rag-eval

仓库创建 2025年7月8日最近提交 18 天前SkillHot 收录 8 小时前

▸ 精选理由

能快速定位 RAG 故障来源，帮助针对性优化检索或生成模块。

这个 Skill 做什么

把检索与生成问题分离，诊断 RAG 系统并定位是检索还是生成导致错误。

把检索和生成两部分拆开诊断，帮你判断 RAG 系统出错是因为没找到对的文档（retrieval）还是用了错误信息生成答案（generation）。适合有 retriever+generator 的流水线、怀疑 hallucination 或想优化 chunking/检索质量时使用。会输出一张诊断矩阵，明确指出先该修检索器还是先调整生成策略。

▸ 展开 SKILL.md 英文原文

Use when the user has a RAG (Retrieval-Augmented Generation) system and wants to evaluate its quality — separating retrieval issues from generation issues. Also use when the user mentions RAG evaluation, faithfulness checking, hallucination detection in RAG, retrieval quality, chunking optimization, or "is my RAG pipeline working." Outputs a diagnostic matrix that pinpoints whether problems are in retrieval or generation.

研究检索RAG 评估检索诊断生成分析通用✓ ClawHub 收录

748

Stars

Forks

仓库内 Skill

+40

7 日增星

安装 / 使用

给你的 Agent 一句话（通用）

帮我安装这个 skill：https://raw.githubusercontent.com/agentscope-ai/OpenJudge/main/skills/eval_pipeline/05-rag-eval/SKILL.md

或 curl 直取 SKILL.md

curl -fsSL "https://raw.githubusercontent.com/agentscope-ai/OpenJudge/main/skills/eval_pipeline/05-rag-eval/SKILL.md"

SKILL.MD 节选查看完整文件 ↗

# RAG Eval

Evaluate RAG systems by diagnosing retrieval and generation separately. A single
"RAG accuracy" number hides whether the problem is finding the right documents or
using them correctly. This skill separates them so you know what to fix.

## When to Activate

- User has a RAG pipeline (retriever + generator) with traces
- User wants to know if their RAG system hallucinates
- User is optimizing chunking strategy and needs before/after comparison
- User wants to build a RAG evaluation dataset

## Checklist

You MUST create a task for each item and complete them in order:

1. **Load RAG traces** — validate query + context + answer triples
2. **Separate retrieval vs generation** — dete

via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有