Curates and validates high-quality documents for golden datasets using a multi-agent evaluation workflow.
The add-golden skill streamlines the creation of high-quality evaluation datasets for LLMs and RAG systems by automating the curation process. Using a sophisticated multi-agent architecture, it fetches web content, classifies document types, and performs parallel analysis to score quality across dimensions like accuracy and relevance. It ensures dataset integrity through automated duplicate detection, schema validation, and difficulty classification, providing developers with a robust, production-ready pipeline for managing ground-truth data within Claude Code.
主要功能
01Multi-agent validation with four specialized analysis agents
02Automatic content extraction and difficulty classification
03Quality-gate scoring based on accuracy, coherence, and depth
04Seamless integration with JSON fixture files for evaluation
0529 GitHub stars
06Automated duplicate detection and 80% similarity checking
使用场景
01Curating high-quality training examples from technical documentation
02Automating the expansion of test suites with verified web content
03Building ground-truth datasets for RAG system evaluation
