model evaluation template risk: low

Prompt Quality Audit Engineer

Instructs the model to act as a senior prompt engineer auditing an enclosed prompt for clarity, completeness, ambiguity, and other quality issues. Delivers structured response in I…

PROMPT

Act as a senior prompt engineer performing a strict and practical quality audit of the prompt enclosed below.

---PROMPT START---
${paste_prompt_here}
---PROMPT END---

Evaluate the prompt for clarity, completeness, ambiguity, missing constraints, weak instructions, conflicting directions, context gaps, output-format weaknesses, and any other issue that could reduce output quality, reliability, consistency, or usability. Prioritize issues based on their combined impact on output quality and likelihood of failure. Focus primarily on issues that directly or predictably affect correctness, reliability, or usability, but include low-probability, high-impact edge cases if they may affect real-world performance. Limit analysis to high-value insights.

In the first section (Issues), identify the most significant problems and explain clearly why each one may cause failure, inconsistency, ambiguity, or suboptimal outputs. Present issues in strict priority order using numbered points. Be comprehensive in identifying issues, but limit explanations to what is necessary to understand their impact.

In the second section (Recommendations), provide specific, practical, and directly applicable improvements. Ensure each recommendation explicitly maps to a corresponding issue (e.g., Issue 1 → Recommendation 1). Do not introduce unrelated recommendations, unless they clearly resolve multiple identified issues.

In the third section (Optimized Prompt), rewrite the prompt in a production-ready form that preserves the original intent while improving clarity, control, precision, completeness, and reliability. The result should be optimized for consistent, unambiguous, format-compliant, and clearly testable outputs in repeated use. Include explicit success criteria only when they improve testability. You may restructure the prompt if necessary, but do not introduce new intent. If essential elements are missing (such as context, constraints, or output format), explicitly account for them using clear placeholders such as ${insert_context_here}. Only make assumptions when required to make the prompt executable; otherwise explicitly identify missing information.

Structure the response using exactly these three section titles: Issues, Recommendations, and Optimized Prompt.

Use English only for the three required section titles. Write everything else in Turkish. Strictly enforce numbering and clear mapping between sections. Avoid unnecessary repetition.

INPUTS

paste_prompt_here REQUIRED: Placeholder for the prompt to be audited

REQUIRED CONTEXT

prompt to audit

ROLES & RULES

Role assignments

Act as a senior prompt engineer performing a strict and practical quality audit of the prompt enclosed below.

Prioritize issues based on their combined impact on output quality and likelihood of failure.
Focus primarily on issues that directly or predictably affect correctness, reliability, or usability, but include low-probability, high-impact edge cases if they may affect real-world performance.
Limit analysis to high-value insights.
Present issues in strict priority order using numbered points.
Be comprehensive in identifying issues, but limit explanations to what is necessary to understand their impact.
Ensure each recommendation explicitly maps to a corresponding issue (e.g., Issue 1 → Recommendation 1).
Do not introduce unrelated recommendations, unless they clearly resolve multiple identified issues.
Rewrite the prompt in a production-ready form that preserves the original intent while improving clarity, control, precision, completeness, and reliability.
Include explicit success criteria only when they improve testability.
You may restructure the prompt if necessary, but do not introduce new intent.
If essential elements are missing (such as context, constraints, or output format), explicitly account for them using clear placeholders such as ${insert_context_here}.
Only make assumptions when required to make the prompt executable; otherwise explicitly identify missing information.
Structure the response using exactly these three section titles: Issues, Recommendations, and Optimized Prompt.
Use English only for the three required section titles. Write everything else in Turkish.
Strictly enforce numbering and clear mapping between sections.
Avoid unnecessary repetition.

EXPECTED OUTPUT

Format

markdown

Schema

markdown_sections · Issues, Recommendations, Optimized Prompt

Constraints

exactly three sections: Issues, Recommendations, Optimized Prompt
Issues: numbered priority order with explanations
Recommendations: mapped to issues (e.g. Issue 1 → Recommendation 1)
Optimized Prompt: production-ready rewrite preserving intent
section titles in English only, everything else in Turkish
strict numbering and clear mapping
use placeholders like ${insert_context_here} for missing elements

SUCCESS CRITERIA

Identify the most significant problems prioritized by impact on output quality
Provide specific improvements mapped to issues
Rewrite prompt to production-ready form preserving intent
Ensure structured response with exact sections in specified languages

FAILURE MODES

Unreplaced ${paste_prompt_here} placeholder leads to auditing empty or irrelevant content.
Turkish language requirement for non-titles may cause translation errors or inconsistencies.
Vague prioritization (impact + likelihood) allows subjective issue ordering.
Potential conflict between 'be comprehensive' and 'limit explanations' leads to inconsistent depth.
Lack of explicit format for Optimized Prompt section allows varying rewrite structures.

CAVEATS

Dependencies

Requires prompt to audit inserted at ${paste_prompt_here}.

Missing context

Language preferences or assumptions about the audited prompt's language.
Examples of common issues or evaluation rubrics for consistency.

Ambiguities

Instruction to write everything except section titles in Turkish conflicts with 'preserving the original intent' when rewriting the Optimized Prompt, especially if the original prompt is in English.
'High-value insights' and 'strict priority order' based on 'combined impact on output quality and likelihood of failure' are subjective without explicit criteria.

QUALITY

OVERALL: 0.82
CLARITY: 0.85
SPECIFICITY: 0.85
REUSABILITY: 0.75
COMPLETENESS: 0.80

IMPROVEMENT SUGGESTIONS

Replace 'Write everything else in Turkish' with a placeholder like 'Write everything else in ${target_language}' or remove to avoid conflicts and improve reusability.
Add 'The Optimized Prompt must retain the original language unless specified otherwise.' to resolve language preservation conflict.
Provide a brief rubric or examples for prioritizing issues, e.g., 'Prioritize: 1. Ambiguities leading to multiple interpretations, 2. Missing constraints...'.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.