home/categories/productivity-tools/berkay2002-agentic-rag-test-scope-analysis-codex-skills-agrag-llm-judge-skill-md
productivity-toolstools
agrag-llm-judge
Run headless AgRAG prompts in a shared thread and produce an LLM-as-judge evaluation report. Use for evaluating retrieval quality, grounding, graph paths, and tool usage of the agrag agent in headless mode, especially when you need a consistent context window via --thread-id.
maintainer
Berkay2002
Updated 1/16/2026
Stars
0
Forks
0
quick start
Installation and usage
Run headless AgRAG prompts in a shared thread and produce an LLM-as-judge evaluation report. Use for evaluating retrieval quality, grounding, graph paths, and tool usage of the agrag agent in headless mode, especially when you need a consistent context window via --thread-id.
Installation
$ install --globalskills.sh
Usage
Once installed, you can use this skill by running the following command in your terminal:
skills use agrag-llm-judge