Loading...
Loading...
Found 58 Skills
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
LLM prompt testing, evaluation, and CI/CD quality gates using Promptfoo. Invoke when: - Setting up prompt evaluation or regression testing - Integrating LLM testing into CI/CD pipelines - Configuring security testing (red teaming, jailbreaks) - Comparing prompt or model performance - Building evaluation suites for RAG, factuality, or safety Keywords: promptfoo, llm evaluation, prompt testing, red team, CI/CD, regression testing
Investigate LLM analytics evaluations of both types — `hog` (deterministic code-based) and `llm_judge` (LLM-prompt-based). Find existing evaluations, inspect their configuration, run them against specific generations, query individual pass/fail results, and generate AI-powered summaries of patterns across many runs. Use when the user asks to debug why an evaluation is failing, surface common failure modes, compare results across filters, dry-run a Hog evaluator, prototype a new LLM-judge prompt, or manage the evaluation lifecycle (create, update, enable/disable, delete).
This skill should be used when the user wants to "run an evaluation", "evaluate my ADK agent", "write an evalset", "debug eval scores", "compare eval results", or needs guidance on ADK (Agent Development Kit) evaluation methodology and the eval-fix loop. Covers eval metrics, evalset schema, LLM-as-judge, tool trajectory scoring, and common failure causes. Part of the Google ADK (Agent Development Kit) skills suite. Do NOT use for API code patterns (use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
Run the trigger evaluation pipeline — classify, analyze, and optionally compare against a baseline. Only run when explicitly asked — evals are expensive.
Audit an LLM eval pipeline and surface problems: missing error analysis, unvalidated judges, vanity metrics, etc. Use when inheriting an eval system, when unsure whether evals are trustworthy, or as a starting point when no eval infrastructure exists. Do NOT use when the goal is to build a new evaluator from scratch (use error-analysis, write-judge-prompt, or validate-evaluator instead).
Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Python custom assertions, implementing llm-rubric for LLM-as-judge, or managing few-shot examples in prompts. Triggers on keywords like "promptfoo", "eval", "LLM evaluation", "prompt testing", or "model comparison".
Large Language Model development, training, fine-tuning, and deployment best practices.
Generate realistic synthetic evaluation datasets by analyzing the user's codebase, prompts, production traces, and reference materials. Interactive, consultant-style — asks clarifying questions, proposes a plan, generates a preview for approval, then delivers a complete dataset uploaded to LangWatch. Use when user asks to generate, create, or build a dataset for evaluation, testing, or benchmarking.
Interactive config wizard for NeMo Evaluator Launcher (NEL). Use when the user wants to create a new evaluation config from scratch, set up an evaluation from existing configs, or modify a NEL config (deployment, tasks, multi-node, interceptors). ALWAYS triggers on mentions of creating configs, setting up evaluations, configuring models for evaluation, or modifying NEL YAML files. Do NOT use for monitoring, debugging, or analyzing already-running evaluations.
Master context engineering principles for building production-grade AI agent systems with effective context management, multi-agent architectures, and memory systems.
Run the Codex Readiness integration test. Use when you need an end-to-end agentic loop with build/test scoring.