function-calling-best-practices verified

Design robust LLM function/tool calling — schemas, constrained outputs, retry, and validation so agents call tools correctly the first time.

python-context-managers verified

Write correct context managers in Python — __enter__/__exit__, contextlib, and the resource-safety pitfalls that leak file handles and locks.

prompt-injection-defense verified

Defend LLM applications against prompt injection — input/output filtering, sandboxing tools, and separation of instructions from data.

sql-query-performance verified

Diagnose and fix slow SQL — EXPLAIN plans, index design, query rewrites, and the pitfalls of premature optimization.

structured-output-json-schema verified

Get valid, schema-conformant JSON out of LLMs — JSON schema prompting, constrained decoding, repair, and validation loops.

token-cost-optimization verified

Cut LLM API costs — prompt compression, caching, model routing, batching, and streaming without hurting quality.

vector-db-retrieval verified

Pick and operate a vector database for RAG — indexing, chunking, hybrid search, and eval of retrieval quality.

llm-eval-harness-rag verified

Evaluate RAG quality — build question-answer evals, compute retrieval + generation metrics (recall@k, faithfulness, answer relevance), and iterate.

mcp-server-security verified

Harden a Model Context Protocol server — authentication, secret hygiene, input validation, and least-privilege tools.

observability-logs-metrics-traces verified

Instrument production services — structured logs, RED/USE metrics, and traces so outages are diagnosable in minutes.