Prompts

Prompts IA sélectionnés pour des usages professionnels, créatifs et techniques.

Claude Opus 4.6 (works well with GPT-5.4 and Gemini 3 Pro — any model with strong instruction-following for structured comparison tasks performs well)CarrièreYou found a job posting for a role that's a stretch — one level above your current title — and you have 45 minutes before the application closes tonight. You need to know fast whether your resume as-is will get filtered out, and what to fix first if it will.

L'Analyseur d'Écarts de CV : Transformez une Offre d'Emploi en Liste Priorisée de Corrections

Comparez votre CV à une offre d'emploi spécifique ligne par ligne et obtenez des écarts classés et des réécritures XYZ avant de soumettre.

9/12/2026

prompt-engineeringCareer

Claude Opus 4.6 (works well with GPT-5.4 and Gemini 3 Pro — any model with strong reasoning over role/priority inference performs well)productivityYou have a 30-minute call in two hours with a VP of Engineering at a potential client and two of their staff engineers, and all you have is their names, titles, and a two-line agenda emailed by an assistant. You've never spoken with any of them before.

Le sprint de préparation de réunion : transformez des noms de participants et un ordre du jour en briefing de cinq minutes

Transformez quelques noms, titres et un ordre du jour vague en un briefing de cinq minutes qui révèle la véritable objection avant le début de la réunion.

9/12/2026

prompt-engineeringproductivity

Claude Opus 5 (strong at holding multiple data points in context while distinguishing statistically significant trends from noise); GPT-5.4 and Gemini 3 Pro also handle this well, though Claude is more consistent about flagging small-base percentage distortions unprompted.Analyse de DonnéesYou're a data analyst at a mid-size e-commerce company. Q3 sales data just landed in a spreadsheet with dozens of columns across 5 regions, and your VP of Sales wants the 3 things that matter by end of day — not a dashboard, not a slide deck, just the insights.

Le Convertisseur de Données Brutes en Note Exécutive : Transformez des Chiffres Désordonnés en Analyse en 4 Étapes Prête à l'Action

Un prompt structuré qui force le modèle à passer par les tendances, anomalies, implications commerciales et recommandations classées — au lieu de simplement décrire ce que montrent les données.

9/11/2026

data analysisanalytics

Claude Opus 5 (strong at generating genuinely distinct psychological angles rather than superficial rewordings of the same hook); GPT-5.4 and Gemini 3 Pro also work well, though Claude tends to produce more varied trigger coverage without a follow-up prompt asking it to differentiate further.marketingYou're a content marketer at a B2B SaaS company with 45 minutes before Monday's content calendar meeting. You need headline options for next week's blog post launch, but the three drafts you've already written all sound like slight rewordings of the same idea.

Le Générateur d'Accroches de Titres : Transformez Un Sujet en 20 Déclencheurs Psychologiques Étiquetés

Un prompt structuré qui produit 20 variantes de titres réparties sur six déclencheurs psychologiques — écart de curiosité, spécificité, aversion à la perte, cadrage contraire, urgence et identité — chacune étiquetée avec la raison de son efficacité pour votre audience.

9/11/2026

marketingcopywriting

Claude Opus 5 (best for reasoning through non-obvious edge cases and generating well-structured test code); also works well with GPT-5.4 or Gemini 3 Pro for most languages, though Claude tends to catch more subtle edge cases in code-review-style tasks.Outils de DéveloppementYou're a backend developer at a mid-size e-commerce company. You just finished writing a discount-calculation function for the checkout flow, code review is in 20 minutes, and you haven't written a single test yet.

L'Auditeur de Couverture de Tests : Transformez Toute Fonction en Suite pytest Complète Avant la Revue de Code

Un prompt structuré qui transforme une fonction et son contexte d'appel en tests de chemin nominal, cas limites, scénarios d'erreur et tests d'intégration.

9/10/2026

testingdeveloper tools

Works well with any strong reasoning model — Claude Opus 4.8, GPT-5.4, or Gemini 3 Pro. This task benefits from a model that generates multiple plausible interpretations rather than converging early on one guess — if a response feels too confident after only one pass, explicitly ask it to generate at least two alternative readings before continuing.CarrièreYou just left a performance review or 1:1 with feedback like 'be more strategic' or 'show more executive presence' — phrases that sound important but give you no idea what to actually change before the next review cycle.

Le Décodeur de Feedback du Manager : Transformez un Retour Vague en Plan d'Action Concret

Un prompt qui génère plusieurs interprétations concrètes d'un retour ambigu comme « sois plus stratégique », identifie la plus probable, et construit un plan mesurable sur 30-60-90 jours.

8/20/2026

Careercommunication

Works well with any strong reasoning model — Claude Opus 4.8, GPT-5.4, or Gemini 3 Pro. The sensitivity-analysis step (identifying which reweighted criterion would flip the recommendation) requires holding multiple weighted scenarios in mind simultaneously, so avoid smaller or faster models for this task — ask the model to show its work step by step rather than just stating a final ranking.productivityYou're facing a decision with three or more viable options — a vendor selection, an infrastructure migration path, a hiring choice between finalists, a build-versus-buy call — and need to present a recommendation that will hold up when a skeptical stakeholder asks why you didn't pick a different option.

Le Constructeur de Matrice de Décision : Transformez une Décision Multi-Options en une Recommandation Pondérée et Défendable

Un prompt structuré d'analyse décisionnelle qui note chaque option selon des critères pondérés, signale les recommandations fragiles et inclut le contre-argument le plus solide contre sa propre conclusion.

8/20/2026

productivitydecision-making

Works well with any strong reasoning model — Claude Opus 4.8, GPT-5.4, or Gemini 3 Pro all handle the vesting-schedule math and present-value comparisons reliably. This task is arithmetic-heavy (strike price, vesting cliffs, dilution estimates), so double-check the model's math on the actual numbers rather than trusting it blindly — ask it to show its work step by step rather than just stating a final comparison figure.Finance et NégociationYou've received a job offer from a private company that includes a mix of base salary and stock options or RSUs, and the recruiter's pitch emphasized the equity's potential upside without giving you a clear way to compare it against your current compensation or a competing cash-heavy offer.

Le Décodeur d'Offre d'Equity : Transformez une Rémunération en Actions Confuse en une Vraie Position de Négociation

Un prompt d'analyse de rémunération qui modélise des scénarios réalistes de baisse, de base et de hausse pour une attribution d'actions ou d'options — au lieu du chiffre optimiste unique par lequel commencent la plupart des offres d'emploi.

8/17/2026

CareerNegotiation

Works best with strong long-context reasoning models — Claude Opus 4.8 or Gemini 3 Pro handle cross-referencing dozens of scattered notes reliably without losing track of earlier details. GPT-5.4 works well too but for very large note dumps (50+ pages), split the input into two passes (characters/timeline, then locations/rules) rather than one giant prompt to avoid it missing contradictions buried deep in the context.creativeYou are 8 months into drafting a fantasy novel — or a game's narrative bible — across chapter drafts, a Discord brainstorming log with beta readers, sticky notes, and a half-finished spreadsheet of character ages. You are about to start the next book or the next act and need one reliable reference before you keep writing, but you no longer remember every detail you established months ago.

La Bible de Cohérence du Worldbuilding : Transformez des Notes de Récit Éparses en un Document Canonique Structuré

Un prompt façon éditeur de continuité qui lit des mois de notes désorganisées de fiction ou de jeu et produit un document canonique structuré — en signalant explicitement les contradictions au lieu de les dissimuler.

8/17/2026

fiction-writingworldbuilding

Works best with strong reasoning models — Claude Opus 4.8, GPT-5.4, or Gemini 3 Pro handle the multi-factor risk ranking (security priority vs. breaking-change severity vs. team capacity) reliably. Weaker models tend to rank everything as "medium risk" instead of actually differentiating, so it's worth checking that the output gives genuinely different reasoning per package rather than a templated response.Outils de DéveloppementYour `npm outdated` output lists 34 packages behind, most flagged for major-version gaps. Your tech lead wants a prioritized upgrade plan before tomorrow's sprint planning, and you don't have time to read every changelog yourself.

L'Évaluateur de Risque de Mise à Niveau des Dépendances : Transformez une liste de paquets obsolètes en un plan de mise à niveau hiérarchisé

Un prompt qui transforme votre liste de dépendances obsolètes en un plan de mise à niveau classé par ordre de risque — séparant les changements majeurs documentés des suppositions éclairées, et respectant la capacité de sprint réelle de votre équipe.

8/14/2026

prompt-engineeringdeveloper tools

Works well with any frontier model (Claude Opus 4.8, GPT-5.4, Gemini 3 Pro). Needs strong cultural-pragmatics knowledge to avoid flattening nuance into stereotype, so smaller or older models tend to produce generic, less reliable rewrites.Rédaction et CommunicationYou're a US-based product manager about to email a factory partner in Japan about a quality issue that will delay shipment by three weeks. Your instinct is to write it the way you'd write to a US vendor: direct, blunt about the problem, demanding a revised timeline by Friday.

L'adaptateur de messages interculturels : réécrivez n'importe quel message pour l'adapter aux normes de communication d'une culture spécifique

Un prompt qui réécrit un message brouillon pour l'adapter aux normes d'une culture spécifique en matière de franchise, de hiérarchie et de transmission des mauvaises nouvelles — sans éédulcorer le fond réel que vous devez communiquer.

8/14/2026

prompt-engineeringworkplace communication

Works well with any current-generation reasoning model — GPT-5.4, Claude Sonnet 5, and Gemini 3 Pro all handle the multi-factor tradeoff reasoning (cost structure vs. competitor pricing vs. buyer psychology) accurately. Weaker models tend to default to "match the competitor median" instead of actually reasoning from the cost structure provided, so it is worth sanity-checking that the output explicitly references your cost structure, not just your competitors.Startups et EntreprisesA solo founder is two weeks from launching a B2B project-management SaaS tool for construction firms. Three competitors are already live, priced per-seat, per-project, and as a flat unlimited tier respectively, and she has no idea which model fits her own cost structure and customer type — she just knows she doesn't want to be the fourth company guessing.

L'analyseur de stratégie tarifaire : alignez votre modèle de prix sur votre structure de coûts réelle

Un prompt structuré qui recommande un modèle de tarification basé sur vos véritables facteurs de coûts et la psychologie de l'acheteur, pas seulement une copie de ce que facturent les concurrents, avec un prix prêt à décider et une objection à laquelle vous devrez répondre.

8/13/2026

prompt-engineeringstartups