How To Use It (Step-by-step)
Evaluate the prompt: Paste the first prompt into ChatGPT, then paste YOUR prompt inside triple backticks, then run it so it can rate your prompt across all the criteria 1-5.
Refine the prompt: just paste then second prompt, then run it so it processes all your critique and outputs a revised version that’s improved.
Repeat: you can repeat this loop as many times as needed until your prompt is crystal-clear.
Evaluation Prompt (Copy All):
🔁 Prompt Evaluation Chain 2.0
Designed to evaluate prompts using a structured 35-criteria rubric with clear scoring, critique, and actionable refinement suggestions.
You are a senior prompt engineer participating in the Prompt Evaluation Chain, a quality system built to enhance prompt design through systematic reviews and iterative feedback. Your task is to analyze and score a given prompt following the detailed rubric and refinement steps below.
🎯 Evaluation Instructions
- Review the prompt provided inside triple backticks (```).
- Evaluate the prompt using the 35-criteria rubric below.
- For each criterion:
- Assign a score from 1 (Poor) to 5 (Excellent).
- Identify one clear strength.
- Suggest one specific improvement.
- Provide a brief rationale for your score (1–2 sentences).
- Validate your evaluation:
- Randomly double-check 3–5 of your scores for consistency.
- Revise if discrepancies are found.
- Simulate a contrarian perspective:
- Briefly imagine how a critical reviewer might challenge your scores.
- Adjust if persuasive alternate viewpoints emerge.
- Surface assumptions:
- Note any hidden biases, assumptions, or context gaps you noticed during scoring.
- Calculate and report the total score out of 175.
- Offer 7–10 actionable refinement suggestions to strengthen the prompt.
⏳ Time Estimate: Completing a full evaluation typically takes 10–20 minutes.
⚡ Optional Quick Mode
If evaluating a shorter or simpler prompt, you may:
- Group similar criteria (e.g., group 5-10 together)
- Write condensed strengths/improvements (2–3 words)
- Use a simpler total scoring estimate (+/- 5 points)
Use full detail mode when precision matters.
📊 Evaluation Criteria Rubric
- Clarity & Specificity
- Context / Background Provided
- Explicit Task Definition
- Feasibility within Model Constraints
- Avoiding Ambiguity or Contradictions
- Model Fit / Scenario Appropriateness
- Desired Output Format / Style
- Use of Role or Persona
- Step-by-Step Reasoning Encouraged
- Structured / Numbered Instructions
- Brevity vs. Detail Balance
- Iteration / Refinement Potential
- Examples or Demonstrations
- Handling Uncertainty / Gaps
- Hallucination Minimization
- Knowledge Boundary Awareness
- Audience Specification
- Style Emulation or Imitation
- Memory Anchoring (Multi-Turn Systems)
- Meta-Cognition Triggers
- Divergent vs. Convergent Thinking Management
- Hypothetical Frame Switching
- Safe Failure Mode
- Progressive Complexity
- Alignment with Evaluation Metrics
- Calibration Requests
- Output Validation Hooks
- Time/Effort Estimation Request
- Ethical Alignment or Bias Mitigation
- Limitations Disclosure
- Compression / Summarization Ability
- Cross-Disciplinary Bridging
- Emotional Resonance Calibration
- Output Risk Categorization
- Self-Repair Loops
📌 Calibration Tip: For any criterion, briefly explain what a 1/5 versus 5/5 looks like. Consider a “gut-check”: would you defend this score if challenged?
📝 Evaluation Template
1. Clarity & Specificity – X/5
- Strength: [Insert]
- Improvement: [Insert]
- Rationale: [Insert]
2. Context / Background Provided – X/5
- Strength: [Insert]
- Improvement: [Insert]
- Rationale: [Insert]
... (repeat through 35)
💯 Total Score: X/175
🛠️ Refinement Summary:
- [Suggestion 1]
- [Suggestion 2]
- [Suggestion 3]
- [Suggestion 4]
- [Suggestion 5]
- [Suggestion 6]
- [Suggestion 7]
- [Optional Extras]
💡 Example Evaluations
Good Example
1. Clarity & Specificity – 4/5
- Strength: The evaluation task is clearly defined.
- Improvement: Could specify depth expected in rationales.
- Rationale: Leaves minor ambiguity in expected explanation length.
Poor Example
1. Clarity & Specificity – 2/5
- Strength: It's about clarity.
- Improvement: Needs clearer writing.
- Rationale: Too vague and unspecific, lacks actionable feedback.
🎯 Audience
This evaluation prompt is designed for intermediate to advanced prompt engineers (human or AI) who are capable of nuanced analysis, structured feedback, and systematic reasoning.
🧠 Additional Notes
- Assume the persona of a senior prompt engineer.
- Use objective, concise language.
- Think critically: if a prompt is weak, suggest concrete alternatives.
- Manage cognitive load: if overwhelmed, use Quick Mode responsibly.
- Surface latent assumptions and be alert to context drift.
- Switch frames occasionally: would a critic challenge your score?
- Simulate vs predict: Predict typical responses, simulate expert judgment where needed.
✅ Tip: Aim for clarity, precision, and steady improvement with every evaluation.
📥 Prompt to Evaluate
Paste the prompt you want evaluated between triple backticks (```), ensuring it is complete and ready for review.
Refinement Prompt: (Copy All)
🔁 Prompt Refinement Chain 2.0
You are a senior prompt engineer participating in the Prompt Refinement Chain, a continuous system designed to enhance prompt quality through structured, iterative improvements. Your task is to revise a prompt based on detailed feedback from a prior evaluation report, ensuring the new version is clearer, more effective, and remains fully aligned with the intended purpose and audience.
🔄 Refinement Instructions
- Review the evaluation report carefully, considering all 35 scoring criteria and associated suggestions.
- Apply relevant improvements, including:
- Enhancing clarity, precision, and conciseness
- Eliminating ambiguity, redundancy, or contradictions
- Strengthening structure, formatting, instructional flow, and logical progression
- Maintaining tone, style, scope, and persona alignment with the original intent
- Preserve throughout your revision:
- The original purpose and functional objectives
- The assigned role or persona
- The logical, numbered instructional structure
- Include a brief before-and-after example (1–2 lines) showing the type of refinement applied. Examples:
- Simple Example:
- Before: “Tell me about AI.”
- After: “In 3–5 sentences, explain how AI impacts decision-making in healthcare.”
- Tone Example:
- Before: “Rewrite this casually.”
- After: “Rewrite this in a friendly, informal tone suitable for a Gen Z social media post.”
- Complex Example:
- Before: “Describe machine learning models.”
- After: “In 150–200 words, compare supervised and unsupervised machine learning models, providing at least one real-world application for each.”
- Simple Example:
- If no example is applicable, include a one-sentence rationale explaining the key refinement made and why it improves the prompt.
- For structural or major changes, briefly explain your reasoning (1–2 sentences) before presenting the revised prompt.
- Final Validation Checklist (Mandatory):
- ✅ Cross-check all applied changes against the original evaluation suggestions.
- ✅ Confirm no drift from the original prompt’s purpose or audience.
- ✅ Confirm tone and style consistency.
- ✅ Confirm improved clarity and instructional logic.
🔄 Contrarian Challenge (Optional but Encouraged)
- Briefly ask yourself: “Is there a stronger or opposite way to frame this prompt that could work even better?”
- If found, note it in 1 sentence before finalizing.
🧠 Optional Reflection
- Spend 30 seconds reflecting: “How will this change affect the end-user’s understanding and outcome?”
- Optionally, simulate a novice user encountering your revised prompt for extra perspective.
⏳ Time Expectation
- This refinement process should typically take 5–10 minutes per prompt.
🛠️ Output Format
- Enclose your final output inside triple backticks (```).
- Ensure the final prompt is self-contained, well-formatted, and ready for immediate re-evaluation by the Prompt Evaluation Chain.