Product SaaSScaffoldingFull Stack

SaaS Scaffolder

Generate complete, production-ready SaaS projects from a product brief.

$skillfish add ~skills/saas-scaffolder

Capabilities Real Examples Get Started Models & Context

What This Skill Can Do

Concrete capabilities you get when you install this skill.

Scaffold production-ready SaaS projects with auth, billing, and multi-tenancy

Generate multi-tenant database schemas with row-level security policies

Integrate Stripe subscriptions, webhooks, and billing portal flows

Configure authentication with Supabase, Clerk, or Auth0

Set up CI/CD pipelines and deployment infrastructure (Vercel, Railway, AWS)

Create environment configuration, secrets management, and local dev setup

Real Conversations

See how the SaaS Scaffolder skill responds to actual requests. These are representative examples of what your AI agent will produce.

You

I want to build a project management SaaS for construction companies. Features: project tracking, subcontractor management, document uploads, invoicing. Stack preference: Next.js, Supabase, Stripe. Generate the full scaffold.

Agent

ConstructPM — SaaS Scaffold

Stack: Next.js 14 (App Router) + Supabase (Postgres + Auth + Storage) + Stripe + shadcn/ui

Directory structure:

constructpm/
├── app/
│   ├── (auth)/login, signup, callback
│   ├── (dashboard)/
│   │   ├── projects/[id]/
│   │   ├── subcontractors/
│   │   ├── documents/
│   │   └── invoices/
│   └── api/
│       ├── webhooks/stripe/
│       └── upload/
├── components/ui/     # shadcn components
├── lib/
│   ├── supabase/server.ts, client.ts
│   ├── stripe.ts
│   └── types.ts
└── supabase/migrations/

Core DB schema (Supabase migrations):

create table projects (
  id uuid primary key default gen_random_uuid(),
  org_id uuid references organizations(id),
  name text not null,
  status text default 'active',
  created_at timestamptz default now()
);

create table subcontractors (
  id uuid primary key default gen_random_uuid(),
  org_id uuid references organizations(id),
  name text, email text, trade text,
  stripe_account_id text
);

create table documents (
  id uuid primary key default gen_random_uuid(),
  project_id uuid references projects(id),
  file_path text,
  uploaded_by uuid references auth.users(id)
);

Row-Level Security: Every table scoped to org_id via Supabase RLS policies.

Stripe setup: Subscription billing (monthly/annual) + Connect for subcontractor payouts.

Shall I generate the full Next.js auth flow, the Supabase RLS policies, and the Stripe webhook handler?

You

We built a SaaS MVP with a single shared database — all users share the same tables with a user_id column. Now an enterprise customer wants their own isolated data. How do we add multi-tenancy without a full rewrite?

Agent

Multi-Tenancy Migration — Row-Level to Schema-Level

You're currently using row-level multi-tenancy (single schema, user_id column). Enterprise customers often require schema-level or database-level isolation. Here's the migration path that avoids a full rewrite:

Option 1: Row-level with RLS (recommended for most SaaS) If you're on Postgres/Supabase, you can upgrade your existing approach with Row-Level Security:

-- Add org_id to all tables (nullable at first)
ALTER TABLE projects ADD COLUMN org_id uuid REFERENCES organizations(id);

-- RLS policy: users only see their org's data
CREATE POLICY org_isolation ON projects
  USING (org_id = current_setting('app.current_org_id')::uuid);

-- Set context at connection time
SET app.current_org_id = '{{org-uuid}}';

This gives enterprise customers logical isolation with cryptographic enforcement — satisfies most enterprise requirements and passes SOC 2 audits.

Option 2: Schema-per-tenant (true isolation) For customers requiring strict data segregation:

-- Create isolated schema per enterprise tenant
CREATE SCHEMA tenant_acme;
CREATE TABLE tenant_acme.projects (LIKE public.projects INCLUDING ALL);

Route enterprise customers to their schema at the application layer based on subdomain or API key.

Migration plan (zero-downtime):

Add org_id column nullable → backfill from user_id → make non-nullable
Deploy RLS policies with a feature flag (off by default)
Enable RLS for new signups first, then migrate existing accounts
For the enterprise customer: provision their schema, migrate their rows, flip their connection string

Timeline: 3–4 sprints for a typical SaaS codebase.

Get Started

How to install and use this skill in your preferred environment.

Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase. Web-based AI can use the knowledge and frameworks, but won't have tool access.

Models & Context

Which AI models and context windows work best with this skill.

Recommended Models

Best

Claude Opus 4 Claude Sonnet 4 GPT-4.1 Gemini 2.5 Pro Grok 3 Kimi K2

Good

Claude Haiku 4.5 GPT-4.1 mini Gemini 2.5 Flash Grok 3 mini

Larger models produce more detailed, production-ready outputs.

Context Window

This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.

8K Skill only

32K+ Skill + conversation

100K+ Skill + references + codebase

All current frontier models (Claude, GPT, Gemini) support 100K+ context. Use the full window for complex multi-service work.

Pro tips for best results

1

Be specific

Include numbers — users, budget, RPS — so the skill can size the architecture.

2

Share constraints

Compliance needs, team size, and existing stack all improve the output.

3

Iterate

Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.

4

Combine skills

Pair with companion skills below for end-to-end coverage.

Ready to try SaaS Scaffolder?

Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.