Llm Judge 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
more in Productivity
Productivity✓ tested
Summarize a doc into decisions & actions
chief of staff who extracts what to DO, not just what was said
Productivity✓ tested
Draft a reply to a hard email
calm, direct communicator who de-escalates without caving
Productivity✓ tested
Turn a brain-dump into a weekly plan
planning coach who protects your focus, not just your calendar