Loading...
Loading...
Found 1,942 Skills
Evaluate agents and skills for quality, completeness, and standards compliance using a 6-step rubric: Identify, Structural, Content, Code, Integration, Report. Use when auditing agents/skills, checking quality after creation or update, or reviewing collection health. Triggers: "evaluate", "audit", "check quality", "review agent", "score skill". Do NOT use for creating or modifying agents/skills — only for read-only assessment and scoring.
Help users make better decisions between competing options. Use when someone is weighing pros and cons, comparing alternatives, struggling with a difficult choice, deciding between speed and quality, or asking "should we do X or Y?"
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.
Use this skill when you need to test or evaluate LangGraph/LangChain agents: writing unit or integration tests, generating test scaffolds, mocking LLM/tool behavior, running trajectory evaluation (match or LLM-as-judge), running LangSmith dataset evaluations, and comparing two agent versions with A/B-style offline analysis. Use it for Python and JavaScript/TypeScript workflows, evaluator design, experiment setup, regression gates, and debugging flaky/incorrect evaluation results.
Use when evaluating agent performance, building test frameworks, measuring quality, or asking about "agent evaluation", "LLM-as-judge", "agent testing", "quality metrics", "evaluation rubrics", "agent benchmarks"
Evaluate educational chapters from dual student and teacher perspectives. This skill should be used when analyzing chapter quality, identifying content gaps, or planning chapter improvements. Reads all lessons in a chapter directory and provides structured analysis with ratings, gap identification, and prioritized recommendations.
Evaluate LLM systems using automated metrics, LLM-as-judge, and benchmarks. Use when testing prompt quality, validating RAG pipelines, measuring safety (hallucinations, bias), or comparing models for production deployment.
Use this when you need to EVALUATE OR IMPROVE or OPTIMIZE an existing LLM agent's output quality - including improving tool selection accuracy, answer quality, reducing costs, or fixing issues where the agent gives wrong/incomplete responses. Evaluates agents systematically using MLflow evaluation with datasets, scorers, and tracing. Covers end-to-end evaluation workflow or individual components (tracing setup, dataset creation, scorer definition, evaluation execution).
Create AI evaluation plans with benchmarks, rubrics, and error analysis workflows.
Structured 8-factor vendor evaluation framework for AI marketing tools, based on Venkatesan & Lecinski's The AI Marketing Canvas (2nd ed., Stanford Business Books, 2026). Scores each tool against EA market accessibility, data requirements, integration compatibility, team capability, and total cost in UGX, then produces a shortlist with 30-day experiment briefs. Invoke when a client has completed the ai-readiness-diagnostic and is at Canvas Step 2 (Experimentation) and is ready to select specific AI tools for structured trials. Also invoke when a client wants to compare 2–4 named tools before purchasing or committing budget.
Create validated LLM-as-a-Judge evaluators following best practices — binary Pass/Fail judges with TPR/TNR validation for measuring specific failure modes. Use when you need to automate quality checks, build guardrails, or measure a specific failure mode identified during trace analysis. Do NOT use when failures are fixable with prompt changes (use optimize-prompt) or when failure modes are unknown (use analyze-trace-failures first).
Evaluates accuracy of quantized or unquantized LLMs using NeMo Evaluator Launcher (NEL). Triggers on "evaluate model", "benchmark accuracy", "run MMLU", "evaluate quantized model", "accuracy drop", "run nel". Handles deployment, config generation, and evaluation execution. Not for quantizing models (use ptq) or deploying/serving models (use deployment).