agentleFS
GlamgarOnDiscordGlamgarOnDiscord/claude-saas-blueprint/.claude/skills/prd/SKILL.md

prd

Skill2 starsChanged 6 months agoMITView on GitHub

Workflow complet \"PRD to Tasks\" pour construire un SaaS de A à Z. Brainstorm → PRD → Architecture → Tasks → Exécution automatique.

131 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use modern-go, usecase and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • jidechaoSkill

    modern-go

    Modernize Go code by applying version-appropriate idioms and APIs (gofix-style transformations). Scans go.mod for the Go version, then transforms Go source files to use modern patterns—from Go 1.0 through 1.26+. Use when the user says "现代化","现代Go语言", "地道的", "idiomatic", "modernize", "modern-go", "update Go code", "gofix", or wants to upgrade Go idioms.

    Also in 3 projects that use this

  • gabriellstSkill

    usecase

    Create an application use case. Use when implementing business operations like CreateOrder, ProcessPayment, CancelBooking. Use this skill for any command/mutation that orchestrates domain logic, whether simple CRUD or complex multi-step transactions with sagas. Dispatch hub — routes to typescript/go variants by file extension.

    Also in 3 projects that use this

  • ulises-jeremiasSkill

    trd

    WHAT — Draft and review a Technical Requirements Document (TRD) using the template, typically

    Also in 3 projects that use this

  • SireJeffSkill

    context-optimize

    Context Optimization - Orchestrate RPI workflow TODO generation with interactive scoping

    Also in 3 projects that use this

  • jidechaoSkill

    loop-it

    Automated issue loop with checkpoint/resume: fetch open GitHub issues → dependency-aware topological sort → implement each issue end-to-end → review with /review-it → document with /note-it → ship with /ship-it → repeat. Persists state to .loop-state.json for crash recovery. Triggers on: loop-it, loop issues, auto implement, 批量实现, 循环实现, 实现所有issue, 恢复循环, resume loop.

    Also in 3 projects that use this

  • snarktankSkill

    ralph

    Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.

    Also in 17 projects that use this

  • +2 more from jidechao

The file

Files
SKILL.md

Modes

/prd brainstorm [idée] — Phase 1 : Exploration

Utiliser /brainstorm pour explorer l'idée :

  • Quel problème ça résout ?
  • Qui sont les utilisateurs cibles ?
  • Quels sont les concurrents ?
  • Quel est le business model ?
  • Quel est le MVP minimal ?

Output : Synthèse validée par l'utilisateur.

/prd generate — Phase 2 : Rédiger le PRD

Générer un Product Requirements Document structuré dans docs/prd.md :

# PRD — [Nom du Produit]

## 1. Vision
- Problème résolu
- Proposition de valeur unique
- Utilisateurs cibles

## 2. Scope MVP
- Features incluses (must-have)
- Features exclues (v2, v3)
- Contraintes techniques

## 3. User Stories
- En tant que [rôle], je veux [action], afin de [bénéfice]
- Organisées par priorité (P0, P1, P2)

## 4. Architecture Technique
- Stack choisie (via /brainstorm si pas encore décidé)
- Schema de données (entités principales + relations)
- Diagramme de flux (auth, paiement, features core)
- Intégrations tierces (Stripe, email, etc.)

## 5. Pages & Navigation
- Sitemap avec toutes les pages
- Wireframes textuels des pages clés

## 6. API Endpoints
- Liste des endpoints nécessaires
- Formats de requête/réponse

## 7. Métriques de Succès
- KPIs à tracker
- Critères de "done" pour le MVP

/prd tasks — Phase 3 : Découper en Tasks

Transformer le PRD en tasks atomiques dans .claude/memory/roadmap/backlog.md :

Règles de découpage :

  • [S] = 1 fichier ou moins, [M] = 2-5 fichiers, [L] = 6+ fichiers (→ décomposer avant exec)
  • Chaque task = 1 commit logique, indépendante ou dépendances explicites
  • Ordre : DB schema → Core logic → API → UI → Tests
  • Grouper par sprint (Sprint 1 = fondations, Sprint 2 = features core, Sprint 3 = polish)

Format :

### Sprint 1 — Fondations
- [ ] [S] Setup projet avec /saas-init
- [ ] [M] Schema DB users + organizations + memberships
- [ ] [M] Auth flow (register, login, logout)
- [ ] [S] Layout principal (sidebar, header, navigation)
- [ ] [S] Page dashboard vide

### Sprint 2 — Core Features
- [ ] [M] Feature: [feature 1 du PRD]
- [ ] [M] Feature: [feature 2 du PRD]
- [ ] [M] Intégration Stripe (plans, checkout, webhooks)

### Sprint 3 — Polish & Ship
- [ ] [M] Landing page
- [ ] [S] SEO + meta tags
- [ ] [M] Tests E2E parcours critiques
- [ ] [S] Deploy check + mise en production

/prd exec — Phase 4 : Exécution Automatique

Avant de démarrer :

  1. Lire backlog.md — vérifier que toutes les tasks [L] sont décomposées en [M] ou [S]
  2. Confirmer le sprint à exécuter avec l'utilisateur

Boucle d'exécution :

  1. Prendre la première task non cochée du sprint en cours
  2. Si task [L] → stop, demander à l'utilisateur de la décomposer d'abord
  3. Lancer le skill approprié :
    • Tasks DB → /schema-gen
    • Tasks API → /api-gen
    • Tasks Feature → /feature
    • Tasks UI → /ui gen
    • Tasks Landing → /ui landing
  4. Après complétion → tsc --noEmit + tests ciblés. Si échec → stop, signaler
  5. Cocher la task dans backlog.md, commit
  6. Passer à la suivante

Fin de sprint :

  • /review automatique
  • /deploy-check staging
  • Pause obligatoire — demander validation utilisateur avant sprint suivant

Garde-fous :

  • Task échoue 2 fois → arrêt + demande utilisateur (ne pas retry en boucle)
  • Ne PAS modifier le PRD sans validation utilisateur
  • Ne PAS sauter les tests entre tasks — chaque task doit laisser le projet dans un état stable

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.