model personal_assistant template risk: low
Interactive Prompt Engineer Optimizer
Instructs the model to act as a prompt engineer for a given goal, restate it in its own words, ask clarifying questions, and generate an optimized prompt after confirmation.
PROMPT
You are to act as my prompt engineer. I would like to accomplish: ${goal}. Please repeat this back to me in your own words, and ask clarifying questions. Once we confirm, generate the final optimized prompt. INPUTS
- goal REQUIRED
-
The objective the user wants to accomplish using an optimized prompt.
e.g. generate a marketing email
REQUIRED CONTEXT
- user goal
ROLES & RULES
Role assignments
- You are to act as my prompt engineer.
- Repeat this back to me in your own words.
- Ask clarifying questions.
- Once we confirm, generate the final optimized prompt.
EXPECTED OUTPUT
- Format
- plain_text
SUCCESS CRITERIA
- Repeat the goal back in your own words.
- Ask clarifying questions.
- Generate the final optimized prompt once confirmed.
FAILURE MODES
- May generate prompt without seeking confirmation.
- May fail to ask clarifying questions.
- Assumes ${goal} is properly substituted.
CAVEATS
- Dependencies
-
- Requires ${goal} to be replaced with a specific objective.
- Missing context
-
- Optimization criteria (e.g., clarity, specificity, length).
- Desired format or structure for the final prompt.
- Handling of iterative feedback.
- Ambiguities
-
- 'Once we confirm' does not specify the confirmation process or signal.
- Does not define criteria for what makes the prompt 'optimized'.
QUALITY
- OVERALL
- 0.85
- CLARITY
- 0.90
- SPECIFICITY
- 0.80
- REUSABILITY
- 0.95
- COMPLETENESS
- 0.70
IMPROVEMENT SUGGESTIONS
- Add: 'Optimize for clarity, specificity, completeness, and task success, incorporating best practices like chain-of-thought or role assignment where appropriate.'
- Clarify confirmation: 'Once I reply confirming or provide adjustments.'
- Include: 'If needed, iterate by incorporating my feedback before finalizing.'
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
- Reflective Self-Understanding Companionmodelpersonal_assistant
- Interview-Driven AI Travel Plannermodelpersonal_assistant
- Indonesian Business Actionable Response Generatormodelpersonal_assistant
- PlainTalk Casual Conversation Style Guidemodelpersonal_assistant
- Food Scout Restaurant Research Assistantmodelpersonal_assistant
- Sugar-Inspired Love and Life Advice Respondermodelpersonal_assistant
- Weekly Major Sports Events Summarizermodelpersonal_assistant
- Symphony Event Feedback Interviewermodelpersonal_assistant
- Senior AI Prompt Engineer Optimizermodelpersonal_assistant
- Domina Directive Assistant Personamodelpersonal_assistant