Prompt Critic and Optimizer Rubric
Evaluate a draft prompt, diagnose why it produces suboptimal results, and rewrite it for maximum reliability, clarity, and performance.
- Category
- AI & Prompt Engineering
- Output
- Markdown
- Fields
- 3
- prompt-engineering
- critical-evaluation
- feedback
- output-optimization
- editing
Prompt
You are an expert prompt engineer and AI interaction specialist. Your task is to evaluate a draft prompt, diagnose why it produces suboptimal results, and rewrite it for maximum reliability, clarity, and performance.
Follow these steps precisely:
1. **Rubric Evaluation**: Assess the draft prompt against these seven criteria: task clarity, role/context definition, specificity, output formatting, constraints, use of examples, and failure/error handling. Assign a score from 1 to 5 for each, followed by a concise one-line justification.
2. **Root Cause Diagnosis**: Identify the top two weaknesses most directly responsible for the poor performance described.
3. **Optimized Rewrite**: Draft a complete, production-ready version of the prompt that resolves the identified weaknesses. Ensure it contains a clear system role, step-by-step instructions, explicit output formatting rules, and appropriate constraints.
4. **Change Explanation**: Briefly summarize what you changed and why each modification improves performance.
5. **Validation Test**: Suggest one specific test input or scenario that would effectively reveal whether the rewritten prompt succeeds.
**Constraints & Guidelines**:
- Rely strictly on the provided information. Do not invent facts, assumptions, or external context.
- If any critical detail is missing or ambiguous, list it under "Open Questions" before proceeding. Do not guess.
- If the user does not provide a goal or observed problem, infer them logically from the draft prompt and state your assumptions.
**Input Data**:
- Draft prompt: Draft prompt
- Intended goal: Intended goal
- Observed issue: Observed issue
**Output Structure**:
Return your response in the following format:
### Rubric Evaluation
- Task clarity: [score]/5 - [reason]
- Role/context: [score]/5 - [reason]
- Specificity: [score]/5 - [reason]
- Output format: [score]/5 - [reason]
- Constraints: [score]/5 - [reason]
- Examples: [score]/5 - [reason]
- Failure handling: [score]/5 - [reason]
### Root Cause Diagnosis
1. [Weakness 1]
2. [Weakness 2]
### Optimized Prompt
[Insert the fully rewritten prompt here]
### Change Explanation
[Brief summary of modifications and rationale]
### Validation Test
[One specific test input or scenario]
### Open Questions
[List any missing or ambiguous details, or state "None"]
How to use this prompt
- Fill in the fields above. Required ones are marked with *.
- Check the prompt preview: your answers appear highlighted in place.
- Select Copy prompt and paste it into ChatGPT, Claude, Gemini or any AI assistant.
More AI & Prompt Engineering prompts
- Structure and Format AI OutputTransform unstructured input into a polished, professional output that strictly matches the requested target format.
- Automate AI WorkflowDesign a reliable, step-by-step AI automation workflow based on the user's specifications.
- Image Generation PromptTransform a user's core concept into highly optimized, ready-to-use prompts for AI image generation.
- LLM Evaluation and Model ComparisonYou are an expert AI model evaluator and technical consultant.
- Prompt Engineering Deep OptimizationRewrite the provided draft prompt using advanced prompt engineering best practices, making it more precise, reliable, and structured.
- System Prompt Production ReadyYou are an expert prompt engineer tasked with crafting production-ready system instructions for AI assistants.