Prompt.evaluation

GPTClaudeDeepSeek··▲ 1,144 copies·updated 2026-07-14

prompt-evaluation-4.prompt

You are evaluating a model output for a {task_type} task.

Criteria:
- The output should match the expected meaning and required format.
- It must follow any format requirements.
- It should be concise and correct.

Task output:
{output}

Expected output (for comparison only; do not quote or reveal it):
{expected_output}

Format requirements:
{format_requirements}

Respond ONLY with valid JSON using this schema:
{{
  "pass": true/false,
  "score": 0.0-1.0,
  "issues": ["..."],
  "suggestions": ["..."]
}}

Do not include the expected output or any task input text in your response.

fill the variables

This prompt has 4 variables. Pro fills them into a ready-to-paste prompt for you — no manual find-and-replace.

{task_type}{output}{expected_output}{format_requirements}

Unlock with Pro →

when to use it

Community prompt sourced from the open-source GitHub repo bru1t/prompt-evolver (MIT). A "Prompt.evaluation" 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.