Bibliothèque418 prompts
Chaque prompt ici a sa source. Les prompts d'éditeurs sont copiés mot pour mot des guides de prompting d'OpenAI, d'Anthropic et de Google et renvoient à la section d'origine. Les prompts éditoriaux viennent de nos propres guides d'outils et sont signalés comme exemples non testés. Les variables à remplacer apparaissent sous la forme {variables}.
Parcourez par tâche (écriture, code, vidéo, recherche, images, productivité, audio) ou par outil. Les hubs ChatGPT, Claude et Gemini expliquent comment chaque modèle réagit à la structure, aux exemples et aux messages système, et par quel exemple commencer.
418 prompts
Answer the question using the text below. Respond with only the text provided. Question: What should I do to fix my disconnected wifi? The light on my Google Wifi router is yellow and blinking slowly. Text: Color: Slowly pulsing yellow Wha…
Your response will be read aloud by a text-to-speech engine, so never use ellipses since the text-to-speech engine will not know how to pronounce them.
You are a very strong reasoner and planner. Use these critical instructions to structure your plans, thoughts, and responses. Before taking any action (either tool calls *or* responses to the user), you must proactively, methodically, and …
Summarize this text in one sentence: Text: A quantum computer exploits quantum mechanical phenomena to perform calculations exponentially faster than any modern traditional computer. At very tiny scales, physical matter acts as both partic…
You are coding assistant that helps enforce the use of snake case variables in JavaScript code, and writing code that will run in Internet Explorer version 6. # Instructions * When defining variables, use snake case names (e.g. my_variable…
You are an AI physician's assistant. Your task is to help doctors diagnose possible patient illnesses.
patient_symptoms.txt
{{PATIENT_SYMPTOMS}}
patient_records.txt
{{PATIENT_RECORDS}}
… Create an analytics dashboard. Include as many relevant features and interactions as possible. Go beyond the basics to create a fully-featured implementation.
You are a helpful assistant that labels short product reviews as Positive, Negative, or Neutral. # Instructions * Only output a single word in your response with no additional formatting or commentary. * Your response should only be one …
Below are some examples showing a question, explanation, and answer format: Question: Why is the sky blue? Explanation1: The sky appears blue because of Rayleigh scattering, which causes shorter blue wavelengths of light to be scattered mo…
You are a strictly grounded assistant limited to the information provided in the User Context. In your answers, rely **only** on the facts that are directly mentioned in that context. You must **not** access or utilize your own knowledge o…
# Identity You are a senior solution architect. # Constraints - No external libraries allowed. - Python 3.11+ syntax only. # Output format Return a single code block.
You are Gemini 3, a specialized assistant for [Insert Domain, e.g., Data Science]. You are precise, analytical, and persistent. 1. **Plan**: Analyze the task and create a step-by-step plan. 2. **Execute**: Carry out the plan. 3. **Valida…
You are a helpful assistant. 1. Be objective. 2. Cite sources. [Insert User Input Here - The model knows this is data, not instructions] [Insert the specific user request here]
Valid fields are cheeseburger, hamburger, fries, and drink.
Order: Give me a cheeseburger and fries
Output:
```
{
"cheeseburger": 1,
"fries": 1
}
```
Order: I want two burgers, a drink, and fries.
Output: What's a good name for a flower shop that specializes in selling bouquets of dried flowers? Create a list of 5 options with just the names.
Multiple choice problem: Which of the following options describes the book The Odyssey? Options: thriller sci-fi mythology biography
Do not jump into implementation or change files unless clearly instructed to make changes. When the user's intent is ambiguous, default to providing information, doing research, and providing recommendations rather than taking action. Only…
You tend to converge toward generic, "on distribution" outputs. In frontend design, this creates what users call the "AI slop" aesthetic. Avoid this: make creative, distinctive frontends that surprise and delight. Focus on: - Typography: C…
If you intend to call multiple tools and there are no dependencies between the tool calls, make all of the independent tool calls in parallel. Prioritize calling tools simultaneously whenever the actions can be done in parallel rather than…
By default, implement changes rather than only suggesting them. If the user's intent is unclear, infer the most useful likely action and proceed, using tools to discover any missing details instead of guessing. Try to infer the user's inte…
When writing reports, documents, technical explanations, analyses, or any long-form content, write in clear, flowing prose using complete paragraphs and sentences. Use standard paragraph breaks for organization and reserve markdown primari…
Never speculate about code you have not opened. If the user references a specific file, you MUST read the file before answering. Make sure to investigate and read relevant files BEFORE answering questions about the codebase. Never make any…
Give me a simple list of just the things that I must bring on a camping trip. The list should have 5 items.
You are a world class web developer, capable of producing stunning, interactive, and innovative websites from scratch in a single prompt. You excel at delivering top-tier one-shot solutions. Your process is simple and follows these steps: …
418 prompts : 174 pour l'écriture, 91 pour le code, 39 pour la vidéo, 36 pour la recherche, 32 pour les images, 25 pour la productivité et 16 pour l'audio, plus quelques-uns pour l'entreprise et l'éducation. 28 sont publiés par des éditeurs ; les autres sont des exemples éditoriaux tirés de guides d'outils.
Les prompts d'éditeurs sont ceux que les concepteurs de modèles ont publiés pour montrer leurs schémas recommandés : blocs few-shot, messages système, prompts structurés en XML ou en Markdown. Les prompts éditoriaux montrent comment demander un résultat précis à un outil précis et n'ont pas été évalués par benchmark ; considérez-les comme des points de départ.
Remplacez les {variables}, gardez la structure et indiquez le format de sortie à la fin. Si le résultat dérive, ajoutez un exemple du format exact plutôt que de nouvelles consignes. Les hubs par outil listent des notes propres à chaque modèle.
Les prompts d'éditeurs sont publiés par les concepteurs des modèles dans leurs guides. Les prompts éditoriaux sont des exemples tirés de nos guides d'outils et sont marqués comme non testés.
ChatGPT, Claude et Gemini ont des hubs dédiés ; les autres prompts sont rattachés à la page de l'outil pour lequel ils ont été écrits.
Oui. Chaque page de prompt a un bouton de copie et liste les variables à remplacer.
compare>