Skill Saas Factory logo

Skill Saas Factory

Organization
IAPro-Community
skill-saas-factory

Build, refactor, review, or plan SaaS products with React/Vite, dashboards, admin panels, Supabase, payments, subscriptions, tenant limits, webhooks, security, infrastructure, and production readiness. Use as the top-level SaaS construction skill when work may need routing to payment, RLS, dashboard, limits, security scan, or deployment skills.

Overview

PublisherIAPro-Community
RepositoryOrquestrador-Maestro
Skill nameskill-saas-factory
Stars
63
Forks
11
Bundled files
4
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by IAPro-Community on GitHub. Read the source before you install it.

Installation

Install the Skill Saas Factory AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/IAPro-Community/Orquestrador-Maestro/tree/v1/codex/skills/skill-saas-factory
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/IAPro-Community/Orquestrador-Maestro.git /tmp/Orquestrador-Maestro
mkdir -p .claude/skills
cp -r /tmp/Orquestrador-Maestro/codex/skills/skill-saas-factory .claude/skills/skill-saas-factory
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Skill Saas Factory in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Skill Saas Factory on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Skill Saas Factory is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

skill-saas-factory

Default SaaS Base

When the user asks to create or modernize a SaaS and gives no narrower scope, treat the baseline product as:

  1. Public landing page.
  2. Registration/sign-up.
  3. Login/sign-in.
  4. Password recovery or magic-link flow when the auth provider supports it.
  5. Onboarding/profile setup.
  6. Authenticated app dashboard.
  7. Billing/plan surface when a payment provider is present.
  8. Admin dashboard for operators.
  9. Security, analytics, and verification gates.

Do not build a marketing-only landing page when the user asked for a SaaS. The first usable app path must exist or be explicitly scoped out.

Workflow

  1. Discover the stack: package scripts, routes, auth provider, database schema/migrations, serverless/API boundaries, payment provider, env requirements, admin layout, and existing tests.
  2. Classify the requested SaaS surface: public, auth, onboarding, app dashboard, admin, billing, analytics, security, or integrations.
  3. Route to focused skills only when they add useful detail. Keep this file as the orchestration layer.
  4. Preserve local patterns before adding architecture. Reuse existing clients, route groups, components, validation, migrations, and deployment conventions.
  5. Implement the smallest coherent SaaS slice: database contract, backend enforcement, UI projection, audit trail, and verification.
  6. Validate with the lightest meaningful gate available: typecheck, build, lint, focused tests, webhook simulation, security scan, or migration dry run.

Public And Auth Surface

For new SaaS work, expect these screens unless the project already has equivalents:

  • Landing: clear product promise, primary CTA to sign up, secondary CTA to sign in, social proof/pricing/FAQ only when useful.
  • Sign up: email/password, OAuth, or magic link according to the existing auth provider; validate errors and duplicate-account states.
  • Login: email/password/OAuth/magic link, forgot-password link, session persistence, clear auth errors.
  • Password recovery: request reset, reset form, expired/invalid token state when supported.
  • Onboarding: minimum profile/workspace setup, plan/trial state, first meaningful action, skip/complete status when appropriate.
  • App dashboard: authenticated home with product-specific empty state, key metrics/actions, account/billing entry points.
  • Admin dashboard: operator-only surface for users, tenants/workspaces, plans, payments, logs, support, settings.

Security rule: every protected screen needs a server/session/data access check. Hidden buttons or hidden routes are not access control.

Surface-To-Skill Routing

  • Landing, public pages, responsive UX, overflow, accessibility: skill-frontend-ux-guardrails.
  • Premium marketing experience, narrative, conversion, and cinematic interaction: skill-premium-web-experience.
  • Modern app UI, component behavior, polished SaaS/admin patterns: skill-modern-ui-patterns.
  • Open-design/tokens/visual QA/component library: skill-open-design-ui.
  • Authenticated dashboard/admin/sidebar/metrics/users/plans/logs: skill-saas-admin-dashboard.
  • Plan limits, trials, feature gates, onboarding completion, blocked states: skill-saas-core-limits.
  • Product events, sign-up funnel, activation, conversion, billing analytics: skill-unified-analytics.
  • Multiagent execution for full SaaS builds: skill-multiagent-orchestration.

Routing

Open only the extra skill needed by the current task:

  • Landing, login, registration, onboarding, responsive/product UX: skill-frontend-ux-guardrails.
  • Premium brand or marketing surface inside the SaaS: skill-premium-web-experience.
  • Modern SaaS UI composition and component states: skill-modern-ui-patterns.
  • Visual design/tokens/component library workflow: skill-open-design-ui.
  • Brazilian PIX/card checkout or AbacatePay billing: skill-abacatepay-integration.
  • Stripe Checkout, Billing, subscriptions, or customer portal: skill-stripe-integration
  • Admin/sidebar/dashboard/metrics/users/plans/logs UI: skill-saas-admin-dashboard.
  • Limits, quotas, entitlements, feature flags, trials, grace periods: skill-saas-core-limits.
  • Supabase RLS, tenant policies, storage policies: skill-supabase-rls.
  • Sign-up activation, conversion events, product analytics, dashboard KPIs: skill-unified-analytics.
  • Local defensive repository security scan: skill-saas-security-scan.
  • DAST/recon against an owned staging URL: skill-saas-dast-recon.
  • Git/CI safety gates: skill-security-hooks.
  • Full SaaS work split across frontend/backend/security/tests: skill-multiagent-orchestration.

Engineering Contract

  1. Keep privileged work server-side. Never expose service-role keys, payment secrets, webhook secrets, provider API keys, or admin tokens to browser code.
  2. Treat billing and entitlement state as backend/database truth. UI state is a projection and checkout redirects are advisory.
  3. Use explicit database selects, tenant/user filters, RLS policies, indexes, idempotency keys, and event ledgers for async flows.
  4. Add audit logs for manual admin actions, payment/entitlement transitions, security-sensitive changes, and automatic limit enforcement.
  5. Validate request bodies and query params at the API boundary. Return structured errors without secrets or stack traces.
  6. Prefer migrations and tests that prove access control, webhook idempotency, and dashboard query shape.
  7. Treat auth flows as product-critical: handle loading, expired session, unauthorized, email confirmation, duplicate account, and recovery states.
  8. Keep public landing analytics privacy-aware; do not collect sensitive form values or payment/auth secrets in event payloads.

Minimum Acceptance Criteria

A new SaaS base is not complete until these are either implemented or explicitly out of scope:

  • Landing page has working CTA routes to registration/login.
  • Sign-up creates or requests an account using the project auth provider.
  • Login establishes a session and redirects to the app dashboard.
  • Protected dashboard rejects unauthenticated users.
  • Onboarding captures the minimum data needed for the product or marks itself unnecessary.
  • Admin routes are role-gated server-side.
  • Billing UI only appears when provider/config/state exists.
  • Empty, loading, error, unauthorized, and mobile states are handled.
  • Typecheck/build/lint or the closest available validation command passes.

Local References

Read only what the task needs:

  • references/project-patterns.md: local JobTask, example-saas, and example-product conventions.
  • references/architecture.md: SaaS module, database, frontend, and backend checklist.
  • references/payments.md: provider selection, webhook, payment table, and entitlement checklist.
  • references/security-infra.md: secrets, Supabase, API, and verification checklist.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Skill Saas Factory AI skill do?

Build, refactor, review, or plan SaaS products with React/Vite, dashboards, admin panels, Supabase, payments, subscriptions, tenant limits, webhooks, security, infrastructure, and production readiness. Use as the top-level SaaS construction skill when work may need routing to payment, RLS, dashboard, limits, security scan, or deployment skills.

Why use Skill Saas Factory on TypingMind?

Because you install it once and use it with any model. Skill Saas Factory is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Skill Saas Factory in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/IAPro-Community/Orquestrador-Maestro/tree/v1/codex/skills/skill-saas-factory. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Skill Saas Factory?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Skill Saas Factory?

As many as you like. As long as a model supports skills, you can use Skill Saas Factory with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Skill Saas Factory AI skill free?

Yes. It is published on GitHub by IAPro-Community under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇