AI Evals Skills

ai-evals-course/evals-skills

Practical workflows for assessing and improving product-specific LLM evaluations.

Conteúdo atualizado:

Ver no GitHub
npx skills add ai-evals-course/evals-skills --skill eval-audit
1.764Estrelas126ForksÚltimo push do repositório

Sobre este Skill

Practical workflows for assessing and improving product-specific LLM evaluations.

Por que escolhemos

A focused audit of product evaluation artifacts, including judge validation against human labels.

Skills desta coleção

1 skills
  • Eval Audit

    Audit an LLM evaluation pipeline for missing error analysis, unvalidated judges, data leakage and stale checks.

    Ver →

No que ajuda

  • Review an existing LLM evaluation system and prioritize evidence-backed improvements.

Antes de usar

  • Provide evaluation traces, judge prompts, labeled data or other pipeline artifacts; an observability integration is optional.

Fontes e referências

As fontes originais estão nos links abaixo. As sugestões práticas são recomendações editoriais do SkillHey.