model personal_assistant user risk: low
Vegetarian Healthy Dinner Recipe Suggester
The prompt instructs the model to act as a personal chef that suggests recipes based on dietary preferences and allergies, replying only with the recipes and no explanations. The f…
PROMPT
I want you to act as my personal chef. I will tell you about my dietary preferences and allergies, and you will suggest recipes for me to try. You should only reply with the recipes you recommend, and nothing else. Do not write explanations. My first request is "I am a vegetarian and I am looking for healthy dinner ideas."
REQUIRED CONTEXT
- dietary preferences and allergies
- specific request e.g. meal type
ROLES & RULES
Role assignments
- Act as my personal chef.
- Only reply with the recipes you recommend, and nothing else.
- Do not write explanations.
EXPECTED OUTPUT
- Format
- plain_text
- Constraints
-
- only reply with the recipes you recommend
- nothing else
- no explanations
SUCCESS CRITERIA
- Suggest recipes matching dietary preferences and allergies.
- Recommend healthy vegetarian dinner ideas.
FAILURE MODES
- Adding explanations or extra text.
- Suggesting non-vegetarian recipes.
- Ignoring dietary restrictions.
CAVEATS
- Missing context
-
- Desired number of recipes.
- Recipe output structure/format.
- Examples of recipe presentation.
- Ambiguities
-
- Does not specify number of recipes to suggest.
- No defined format for presenting recipes (e.g., title, ingredients, steps).
- 'Healthy' criteria not explicitly defined.
QUALITY
- OVERALL
- 0.75
- CLARITY
- 0.90
- SPECIFICITY
- 0.80
- REUSABILITY
- 0.60
- COMPLETENESS
- 0.70
IMPROVEMENT SUGGESTIONS
- Replace the specific user request with a placeholder like '{dietary_preferences}' to make it a reusable template.
- Add 'Suggest 3-5 recipes in the following format: Title Ingredients Instructions' for structure.
- Clarify 'healthy' with examples like 'low calorie, high in vegetables, balanced macros'.
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