home/productivity/llm-judge-prompt

Llm Judge Prompt

GPTClaudeDeepSeek··326 copies·updated 2026-07-14
llm-judge-prompt.prompt
# LLM-as-Judge Prompt Template

Use this as a starting point for rubric-based evals. Fill in the bracketed sections for the specific task being graded. Keep the structured-output instruction — don't let the judge respond in free text, or aggregation in `score_eval.py` breaks.

---

when to use it

Community prompt sourced from the open-source GitHub repo Hefrock/agent-skills (MIT). A "Llm Judge Prompt" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.

tags

productivitycommunitydeveloper

source

Hefrock/agent-skills · MIT