agentsclimarketplace

Ai evaluation

Skill ebarti/skills/ai-evaluation

📚 Agent skills distilled from technical books — AI Engineering, Context Engineering, Designing Data-Intensive Applications, and more. Agent-agnostic, plain Markdown. Give your AI agent a bookshelf.

Install
npx -y skills add ebarti/skills --skill ai-evaluation

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Practical knowledge for evaluating AI/LLM systems. Covers language modeling metrics (perplexity, cross-entropy), exact evaluation methods (functional correctness, similarity), AI-as-judge patterns, comparative evaluation, evaluation criteria for production systems, model selection workflows, and designing end-to-end evaluation pipelines. Use this skill when: - Designing an evaluation strategy for an LLM application - Choosing between models or providers (build vs buy) - Selecting evaluation metrics (perplexity, BLEU, semantic similarity) - Setting up AI-as-judge evaluation - Interpreting public benchmarks (MMLU, HumanEval, etc.) - Building an evaluation pipeline with scoring rubrics

SKILL.md

2.1 KB, as published. Nobody here has run it

AI Evaluation

Knowledge from "AI Engineering" by Chip Huyen (Chapters 3-4). Practical methods for evaluating foundation models and AI systems built on top of them.

Quick Start

  1. Check guidelines.md to find which files to load for your task
  2. Load only relevant files (each topic has knowledge.md, rules.md, examples.md)
  3. Apply guidance to your work

Contents

References

CategoryPurpose
language-modeling-metricsEntropy, cross-entropy, perplexity, bits-per-character
exact-evaluationFunctional correctness, exact match, lexical/semantic similarity, embeddings
ai-as-judgeWhen to use AI judges, how to prompt them, limitations and biases
comparative-evaluationRanking models with pairwise comparisons, Bradley-Terry, scalability challenges
evaluation-criteriaDomain capability, generation (factual, safety), instruction-following, cost/latency
model-selectionSelection workflow, open source vs API, navigating public benchmarks
evaluation-pipelineEnd-to-end pipeline design, scoring rubrics, evaluation methods

Workflows

TaskWorkflow
Choose a model (build vs buy, OS vs API)workflows/select-model.md
Design an end-to-end evaluation pipelineworkflows/design-eval-pipeline.md

Guidelines

See guidelines.md for task-based file selection.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.