Skip to main content
Prompts Multi-LLM Prompt Improver in Arabic

model analysis template risk: low

Multi-LLM Prompt Improver in Arabic

Directs the AI to act as an expert prompt engineer, analyze and improve a specified prompt for better accuracy, and create four tailored versions for ChatGPT, Claude, Gemini, and C…

PROMPT 

Act as a certified and expert AI prompt engineer

Analyze and improve the following prompt to get more accurate and best results and answers.

Write 4 versions for ChatGPT, Claude , Gemini, and for Chinese LLMs (e.g. MiniMax, GLM, DeepSeek, Qwen).

<prompt>

...

</prompt>

Write the output in Standard Arabic.

INPUTS

prompt REQUIRED

The original prompt text to analyze and improve

REQUIRED CONTEXT

  • original prompt enclosed in <prompt> tags

ROLES & RULES

Role assignments

  • Act as a certified and expert AI prompt engineer
  1. Analyze and improve the following prompt to get more accurate and best results and answers.
  2. Write 4 versions for ChatGPT, Claude, Gemini, and for Chinese LLMs (e.g. MiniMax, GLM, DeepSeek, Qwen).
  3. Write the output in Standard Arabic.

EXPECTED OUTPUT

Format
markdown
Constraints
  • 4 versions: one for ChatGPT, one for Claude, one for Gemini, one for Chinese LLMs (e.g. MiniMax, GLM, DeepSeek, Qwen)
  • entire output in Standard Arabic

SUCCESS CRITERIA

  • Analyze and improve the prompt for accuracy.
  • Write 4 tailored versions for specified LLMs.
  • Output entirely in Standard Arabic.

FAILURE MODES

  • Placeholder '...' in <prompt> may cause generic analysis.
  • Lacks explicit structure for versions, leading to inconsistent output.
  • No defined metrics for 'more accurate and best results'.
  • May produce non-Standard Arabic output.

CAVEATS

Dependencies
  • Content of the <prompt>...</prompt> section.
Missing context
  • Criteria for 'more accurate and best results' (e.g., metrics like accuracy, coherence).
  • Expected output structure (e.g., analysis section, then labeled versions).
  • Details on LLM differences (e.g., token limits, preferred prompting styles).
Ambiguities
  • Unclear what 'analyze and improve' specifically entails (e.g., structure review, scoring, or just rewriting).
  • Unspecified how to tailor versions to each LLM (e.g., model-specific quirks or formats).
  • Placeholder '...' in <prompt> assumes content will be inserted, but no guidance on handling empty cases.
  • Output in 'Standard Arabic' – unclear if analysis or only versions should be in Arabic.

QUALITY

OVERALL
0.75
CLARITY
0.80
SPECIFICITY
0.60
REUSABILITY
0.90
COMPLETENESS
0.70

IMPROVEMENT SUGGESTIONS

  • Add explicit output format: '1. Analysis summary. 2. Improved version for ChatGPT. 3. For Claude, etc., all in Modern Standard Arabic.'
  • Specify analysis components: 'Evaluate clarity, specificity; suggest fixes.'
  • Include instructions: 'Tailor versions to LLM strengths, e.g., Claude for reasoning, Gemini for multimodality.'
  • Replace 'Standard Arabic' with 'Modern Standard Arabic (MSA)' and confirm it applies to entire output.

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.

MORE FOR MODEL