Event-driven script execution system in Claude Code that automatically runs shell commands in response to specific events, enabling workflow automation, quality gates, and custom integrations.

LangChain's unified platform for LLM observability, evaluation, prompt management, and agent deployment. Trace, evaluate, and monitor agent applications in one place — with LangGraph deployment built in.

Open-source LLM engineering platform: tracing, evals, prompt management, and metrics for LLM apps and agents. Self-hostable or cloud, with 40+ framework integrations. 15,000+ GitHub stars.

Model evaluation tools with standard metrics, benchmarks, and comprehensive performance analysis for AI models.

Dispatch code-reviewer subagent to catch issues before they cascade - review early, review often.

Systematic peer review toolkit for evaluating methodology, statistics, design, reproducibility, and ethics.

Apply ScholarEval framework to systematically evaluate scholarly work - comprehensive analysis across research quality dimensions with structured scoring and feedback.

Evaluate research rigor systematically - assess methodology, experimental design, statistical validity, biases, confounding, and evidence quality using GRADE and Cochrane ROB.