agentleFS
Sign inStart free
wolulabswolulabs/hermes-founder-os/skills/rapid-saas-builder/SKILL.md

rapid-saas-builder

Skill18 starsChanged 6 months agoMITView on GitHub

Turns an approved PRD into a fast AI-assisted SaaS build pipeline covering frontend, backend, integration, deploy, and testing.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 10 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill after PRD.md exists and the MVP scope is approved.

    line 8
  2. Distinctive:

    Create a clear, checklist-based build pipeline for:

    line 14
  3. Distinctive:

    Use as many of these as available:

    line 25
  4. Very specific:

    If PRD.md is missing, stop and ask for it.

    line 36
  5. Distinctive:

    Do not validate the business idea.

    line 54
  6. Distinctive:

    Do not create marketing plans.

    line 55
  7. Distinctive:

    Do not add features because they are "standard SaaS" unless the PRD requires them.

    line 56
  8. Distinctive:

    Prefer simple, proven tools.

    line 58
  9. Distinctive:

    Prefer one deployable product over fragmented services.

    line 59
  10. Distinctive:

    Keep stages small and independently verifiable.

    line 60
  11. Distinctive:

    Use checklists for each stage.

    line 61
  12. Distinctive:

    Treat AI coding tools as accelerators, not decision-makers.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Rapid SaaS Builder

Use this skill after PRD.md exists and the MVP scope is approved. Rapid SaaS Builder turns product requirements into a staged AI-assisted SaaS build workflow.

This skill is for execution, not validation. It should not validate business ideas, create marketing plans, expand product strategy, or invent features outside the PRD.

Primary Purpose

Create a clear, checklist-based build pipeline for:

  1. Planning / PRD
  2. Frontend Development
  3. Backend Development
  4. Integration
  5. Deploy
  6. Testing

Required Inputs

Use as many of these as available:

  • PRD.md
  • TASKS.md
  • USER_FLOW.md
  • MVP_CHECKLIST.md
  • ARCHITECTURE_REVIEW.md
  • Tech stack or repository context
  • Deployment target
  • Authentication, database, payment, and integration requirements

If PRD.md is missing, stop and ask for it. If architecture is missing, proceed with conservative assumptions and flag them.

Default Output Format

  1. Build Summary
  2. Required Inputs
  3. Frontend Plan
  4. Backend Plan
  5. Integration Plan
  6. Deployment Plan
  7. Testing Plan
  8. Tool Recommendations
  9. MVP Guardrails
  10. Next Implementation Tasks

Operating Rules

  • Build only the MVP scope from PRD.md.
  • Do not validate the business idea.
  • Do not create marketing plans.
  • Do not add features because they are "standard SaaS" unless the PRD requires them.
  • Avoid overengineering.
  • Prefer simple, proven tools.
  • Prefer one deployable product over fragmented services.
  • Keep stages small and independently verifiable.
  • Use checklists for each stage.
  • Treat AI coding tools as accelerators, not decision-makers.
  • For mobile apps, do not implement external checkout for in-app digital goods, credits, premium features, or subscriptions unless a documented store-policy exception applies. Use Apple IAP / Google Play Billing, often via RevenueCat.

MVP Guardrails

Always include:

  • In scope.
  • Out of scope.
  • Assumptions.
  • Dependencies.
  • Manual steps allowed.
  • What not to build yet.
  • Verification required before moving to the next stage.

Stage Handoff

Each stage should end with:

Done:
- [completed item]

Blocked:
- [blocker or none]

Verify:
- [test/check]

Next:
- [next task]

References

  • references/ai-saas-pipeline.md for the full build pipeline.
  • references/frontend-workflow.md for frontend execution.
  • references/backend-workflow.md for backend execution.
  • references/integration-workflow.md for integration execution.
  • references/deploy-workflow.md for deploy execution.
  • references/testing-workflow.md for testing execution.

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.

Check your setup, free