agentleFS
wolulabswolulabs/hermes-founder-os/skills/founder-os/SKILL.md

founder-os

Skill18 starsChanged 6 months agoMITView on GitHub

Top-level orchestration skill for Hermes Agent startup workflows. Use it to route ideas between validation, PRD, architecture, build, UX, growth, and launch skills; summarize context between stages; prevent context pollution; and recommend the next workflow without doing every specialist task directly.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. AdeyStudios/skills★ 1same name
    2. zhouczcz/founder-os★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository8 other files it gives its agents.

The file

Show its rules and text

We split this skill into the rules it gives an agent

19 rules. About 0 are common, 11 are distinctive, and 8 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 8

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use Founder OS to:

    line 14
  2. Distinctive:

    Keep decisions, assumptions, and outputs separated.

    line 21
  3. Very specific:

    Use validation-lab for idea validation, market demand, pain points, competitors, ICP, scoring, and Go / No-Go / Pivot.

    line 26
  4. Very specific:

    Use prd-studio for PRD, MVP scope, user flows, requirements, non-goals, and task breakdown.

    line 27
  5. Very specific:

    Use architecture-reviewer for system architecture, database design, security, scaling, maintainability, and technical debt.

    line 28
  6. Very specific:

    Use rapid-saas-builder for turning an approved PRD into a fast AI-assisted SaaS build pipeline across frontend, backend, integration, …

    line 29
  7. Very specific:

    Use build-system for implementation planning, coding execution, refactor rules, and test checklists.

    line 30
  8. Very specific:

    Use ux-critic for UX review, onboarding friction, dashboard critique, CTA clarity, mobile usability, and conversion friction.

    line 31
  9. Very specific:

    Use growth-lab for landing page copy, SEO, content strategy, ads angles, short-form scripts, email copy, and acquisition.

    line 32
  10. Very specific:

    Use launch-room for launch readiness, deployment checklist, Product Hunt, announcements, and post-launch review.

    line 33
  11. Distinctive:

    Do not force every project through every stage.

    line 50
  12. Distinctive:

    Ask for only the missing information needed to start the next workflow.

    line 57
  13. Distinctive:

    If enough context exists, provide the exact prompt the user can send to the next skill.

    line 58
  14. Distinctive:

    Use this format when routing:

    line 62
  15. Distinctive:

    Do not carry raw brainstorming unless it directly affects the next stage.

    line 86
  16. Distinctive:

    Do not carry long research dumps.

    line 87
  17. Distinctive:

    Do not mix code details into growth or validation context unless relevant.

    line 88
  18. Distinctive:

    Do not let PRD scope expand beyond validated evidence.

    line 89
  19. Distinctive:

    Do not use Founder OS as the main skill when the user clearly asks for:

    line 94

≈ “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

Founder OS

Founder OS is the strategic orchestration layer for Hermes Agent. It decides what workflow should run next, keeps context clean between stages, and prevents one conversation from becoming a bloated mix of ideation, validation, PRD writing, coding, marketing, and launch planning.

It should not act as the primary worker for validation reports, PRDs, code implementation, marketing assets, UX audits, launch plans, or architecture reviews unless the user explicitly asks for a compact strategic answer.

Core Role

Use Founder OS to:

  • Understand the user's current startup stage.
  • Route the task to the right specialist skill.
  • Summarize context before moving to another skill or channel.
  • Identify missing inputs before a workflow starts.
  • Recommend the next best action.
  • Keep decisions, assumptions, and outputs separated.
  • Prevent context pollution from raw brainstorming, research, code, and launch details.

Specialist Skill Routing

  • Use validation-lab for idea validation, market demand, pain points, competitors, ICP, scoring, and Go / No-Go / Pivot.
  • Use prd-studio for PRD, MVP scope, user flows, requirements, non-goals, and task breakdown.
  • Use architecture-reviewer for system architecture, database design, security, scaling, maintainability, and technical debt.
  • Use rapid-saas-builder for turning an approved PRD into a fast AI-assisted SaaS build pipeline across frontend, backend, integration, deploy, and testing.
  • Use build-system for implementation planning, coding execution, refactor rules, and test checklists.
  • Use ux-critic for UX review, onboarding friction, dashboard critique, CTA clarity, mobile usability, and conversion friction.
  • Use growth-lab for landing page copy, SEO, content strategy, ads angles, short-form scripts, email copy, and acquisition.
  • Use launch-room for launch readiness, deployment checklist, Product Hunt, announcements, and post-launch review.

Default Workflow

Recommended path:

venture-lab
-> validation-lab
-> prd-studio
-> architecture-reviewer
-> rapid-saas-builder
-> ux-critic
-> growth-lab
-> launch-room

Do not force every project through every stage. Route based on the user's current bottleneck.

How To Operate

  1. Classify the request by stage and intent.
  2. State the recommended specialist skill or channel.
  3. Produce a compact routing brief.
  4. Ask for only the missing information needed to start the next workflow.
  5. If enough context exists, provide the exact prompt the user can send to the next skill.

Routing Brief Format

Use this format when routing:

Recommended next workflow: [skill/channel]

Why:
- [reason 1]
- [reason 2]

Context to carry forward:
- Idea:
- Target user:
- Current evidence:
- Key assumptions:
- Constraints:
- Desired output:

Suggested next prompt:
"[prompt]"

Context Handoff Rules

  • Carry forward decisions, constraints, evidence, and open questions.
  • Do not carry raw brainstorming unless it directly affects the next stage.
  • Do not carry long research dumps; summarize useful signals.
  • Do not mix code details into growth or validation context unless relevant.
  • Do not let PRD scope expand beyond validated evidence.
  • Label uncertain facts as assumptions.

When Not To Use Founder OS

Do not use Founder OS as the main skill when the user clearly asks for:

  • A full validation report.
  • A complete PRD or task list.
  • Code implementation.
  • A technical architecture review.
  • Landing page copy or SEO plan.
  • A UX audit.
  • Launch checklist or announcement copy.

In those cases, route directly to the appropriate specialist skill.

References

  • references/orchestration-framework.md for orchestration workflow and handoff rules.
  • references/decision-routing.md for routing logic and 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.