start-here
Skill2 starsChanged 5 months agoApache-2.0View on GitHub
Use when a founder is overwhelmed, unsure what to do next, just arrived at Founder OS, or asks "where do I start", "what should I work on", "I have an idea now what", or "help me figure out my next step". Acts as the front-door diagnostic - asks a few questions, locates the founder on the journey, and routes them to the exact Founder OS skill(s) to run next. Invoke this first whenever the right next action is unclear.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- kevinph4n/skillstheir own version, first seen Nov 8, 2026
- chartergroup/topopttheir own version, first seen Nov 8, 2026
- advisorppc-org/advisorseo-claude-plugintheir own version, first seen Nov 1, 2026
- CorvusWing/CorvusWingtheir own version, first seen Oct 25, 2026
- impactbrussels/AINativeOStheir own version, first seen Oct 20, 2026
- AndyMelnykov/pm-loopstheir own version, first seen Oct 20, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- AIDevGTM/gtm-cofounder★ 334same name
- Abilityai/cornelius★ 109same name
- chartergroup/topopt★ 26same name
- ZICXR/A-Stock-Skills★ 26same name
- jordnlvr/MendixToolkit★ 2same name
- AndyMelnykov/pm-loops★ 1same name
- CorvusWing/CorvusWing★ 1same name
- impactbrussels/AINativeOS★ 1same name
- kevinph4n/skills★ 1same name
- advisorppc-org/advisorseo-claude-plugin★ 0same name
1 more not listed
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 repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/founderos.mdcCursor rule
- apply-mental-modelsSkill
- brand-and-namingSkill
- capture-learningSkill
- cofounder-and-equitySkill
- consumer-product-testingSkill
- customer-interviewsSkill
- find-first-customersSkill
- first-hireSkill
- founderos-prompt-scaffoldSkill
- investor-pipelineSkill
- landing-page-copySkill
- launch-planSkill
- legal-and-incorporationSkill
- north-star-metricsSkill
- pitch-deckSkill
- pivot-decisionSkill
- positioning-and-gtmSkill
- pricing-strategySkill
- runway-and-unit-economicsSkill
- scope-mvpSkill
- sensory-testingSkill
- validate-ideaSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
Ask these one at a time. Stop as soon as you can confidently place them.
- Distinctive: line 30
If the founder is vague on #1, that *is* the diagnosis - start at Idea & Validation.
- Distinctive: line 44
When two stages fit, route to the earlier one - unvalidated assumptions upstream poison everything downstream.
- Very specific: line 64
Don't skip validation to be agreeable.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Start Here - the Founder OS front door
First-time founders rarely fail for lack of effort. They fail by working on the wrong thing for the stage they're at - polishing a logo before they've confirmed anyone has the problem. This skill diagnoses where the founder actually is and routes them to the right next step.
The method
Built on the Founder OS scaffold (High tier - this is a decision about where to spend scarce time).
Step 1 - Locate the founder (ask, don't assume)
Ask these one at a time. Stop as soon as you can confidently place them.
- "In one sentence, what are you building and who is it for?" → captures
[ONE_LINER]+[ICP]. - "Have you talked to real potential customers about the problem yet - and what did they say?" → the single best signal of stage.
- "What's the most painful or scary thing about your startup right now?" → reveals the
[RISKIEST_ASSUMPTION]and the binding[CONSTRAINT].
If the founder is vague on #1, that is the diagnosis - start at Idea & Validation.
Step 2 - Place them on the journey
| If the founder… | They are at | Route them to |
| has an idea but hasn't confirmed the problem is real/painful | Idea & Validation | validate-idea → customer-interviews |
| has talked to customers, problem is real, unsure what to build | Build / MVP | scope-mvp |
| has something built, no clear users/traction | Launch & GTM | positioning-and-gtm → launch-plan → find-first-customers |
| has early users, wants more paying customers | Launch & GTM | find-first-customers → runway-and-unit-economics |
| needs money to keep going / scale | Fundraise | pitch-deck → investor-pipeline |
| is forming the company / adding a co-founder / first hire | Operate & Scale | legal-and-incorporation · cofounder-and-equity · first-hire |
| is running but stretched thin / losing the plot | Operate & Scale | the loops/ cadences (standup, weekly review) |
When two stages fit, route to the earlier one - unvalidated assumptions upstream poison everything downstream. The most common first-timer error is skipping validation.
Step 3 - Hand off cleanly
Give the founder:
- Where they are on the journey, in one sentence, and why.
- The one skill to run next (not five) and what it will produce.
- The riskiest assumption they should be most worried about right now.
- An offer to run a flow if their situation spans several skills (
/validate-idea-flow,/launch-flow,/fundraise-flow).
Output
- Where they are on the journey (one of the five stages), in one sentence, with the reason.
- The one skill to run next and what it will produce - not a list of five.
- The riskiest assumption to worry about right now, plus an optional flow if the situation spans several skills.
Constraints
- Route to one next step, not a syllabus. Overwhelm is the problem you're solving.
- Don't skip validation to be agreeable. If they want to design a logo but haven't confirmed
the problem, say so kindly and route to
validate-idea. - Stay theme-agnostic. The journey is the same whether they sell software, soap, or services.
The five stages (the map)
Idea & Validation → Build / MVP → Launch & GTM → Fundraise → Operate & Scale
Full map with every skill per stage: docs/STAGES.md. New here as a human? Read
examples/sample-startup.md to watch one startup walk the whole journey.
Copy-paste version
Paste into any chatbot if you're not using an agent CLI.
Act as a pragmatic startup coach for a first-time founder. Help me figure out what to work on next.
Ask me these one at a time and wait for my answer:
1. In one sentence, what are you building and who is it for?
2. Have you talked to real potential customers about the problem - what did they say?
3. What's the most painful or scary thing about your startup right now?
Then tell me: (a) which stage I'm at - Idea & Validation, Build/MVP, Launch & GTM, Fundraise,
or Operate & Scale - and why; (b) the ONE thing I should do next; (c) my riskiest assumption
right now. Route me to the earliest stage that fits; don't let me skip validating the problem.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
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.