agentleFS
Sign inStart free
wolulabswolulabs/hermes-founder-os/skills/prd-studio/SKILL.md

prd-studio

Skill18 starsChanged 6 months agoMITView on GitHub

Specialist skill for converting validated startup, app, or SaaS ideas into product requirements, MVP scope, user flows, non-goals, acceptance criteria, and implementation task breakdowns. Primary outputs: PRD.md, TASKS.md, USER_FLOW.md, MVP_CHECKLIST.md.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill after validation confirms an idea is worth defining.

    line 8
  2. Distinctive:

    Read the validation report or product brief.

    line 41
  3. Distinctive:

    Write functional and non-functional requirements.

    line 46
  4. Distinctive:

    Do not add features outside validated MVP scope.

    line 53
  5. Distinctive:

    Prefer one core workflow over many partial workflows.

    line 54
  6. Distinctive:

    Use acceptance criteria that can be tested.

    line 58

≈ “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

PRD Studio

Use this skill after validation confirms an idea is worth defining. PRD Studio converts a validation report or product brief into practical product artifacts for implementation.

The goal is clarity, scope control, and build readiness. Do not reopen market validation unless the provided context is too weak to define an MVP.

Primary Outputs

  • PRD.md
  • TASKS.md
  • USER_FLOW.md
  • MVP_CHECKLIST.md

Use This Skill For

  • Product requirements.
  • MVP scope.
  • Feature prioritization.
  • User flows.
  • Functional requirements.
  • Non-functional requirements.
  • Non-goals.
  • Acceptance criteria.
  • Task breakdown.

Do Not Use This Skill For

  • Market validation and scoring.
  • Architecture review.
  • Code implementation.
  • UX critique of an existing product.
  • Landing page or launch copy.

Default Workflow

  1. Read the validation report or product brief.
  2. Extract ICP, problem, promise, constraints, and decision.
  3. Define MVP objective and riskiest assumption.
  4. Draft user flows.
  5. Separate must-have, should-have, later, and explicit non-goals.
  6. Write functional and non-functional requirements.
  7. Define acceptance criteria.
  8. Break work into implementation tasks.
  9. Produce an MVP checklist.

Scope Rules

  • Do not add features outside validated MVP scope.
  • Prefer one core workflow over many partial workflows.
  • Mark assumptions explicitly.
  • Keep non-goals visible.
  • Include manual steps when they reduce build risk.
  • Use acceptance criteria that can be tested.
  • For mobile apps, explicitly classify monetization as digital goods/services, physical goods/services, or external real-world services before specifying payment requirements.
  • For iOS/Android apps selling digital content, premium features, credits, or subscriptions consumed in the app, default to platform in-app purchases through Apple IAP and Google Play Billing, often via RevenueCat. Do not specify Stripe, PayPal, Midtrans, or other external payment gateways for those in-app digital purchases unless a documented platform-policy exception applies.

References

  • references/prd-template.md for PRD structure.
  • references/user-flow-template.md for flow mapping.
  • references/requirements-template.md for requirements.
  • references/mobile-app-requirements.md for mobile app and app-store payment constraints.
  • references/task-breakdown-template.md for implementation tasks.
  • examples/PRD.example.md, examples/TASKS.example.md, and examples/USER_FLOW.example.md for examples.

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