“LLM evaluation”

Evaluate a call recording with a multimodal LLM.

Evaluation — an observability concept covering evaluation, score, drift, shadow, benchmark.

Renamed to /model-assessment in v6 (removed in v7).

You're a quality engineer who has seen agents that aced benchmarks fail spectacularly in production.

Use when designing, configuring, running, or troubleshooting NeMo Agent Toolkit evaluations, datasets, evaluator selection, ATIF surfaces, quality gates…

Evaluate one design or a user-approved maturity-mapped batch through a transparent evidence-based rubric.

Use when the user wants proof that finished work meets its acceptance criteria, not just that tests pass: 'verify it is actually done', 'check it against the…

This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or…

Evaluate any agent skill against a merged framework — Anthropic's Claude Code best practices plus Matt Pocock's writing-great-skills methodology — across 4…

Build evaluation pipelines for AI outputs — create datasets, write evaluators, and measure quality systematically.

Use when building, running, or debugging evaluations for LLM or agent components: golden sets, regression evals, LLM-as-judge, rubric scoring…

Inspects the plan, milestones, tasks, and generated session schedules to certify they meet formatting guidelines, safety constraints, and scheduling…

Evaluate agent behavior with versioned cases and explicit verifiers.

Evaluate, test, and recommend tools and platforms with weighted scoring, TCO analysis, and strategic adoption planning.

Design LLM-as-judge rubrics, direct scores and pairwise comparisons.

Provides qualitative-first, evidence-traceable developmental review of scholarly works and audit low-stakes research-assessment rubrics with optional local…

Evaluate whether a the reference deployment skill actually works — blind runner + separate judge against a bar, rubric scoring, pass-rate on re-runs, and…

Evaluate prompt, model, retrieval, and agent changes with repeated graded trials.

Automated regression testing and continuous evaluation for LLM prompts, ensuring deterministic outputs and preventing prompt drift.

Use when evaluating MCP-enabled agents, tool-using LLM systems, multi-server workflows, tool-selection quality, trajectory quality, task completion, or MCP…

Use Langfuse for LLM observability and evaluation and look up Langfuse documentation.

Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR).

Use when creating or updating agent evaluation suites.

Systematic evaluation of Retrieval-Augmented Generation (RAG) pipelines measuring faithfulness, answer relevance, context recall, and precision.