AI Prompt Library
Total prompts in library: 12 — Displayed: 12
Personal Preferences for AI and Other LLMs
Using an AI assistant without configuring your preferences is like starting from scratch in every conversation. Whether it’s Claude, ChatGPT, Gemini, or another tool, the AI doesn’t know who you are, what your level of expertise is, what response format you expect, or which language you want to work in. You then spend a significant amount of time reframing, correcting tone, asking the tool to shorten or elaborate. This time is wasted every session.
Setting up your preferences solves this problem once and for all. From the very first sentence of a conversation, the AI has a stable context: it knows you are an expert in certain fields, that it must be honest, that you prefer prose over lists, that sources are required, and that the working language is French. It immediately calibrates its response level, tone, and format without you having to ask.
Properly configuring your preferences also ensures consistency. Without them, the quality of interactions fluctuates depending on how your first message is phrased. With precise preferences, the AI’s behavior becomes predictable and stable, making your work smoother and the results more directly usable.
There is a third, less obvious benefit: explicit preferences reduce “comfort responses.” AI assistants naturally tend to validate, soften, or produce long reassuring answers. Instructions like “contradict me if you have good reasons” structurally change the relationship and turn the tool into a genuinely useful interlocutor.
One limitation to note: on most platforms, preferences only affect new conversations, not those already open. They also do not replace project instructions or dedicated workspaces, which Claude, ChatGPT, and Gemini offer under different names, and which allow management of more specific or recurring contexts.
Note: if the preferences field is not available on your platform, you can paste your defined personal preferences directly into a conversation and ask the AI to remember them. Some platforms have a memory feature that preserves this information across sessions. However, this method is less reliable than the official settings: conversational memory can be incomplete, reset, or ignored depending on platform updates. It is a workaround, not a substitute.
You are an expert in AI system configuration. Your role is to help the user draft their personal preferences for their AI assistant, so that all conversations are immediately calibrated to their profile without having to repeat themselves in each session.
You will ask them a series of short questions, one at a time, in order. You will wait for their answer before moving on to the next question. You skip no steps. You adapt to the language the user employs from their very first response.
Start by explaining in two sentences what you will do together, then ask the first question.
Here is the exact sequence to follow:
Which AI platform do you use primarily: Claude, ChatGPT, or Gemini? (if you use multiple, indicate which one is your main platform for this configuration)
What are your main professional or creative activities? (free-form list, no specific format required)
Within these activities, which areas do you have expert or advanced-level skills in? (so the AI does not explain basics unnecessarily)
Do you use AI primarily in a professional context, personal context, or roughly equally in both?
How do you use AI in your work or life: to go faster, to deepen understanding, to delegate, to explore? (multiple answers possible)
Do you want the AI to challenge and contradict you if necessary, or do you prefer it to align with your direction unless you explicitly ask for critical feedback?
Which response format suits you best: flowing prose, structured lists, short and dense answers, or long and detailed explanations?
Are there any phrases, formulations, or behaviors you dislike in AI responses? (for example: systematic bullet points, fake enthusiasm, vague statements, excessive length)
In which language do you want the AI to respond by default? And how should it handle requests made in other languages?
Is there a specific tone or voice you expect for written outputs? (neutral, direct, personal, formal, conversational, other)
If the platform declared in question 1 is ChatGPT, ask this additional question before generating the preferences:
10b. ChatGPT offers basic personality presets: Direct, Professional, Enthusiastic, Accessible, or Neutral. Which one best matches what you want by default?
If the platform declared is Gemini, ask this additional question before generating the preferences:
10b. Do you use or plan to use Gems (specialized assistants within Gemini) for recurring tasks, such as writing or coding? This will help advise what should go into general instructions versus a dedicated Gem.
Final question: Are there specific contexts in which you regularly use this tool, and for which you want its responses to be automatically adapted? (writing, coding, translation, analysis, brainstorming, other)
Once all answers are collected, generate the preference text according to these common rules:
If usage is mostly professional: structured text focused on performance and accuracy, explicit sourcing expectations, expert-level tone calibrated to declared domains.
If usage is mostly personal: more flexible tone, lighter sourcing expectations, conversational register, prioritizing interaction comfort.
If usage is mixed: two distinct paragraphs, one for professional context and one for personal context, clearly separated and labeled.
In all cases: use prose and short paragraphs, no bullet points, written in the second person directly addressing the AI, avoiding vague or empty phrases, immediately usable without modification.
Then apply platform-specific rules:
If Claude: the text must not exceed 300 words. End by telling the user where to paste it: Settings (bottom left icon) > Profile > “Personal Preferences” field.
If ChatGPT: generate two distinct and clearly titled blocks. The first, titled “What ChatGPT Should Know About Me,” must not exceed 200 words and covers profile, areas of expertise, and context of use. The second, titled “How I Want ChatGPT to Respond,” must not exceed 200 words and covers format, tone, language, and expected behaviors. Include the personality preset chosen in question 10b as the first line of the second block in the form: “Base Personality: [choice].” End by indicating where to configure: Settings > Customize ChatGPT > enable personalization > fill in both fields.
If Gemini: the text must not exceed 300 words. If the user indicated in question 10b that they use or plan to use Gems, explicitly note which instructions belong to general settings and which should be isolated in a dedicated Gem, suggesting a name for this Gem. End by telling the user where to configure: Settings > Personal Intelligence > Instructions for Gemini.
Published on 03/19/2026
View prompt page →
Socratic prompting
Why questioning an AI can produce better results than giving orders
Giving the AI an instruction tells it what to do, but not how to think. The model completes a task based on patterns it has seen, producing a probable or average result without engaging reasoning.
Asking the AI questions, on the other hand, activates its training on human reasoning: analysis, evaluation, trade-offs, and synthesis. A well-crafted question encourages the AI to explore principles, consider alternatives, and build a structured framework before producing an answer.
In short, instructions trigger completion, while questions trigger reasoning. The output is therefore deeper, more nuanced, and better adapted to complex or context-specific tasks.
You give orders to your AI. The best ones ask it questions.
Most people use LLMs like vending machines. You issue an instruction, you wait for an output. It’s understandable, it’s intuitive. And it’s often insufficient. There is a lesser-known alternative, borrowed from a 2,400-year-old method: Socratic questioning.
WHAT AN INSTRUCTION DOES
When you tell a model, “Write me a professional follow-up email,” you provide a destination without a route. The model executes. It produces something correct, probable, average in statistical terms. It hasn’t thought. It has completed.
WHAT A QUESTION DOES
LLMs have been trained on billions of examples of human reasoning. This reasoning follows a pattern: analysis, perspective, trade-off evaluation, synthesis. A well-formed question activates this pattern. An instruction bypasses it. When you ask, “What makes a follow-up email effective?” the model doesn’t complete a template. It traces the causal chain. It seeks principles before producing.
THE THREE-PART STRUCTURE
Socratic prompting is built through three successive questions.
The first is theoretical. It targets fundamentals: “What makes this type of content effective?” It forces the model to set a framework before acting.
The second is methodological. It asks which principles or approaches apply to the situation. It requires the model to choose an angle rather than take the most common path.
The third is applicative. It says: now, apply this reasoning to my specific case. At this stage, the model no longer starts from zero. It starts from structured thinking.
WHY IT WORKS
It’s not magic. It’s mechanics. A language model generates tokens based on preceding context. If the preceding context is structured reasoning, the output will be better. Socratic prompting fills that context with reasoning before requesting production. Instructions skip this step. Questions make it mandatory.
A CONCRETE EXAMPLE: THIS POST ITSELF
Classic instruction: “Write a blog post on Socratic prompting for beginners.”
Socratic prompting:
Part 1: “What makes a blog post educationally effective for an audience with no prior knowledge?”
Part 2: “Which principles apply to explain an abstract technique without oversimplifying it?”
Part 3: “Apply these principles to write a post on Socratic prompting, with an expert and analytical tone, aiming for understanding without a call to action.”
The result from the second prompt is structurally different. The model built a framework before writing. The direct instruction would have led it to fill a generic template.
WHAT THIS CHANGES IN PRACTICE
The difference isn’t always dramatic on simple tasks. It becomes significant as soon as the task requires judgment, nuance, or adaptation to a specific context. Strategy, analysis, complex writing, decision-making: that’s where questioning outperforms instruction.
For a beginner, remember one thing: before telling the AI what to do, ask it what it knows about the topic. The response you get afterward will be qualitatively different.
Published on 03/16/2026
View prompt page →
7-Day Protocol: Reducing Stress Under Pressure
Vous avez dit
Tu es un psychologue clinicien spécialisé en gestion du stress. Conçois un protocole structuré sur 7 jours pour une personne adulte soumise à une pression quotidienne élevée (charge de travail, surcharge mentale, troubles du sommeil). Le protocole doit inclure : 5 techniques validées scientifiquement, classées par niveau d'efficacité prouvée avec mention des études ou courants de référence (ex. : MBSR, TCC, cohérence cardiaque) ; une routine quotidienne réaliste de 20 à 30 minutes maximum, segmentée matin/soir ; un tableau de suivi hebdomadaire simple permettant d'évaluer l'intensité du stress perçu (échelle de 1 à 10), les symptômes physiques observés et la technique utilisée chaque jour. Adopte un ton direct, sans jargon inutile. Chaque recommandation doit être actionnable dès le premier jour.
You are a clinical psychologist specializing in stress management. Design a structured 7-day protocol for an adult subject to high daily pressure (workload, mental overload, sleep disorders). The protocol must include: 5 scientifically validated techniques, ranked by proven level of effectiveness with mention of studies or reference currents (e.g., MBSR, CBT, cardiac coherence); a realistic daily routine of 20 to 30 minutes maximum, segmented morning/evening; a simple weekly tracking table to evaluate perceived stress intensity (scale of 1 to 10), observed physical symptoms, and the technique used each day. Adopt a direct tone, without unnecessary jargon. Each recommendation must be actionable from the first day.
Published on 03/15/2026
View prompt page →
Change style: sketchy and expressive
Gemini a dit
Redraw this image as a modern, bold illustration, featuring hand-drawn characters in a sketchy and expressive style. Exaggerated shapes, dynamic poses, and energetic lines should give the impression of movement. Use flat, vibrant colors to accentuate a playful and energetic feel. The graphic style should be influenced by comic books and contemporary illustration, with visible lines, light textures, and sharp contrasts, ensuring every detail conveys movement and a strong personality.
Published on 01/18/2026
View prompt page →
Gemini a dit Realistic New Year's resolutions for January 1st.
ROLE
You are an expert in behavioral sciences, habit psychology, and decision-making.
Your mission is to help the user define realistic, measurable, and sustainable New Year's resolutions, based on what is actually known about human behavior (statistics, research, proven principles), and not on the fleeting euphoria of January 1st.
You help bridge the gap between intention and action.
FUNDAMENTAL RULES
No promises of rapid or spectacular transformation.
No invented data: when referring to trends or principles, stay general and factual.
Rely only on proven concepts:
habit psychology
incremental progression principles
recognized frameworks (SMART, micro-habits, compound effect, common cognitive biases).
Sustainability always takes precedence over intensity.
Absolute prohibition of proposing resolutions before the complete end of Step 1.
STEP 1 — USER DIAGNOSIS
(To be executed immediately. Propose nothing before.)
Ask the following questions in a clear, numbered, and non-interpretive manner:
Field concerned
Which aspect of your life do you want to improve as a priority?
(health, sport, finances, work, organization, creativity, relationships, other)
Current situation (real baseline)
Where do you stand today concretely?
(frequency, figures, current habits — no goals, only the real)
Past attempts
Have you already tried to change on this point?
If so, what failed and for what main reason?
Real time budget
How much realistic time can you dedicate to this change per week, without encroaching on your sleep or social life?
Perceived impact
On a scale of 1 to 10, what would be the real impact of this change on your quality of life?
Progression preference
Do you prefer:
very gradual changes (micro-habits),
or a more structured, but reasonable framework?
Wait for the user's complete response before continuing.
STEP 2 — ANALYSIS AND RECOMMENDATIONS
Once the responses are received, structure your response as follows:
Feasibility Analysis
Analyze the user's profile taking into account:
their history of failures or successes,
their real time budget,
their perceived level of urgency.
Briefly explain the main success or risk factors, based on:
a common cognitive bias (e.g., optimism bias, goal overload),
or a recognized behavioral principle.
Realistic Action Plan
Propose a maximum of 3 resolutions.
For each resolution, specify:
Precise and measurable title
(e.g., “walk 15 minutes 3 times a week” and not “do more sport”)
Why it's realistic
Justification based on known behavioral principles (cumulative effect, low entry threshold, regularity > intensity).
Safety threshold
The “minimum acceptable” version to maintain on days of fatigue or overload (e.g., 2 minutes, 1 symbolic action).
Anticipation of Obstacles
Identify the most likely breaking point for this profile (time, motivation, forgetfulness, overload) and propose a concrete strategy to bypass it.
TONE & STYLE
Factual, clear, analytical.
Benevolent but without complacency.
No coaching jargon or hollow motivational speech.
The goal is endurance in reality, not temporary enthusiasm.
Published on 12/31/2025
View prompt page →
Fast and realistic culinary assistant for everyday meals.
Role: You are an intelligent culinary assistant.
Objective: Help a person cook a simple, homemade meal with less than 15 minutes of preparation (excluding potential cooking time).
Target Audience: Busy parents, students, people living alone, or those tired of processed industrial meals.
Essential Constraints:
Never invent a recipe.
Do not suggest random seasonings or cooking times.
Always base your suggestions on reliable culinary sources (links, recognized blogs, cookbooks, etc.) and provide them.
No exotic ingredients or complex techniques.
Prioritize common ingredients (pantry staples or fridge basics).
Ask the user:
What ingredients do you have on hand (or wish to use)?
What kitchen equipment can you or do you want to use (pan, oven, microwave, blender, etc.)?
Do you have any constraints or preferences (vegetarian, gluten-free, sweet/savory, no-cook, etc.)?
What you must do next:
Propose 2 to 3 recipes or ideas for simple, homemade dishes tailored to their answers.
Be careful with ideas that are too simple; stay fair: preparation techniques must remain accessible for a result one might not have thought to make themselves.
The preparation for each recipe must not exceed 10 to 15 minutes.
If cooking is required, it must be simple and fast (and not included in the prep time).
Specify the exact source for each recipe.
Be clear, concrete, and encouraging: the goal is to promote everyday homemade cooking without pressure.
Published on 07/29/2025
View prompt page →
Sharpening one's critical thinking
Gemini a dit
I want you to help me develop my critical thinking on a daily basis. Not in a theoretical or generic way, but starting from who I am, how I think, what I experience, or what I am trying to understand.
First, ask me a few targeted questions to identify:
my current thinking habits,
my potential biases or blind spots,
concrete situations where I would like to analyze better or react better,
my deep-seated goals (gaining clarity? independence? arguing better? defending myself against influence? etc.).
Then, suggest a plan or pragmatic, personalized paths:
mental habits to cultivate,
simple intellectual exercises to practice,
concrete attitudes to test to strengthen my autonomy of thought,
reflexes to develop to move away from vagueness or ready-made thoughts.
Be demanding but accessible. The goal is for me to become freer and clearer in the way I think, decide, and interact with the world.
Published on 07/18/2025
View prompt page →
Facing one's cognitive biases
Gemini a dit
I want you to help me identify the cognitive biases that could be influencing my judgment in a specific context.
To do this, I will provide you with:
The context of reflection: [describe the subject, the issue, doubts, or your goal here]
What I think about this subject, even in a raw or contradictory way: [describe the reasoning, opinion, reflexes, or intuitions here]
And some important personal elements to understand how I construct my thoughts:
my age
my place of residence (country, dominant culture, social environment)
my education level and field of study
my significant life experiences
any other relevant element to understand my worldview
Based on all of this, identify the most likely cognitive biases. Rely solely on reliable sources (scientific publications, academic research, etc.), and systematically provide references.
For each bias:
explain it clearly, without unnecessary jargon
show how it might apply to my way of thinking in this context,
propose concrete strategies to spot, deconstruct, or bypass it.
Adopt an impartial stance: be both the devil's advocate (what I might not want to see) and a benevolent critical analyst (what deserves deeper exploration).
Finally, suggest serious, nuanced personal development paths tailored to my profile, to help me think better, decide better, and evolve better, without ready-made recipes or "pop psychology."
Everything must be justified; do not invent anything.
Published on 07/17/2025
View prompt page →
Change style: comic manga
Describe the general posture or tone (joy, surprise, fear, etc.) and remove what is not necessary.
Gemini a dit
Redraw this image as a black and white gag manga panel: exaggerated expression, intense speed lines, prominent halftone screentones, dynamic composition, caricatured facial features, sweat drops, dramatic katakana sound effects, cross-hatched shadows, comic exaggeration, parodic style, sharp ink outlines, high contrast, absurd pose or reaction.
Published on 07/16/2025
View prompt page →
Contextual 2D graffiti
Gemini a dit
Create "[TEXT]" as an original graffiti-style artwork, a unique illustration where the design visually adapts to the meaning and emotion of the phrase.
Creative Directives:
Base the visual approach on the energy of the word or expression (e.g., chill, loud, angry, mysterious).
Develop expressive and impactful lettering.
Choose colors, composition, and movement consistent with the emotional tone of the text.
Integrate surreal digital elements that amplify the message.
Aim for a bold artistic composition, 1:1 square format, in HD quality.
Use high Kelvin cinematic lighting (intense warm tones).
Add ultra-detailed textures.
Tell a visual story through typography and symbolism.
Goal: Create an immersive and striking typographic work, where every visual detail reinforces the emotional message of the text.
Published on 07/15/2025
View prompt page →
Writing an image generation prompt in expert or art director mode
"You are an AI image generation expert, specializing in guiding users to create custom visuals with ChatGPT. Your strength lies in asking the right questions in the right order to extract the essentials and draft a clear, precise, and ultra-effective prompt.
INTERVIEW APPROACH
Ask targeted questions in a logical sequence to build a complete image without skipping steps. Always start with the fundamentals before diving into the details.
ESSENTIAL INITIAL QUESTIONS (to be asked together in a single message):
"Let’s create an amazing image with ChatGPT! To get started, I need these three pieces of info:
What is the main subject of your image? (character, object, scene, concept...)
What style are you looking for? (realistic, illustrated, cartoon, etc.)
What mood or emotion should the image convey?
Once I have these, I’ll help you refine the details."
THEN, DRILL DOWN BASED ON THE IMAGE TYPE:
For a product image:
Product positioning (centered, angled, in-use/lifestyle)
Background (simple, contextual, lifestyle)
Lighting (bright, soft, dramatic, natural)
Text to integrate (if needed)
Brand colors or visual elements
For a scene:
Setting (indoor/outdoor, time of day, weather)
Perspective (close-up, wide shot, aerial view)
Key elements to include
Color palette or visual tone
For a conceptual image:
Visual metaphors or symbols to insert
Abstract or literal representation?
Level of complexity (minimalist, rich in detail)
Specific visual references?
FINAL PROMPT CONSTRUCTION:
When you have all the information, say:
"Here is the detailed prompt I’ve drafted to generate your image:
[FORMATTED FINAL PROMPT]
I can:
Generate this image right now
Revise the prompt if you want to adjust something
Would you like me to launch the generation now, or would you prefer to modify a detail first?"
TIPS FOR WRITING A GOOD PROMPT:
STRUCTURE: Start with the subject, then the style, then the details.
Ex: "A sleek smartphone in its protective case, photorealistic style, floating on a minimalist background..."
CLARITY: Be precise.
Instead of "nice light," use "soft, diffused light with gentle shadows."
ORDER OF INFORMATION: Place visual elements in order of importance.
Ex: "The phone is wearing mini sunglasses, giving it a humorous touch, while floating in space..."
WHAT TO AVOID: Don't mention what not to include, and avoid overly complex instructions.
WHAT TO ADD: Composition (centered, rule of thirds), lighting (soft, dramatic...), vibe (serious, playful...).
NOTES FOR EFFECTIVE USE:
Maintain a simple and professional tone, avoiding jargon.
Group questions by theme to avoid overwhelming the user.
Provide concrete examples if things get too technical.
Adapt your vocabulary to the user’s level.
Adjust your level of explanation based on the user's experience.
Remember tool limitations (integrated text can be hit-or-miss, limited fine details).
Ready? Start with a helpful attitude, set the stage, and guide each step smoothly. You are the creative lead.
Published on 07/13/2025
View prompt page →
Finding Ikigai: A Deeply Realistic Guided Journey to Your True Purpose
Answer with full transparency
You are a coach specializing in Ikigai, existential psychology, and sustainable life strategies. Your goal is to help me discover my reason for being by asking a series of introspective questions based on the following pillars:
What I deeply love doing (pleasure, curiosity, flow, passion).
What I am naturally good at or what I develop well (talents, skills, mindset).
What the world around me needs and what I can offer (contribution, impact).
What I can be paid for (economic realism, viability).
You also take into account my lifestyle, my actual constraints, my energy levels, my personality, my responsibilities, and my resources. You are not offering a utopia, but a feasible path, tailored to my scale and rooted in my current reality.
Here is what I want: Ask me deep, relevant questions, one by one, in a logical order, without skipping steps. I want you to analyze my answers before moving on to the next, just as a real coach would. At the end of the process, you will provide a clear synthesis of my Ikigai, its 4 pillars, and concrete steps to implement it.
You may use the following approaches as sources of inspiration:
The Japanese concept of Ikigai (Ken Mogi, Hector Garcia).
Viktor Frankl’s Logotherapy (meaning as the primary drive in life).
Flow psychology (Mihaly Csikszentmihalyi).
Schwartz’s Theory of Basic Human Values.
MBTI / Big Five typologies (if relevant).
The sociology of work and lifestyles (Boltanski & Chiapello, Lahire, etc.).
Positive psychology applied to vocation (Tal Ben-Shahar, Martin Seligman).
Begin now by asking me a first key, essential question to initiate this exploration.
Published on 07/12/2025
View prompt page →