La structure de dossier recommandée
Crée un dossier Claude Cowork à la racine de ton ordinateur. Dedans, trois sous-dossiers :
Claude Cowork/
├── ABOUT ME/
│ ├── about-me.md
│ ├── [fichier 2]
│ └── [fichier 3]
├── OUTPUTS/
└── TEMPLATES/
Seul ABOUT ME est lu automatiquement par Claude au démarrage de chaque session. OUTPUTS et TEMPLATES existent pour que tu puisses les appeler manuellement quand tu en as besoin.
Le dossier ABOUT ME contient 3 fichiers core. Le plus important : about-me.md.
Tu pars de zéro
Ouvre une nouvelle session Cowork. Sélectionne Opus 4.6 + Extended Thinking. Puis colle ce prompt :
You are building my about-me.md file for my Cowork folder. This file will be read by Claude at the start of every session to help you do my job with me. It needs to be concise and high-signal. Your job: interview me using AskUserQuestion (20 questions), then compile the answers into a condensed about-me.md under 2,000 tokens.
## How to interview me
Use AskUserQuestion for every question. One question at a time. Let me use "Other" to dictate long answers when I need to. If I give a vague answer, push back. Ask for a specific example or rephrase. Don't accept "I like to keep things clear" without knowing what clear looks like in my work. Follow interesting threads. If something unexpected comes up, go deeper before moving on.
## What to cover (15-20 questions, adapt based on what matters for my role)
WHO I AM (3 questions)
- What do I do? What's my role, my company, my industry?
- Who do I work with or work for? (clients, team, stakeholders, audience)
- What does a good week of work look like for me?
HOW I WORK (4 questions)
- What tools do I use every day and how?
- Walk me through how I start a typical task from zero to done.
- What does my review/editing/QA process look like?
- When I hand something off (to a client, a boss, a reader), what does "done" look like?
WHAT GOOD LOOKS LIKE (4 questions)
- Show me or describe the best output you've produced recently. What made it good?
- What separates great work from average work in your field?
- When you look at someone else's work and think "this is good," what are you reacting to?
- If I had to judge your work, what should I be looking for?
WHAT YOU HATE (4 questions)
- What's an example of bad work in your field? What specifically makes it bad?
- What patterns, shortcuts, or habits in your industry make you cringe?
- When Claude writes something for you and it's wrong, what's usually off? (tone, structure, detail level, assumptions)
YOUR RULES (3 questions)
- What do you never do in your work? Hard lines you won't cross.
- What are the 2-3 non-negotiables that every piece of your work must have?
YOUR OPINIONS (3 questions)
- What do you believe about your field that most people disagree with?
- What's changing in your industry that most people are ignoring?
- What's overrated in your field right now?
Claude va t'interviewer question par question. Réponds honnêtement, donne des exemples précis. Si ta réponse est vague, il te repoussera, c'est voulu. À la fin, il compile tout en un fichier about-me.md dense et lisible.
Tu as déjà un fichier existant
Upload ton ancien fichier dans Cowork et colle ce prompt :
This is my about-me file and I need to save tokens. Ask me questions on how to trim effectively until we have the perfect document.
La méthode de @rubenhassid : extraire les patterns, virer les transcripts bruts. "I trimmed it to under 2,000 words by extracting the patterns and throwing away the raw transcripts. Almost the same, but 10x less noise."
Ce que ça donne en session
Chaque fois que tu ouvres Cowork et que tu sélectionnes ton dossier, Claude lit ABOUT ME en premier. Il sait qui tu es avant que tu poses ta première question. Tu n'as plus à te réexpliquer, tu n'as plus à coller ton contexte en début de session.
C'est la même logique que ce qu'on avait creusé sur MemPalace et la mémoire IA locale, sauf qu'ici c'est natif dans l'app Claude, sans rien à installer.
