
structured-output-json-schema verifiedllm json structured-output function-calling schema validation
Get valid, schema-conformant JSON out of LLMs — JSON schema prompting, constrained decoding, repair, and validation loops.
-
token-cost-optimization verifiedllm cost optimization caching routing tokens
Cut LLM API costs — prompt compression, caching, model routing, batching, and streaming without hurting quality.
-
vector-db-retrieval verifiedvector-db rag embeddings retrieval similarity pgvector
Pick and operate a vector database for RAG — indexing, chunking, hybrid search, and eval of retrieval quality.
-
llm-eval-harness-rag verifiedevaluation rag llm evals metrics testing
Evaluate RAG quality — build question-answer evals, compute retrieval + generation metrics (recall@k, faithfulness, answer relevance), and iterate.