Générateur de résumé MVP

Remplir ce prompt

Génère, à la fin d’un MVP, un fichier abstract.md qui retrace le parcours du projet, les impasses, les approches infructueuses et les décisions clés pour référence future.

Modèle de prompt

You are a senior engineer documenting the journey of a finished MVP. Your task is to create an `abstract.md` file at the project root that captures NOT the final state of the code, but the path that led there. Think of it as the older, wiser sibling of CLAUDE.md: it preserves context, lessons, and dead ends so future contributors (human or AI) understand WHY the code looks the way it does.

### PROJECT CONTEXT
{{Project Context: if used in an AI agent use the current project}}

### TARGET AUDIENCE
The document will be read by: {{Audience: Future Me, A New Developer, An AI Coding Agent, Stakeholders}}
Match the tone, terminology, and level of technical depth to this audience.

### LEVEL OF DETAIL
{{Detail Level: *Deep Dive, Balanced Overview, Concise Summary}}

### INSTRUCTIONS
Analyze the entire codebase, commit history, comments, TODOs, deprecated files, and any existing documentation. Then produce an `abstract.md` with the following sections:

1. **What This App Does** — A plain-language description of the MVP's purpose and core value proposition. No marketing fluff.
2. **The Original Vision vs. What Shipped** — How the initial idea evolved. What was cut, what was added, what changed direction.
3. **Architecture As-Is** — A short, honest description of the current architecture, including the parts that are clean and the parts that are duct-taped.
4. **What Was Tried and Failed** — Concrete approaches, libraries, frameworks, or designs that were attempted and abandoned. For each, explain WHY it failed.
5. **Dead Ends and Rabbit Holes** — Specific problems that consumed disproportionate time. Include what the trap looked like and how it was escaped (or worked around).
6. **Key Decisions and Trade-offs** — The 5–10 most consequential decisions, each with the alternatives considered and the reasoning behind the choice.
7. **Known Debt and Smells** — Code, structure, or dependencies that work but should not survive a rewrite. Be brutally honest.
8. **What I Would Throw Away** — If starting fresh tomorrow, which parts of this MVP would not make it into v2, and why.
9. **Lessons Learned** — Hard-won insights, both technical and product-related, that should not be forgotten.
10. **Open Questions** — Unresolved problems, untested assumptions, and areas where the team flew blind.

### STYLE
- Use first-person singular ("I") or plural ("we") consistently.
- Prefer short paragraphs and bullet points over walls of text.
- Cite specific files, commits, or modules where relevant.
- Do not sanitize failures. Dead ends are the most valuable part of this document.

### OUTPUT
Write the final result directly to `abstract.md` at the project root. Do not return the content in chat — create the file.

Guide du prompt

Idéal pour

  • Partir d'un prompt structuré et réutilisable plutôt que d'une conversation vierge.
  • Adapter le prompt à vos propres données tout en conservant l'intention d'origine.
  • Les workflows liés à Software Development.

Comment l'utiliser

  1. Copiez le modèle de prompt complet.
  2. Remplacez chaque variable par votre propre contexte ou choisissez l'une des options suggérées.
  3. Collez le prompt complété dans ChatGPT, Claude, Gemini ou un autre assistant IA.

Variables de ce prompt

Project Context

if used in an AI agent use the current project

Audience

Future Me, A New Developer, An AI Coding Agent, Stakeholders

Detail Level

Deep Dive, Balanced Overview, Concise Summary

Exemple de départ

You are a senior engineer documenting the journey of a finished MVP. Your task is to create an `abstract.md` file at the project root that captures NOT the final state of the code, but the path that led there. Think of it as the older, wiser sibling of CLAUDE.md: it preserves context, lessons, and dead ends so future contributors (human or AI) understand WHY the code looks the way it does.

### PROJECT CONTEXT
if used in an AI agent use the current project

### TARGET AUDIENCE
The document will be read by: Future Me
Match the tone, terminology, and level of technical depth to this audience.

### LEVEL OF DETAIL
Deep Dive

### INSTRUCTIONS
Analyze the entire codebase, commit history, comments, TODOs, deprecated files, and any existing documentation. Then produce an `abstract.md` with the following sections:

1. **What This App Does** — A plain-language description of the MVP's purpose...

Comment fonctionnent les variables

Syntaxe des variables

Les variables sont entourées de {{ et }} et suivent ce modèle :

{{variable name: option1, option2, option3 }}

Variables prédéfinies

Une sélection peut référencer une liste de variables prédéfinie à l'aide de crochets. Elles apparaissent en [orange] et fournissent des valeurs courantes comme des couleurs, des tons ou des langues.

{{Tone: [tones] }}

Listes de choix personnalisées

Vous pouvez aussi fournir une liste de choix en ligne, séparés par des virgules.

{{Format: bullet points, paragraphs, numbered list }}
💡

Astuce : vous n'avez pas besoin de l'application PUCO pour utiliser ces prompts ! Copiez simplement le modèle et remplacez chaque section {{…}} par votre propre texte directement dans ChatGPT, Claude, Gemini ou tout autre assistant IA.

Utilisez ce prompt en quelques secondes, pas en minutes

Installez PUCO pour Mac : appuyez sur un raccourci dans n'importe quelle app, remplissez un formulaire intelligent, collez dans ChatGPT, Claude ou Gemini. Chaque variable devient un menu déroulant soigné. Vos dernières valeurs sont mémorisées.

Télécharger sur le Mac App Store