libeval

Official

Automated RAG evaluation and recall analysis.

Authorcopilot-ld
Version1.0.0
Installs0

System Documentation

What problem does it solve?

The Skill enables automated assessment of RAG agent quality by coordinating evaluation across criteria, recall, and trace analyses, and by persisting results for reporting.

Core Features & Use Cases

  • Evaluator orchestrates evaluation runs across multiple scenarios and models.
  • CriteriaEvaluator scores responses against rubrics using an LLM-based judge.
  • RecallEvaluator validates retrieval coverage by examining memory windows and stored subjects.
  • TraceEvaluator analyzes execution traces for performance, safety, and correctness.
  • EvalStore persists results to enable comprehensive reporting and benchmarking.

Quick Start

Run the evaluation suite defined in config/eval.yml and review the generated SUMMARY.md and per-scenario reports.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: libeval
Download link: https://github.com/copilot-ld/copilot-ld/archive/main.zip#libeval

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.