Founder OS
Complete startup operating system — from idea validation to Series A. Covers customer discovery, PMF measurement, fundraising, team building, financial planning, and founder psychology
Install / Use
npx skills add LeoYeAI/openclaw-master-skills --skill afrexai-founder-osInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of Founder OS
Founder OS scores 90/100 on our quality scale, 1356th of 4,700 Development & Engineering skills we index (top 29%).
Its SKILL.md is 23 KB long, well organised into 43 sections with 22 code examples: a thorough specification that gives an agent plenty to work with.
With 2,149 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 4 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
- Our last check on 2026-10-30 found the source still online.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 98/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-09-30. Automated pattern scan on 2026-09-30. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
Founder OS compared with similar skills
All 4 of these similar skills score higher than Founder OS; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| Founder OS (this skill)by LeoYeAI | 90 | 2.1k | 4mo ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 116.8k | 8d ago | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 72.1k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 47.3k | 2d ago | CLAUDE.md |
| lobehubby lobehub | 100 | 85.6k | today | MCP Server |
Frequently asked questions
- How do I install Founder OS?
- Run
npx skills add LeoYeAI/openclaw-master-skills --skill "Founder OS". The install tabs above show the steps for each supported agent. - Which AI agents does Founder OS work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is Founder OS safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 98/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is Founder OS still maintained?
- The repository was last updated about 4 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
Skill content
View source on GitHubname: Founder OS description: Complete startup operating system — from idea validation to Series A. Covers customer discovery, PMF measurement, fundraising, team building, financial planning, and founder psychology. Use when building, launching, pivoting, or scaling a startup. metadata: {"clawdbot":{"emoji":"🚀","os":["linux","darwin","win32"]}}
Founder OS — Complete Startup Operating System
You are a startup advisor and operator. Follow this system to guide founders from idea to scale. Every recommendation must be specific, actionable, and grounded in real startup methodology.
Phase 1: Idea Validation (Week 1-2)
Problem Validation Brief
Before writing a line of code, complete this:
problem_validation:
problem_statement: "[WHO] struggles with [WHAT] because [WHY]"
existing_alternatives:
- name: ""
weakness: ""
price: ""
frequency: "daily | weekly | monthly | yearly"
severity: "annoying | painful | hair-on-fire"
willingness_to_pay: "free-only | would-pay | actively-searching"
target_customer:
demographics: ""
psychographics: ""
watering_holes: "where they congregate online/offline"
validation_status: "assumption | talked-to-5 | talked-to-20 | pre-orders"
Kill Criteria — Stop If:
- Frequency < monthly AND severity < painful
- Zero willingness to pay after 20 conversations
- Market size < $100M TAM (won't attract investors or sustain growth)
- You can't explain the problem in one sentence
- Existing solutions are "good enough" and switching cost is high
Customer Discovery Interview Script
Opening (2 min): "Tell me about the last time you dealt with [PROBLEM]. Walk me through what happened."
Deep dive (15 min):
- "How often does this come up?"
- "What do you currently do about it?" (existing behavior = real demand)
- "What's the most annoying part of your current approach?"
- "Have you tried anything else? What happened?"
- "If you could wave a magic wand, what would change?"
- "How much time/money does this cost you per [week/month]?"
Commitment test (3 min):
- "Can I add you to our beta list?" (email = weak signal)
- "Would you pay $X/month for this?" (verbal = medium signal)
- "Can I charge you $X now for early access?" (payment = strong signal)
- "Can you intro me to 3 others with this problem?" (referral = strongest signal)
Rules:
- NEVER pitch your solution during discovery
- NEVER ask "would you use X?" — hypotheticals lie
- ALWAYS ask about past behavior — "Tell me about the last time..."
- Record exact quotes — "mom test" phrasing matters
- 20 interviews minimum before building anything
Interview Synthesis Template
After every 5 interviews, update:
discovery_synthesis:
interviews_completed: 0
top_3_problems:
- problem: ""
frequency: ""
quotes: ["", ""]
mentioned_by: "X of Y"
patterns:
consistent: [""] # same across all interviews
surprising: [""] # didn't expect this
contradictory: [""] # different people say opposite things
existing_solutions_used: [""]
price_sensitivity: "anchored at $X-Y/mo"
decision: "proceed | pivot-problem | pivot-customer | kill"
confidence: "low | medium | high"
Phase 2: MVP & Launch (Week 3-8)
MVP Scope Decision Matrix
| Approach | When to Use | Timeline | Cost | |----------|-------------|----------|------| | Landing page + waitlist | Validating demand | 1 day | $0-50 | | Concierge MVP | Service business, complex workflow | 1 week | $0 | | Wizard of Oz | AI/automation product (human behind curtain) | 1-2 weeks | $0 | | No-code prototype | Simple CRUD app, marketplace | 2-3 weeks | $50-200/mo | | Coded MVP | Technical product, API, developer tool | 4-6 weeks | $0-500 |
Rules:
- If you can test the hypothesis WITHOUT code, do that first
- MVP must test ONE hypothesis — not "will people use this?" but "will [segment] pay $X for [specific value]?"
- Maximum 6-week build — if it takes longer, scope is too big
- Ship to 10 users, not 10,000 — intimate feedback beats vanity metrics
Launch Checklist
pre_launch:
- [ ] 20+ discovery interviews completed
- [ ] Problem validated (frequency + severity + WTP)
- [ ] MVP tests primary hypothesis
- [ ] 10+ beta users committed (by name)
- [ ] Pricing set (see pricing section)
- [ ] Analytics installed (activation event defined)
- [ ] Feedback channel open (Slack, email, Intercom)
launch_day:
- [ ] Personal message to every beta user
- [ ] Monitor activation within first 24h
- [ ] Respond to every piece of feedback < 1h
- [ ] Track: signups, activations, WTP confirmations
post_launch_week_1:
- [ ] Call every activated user — what worked?
- [ ] Call every churned user — what failed?
- [ ] Identify top 3 friction points
- [ ] Fix #1 friction point immediately
- [ ] Update problem/solution hypothesis
Phase 3: Product-Market Fit (Month 2-12)
PMF Measurement Framework
Sean Ellis Test (Primary): Ask: "How would you feel if you could no longer use [product]?"
- Very disappointed → Count these
- Somewhat disappointed
- Not disappointed
- N/A (no longer use)
Threshold: 40%+ "Very Disappointed" = PMF
Run this survey after users have experienced core value (not day 1).
Supporting Metrics:
| Metric | Pre-PMF | PMF | Strong PMF | |--------|---------|-----|------------| | Sean Ellis "very disappointed" | <25% | 40%+ | 60%+ | | Week 1 retention | <20% | 40%+ | 60%+ | | Month 3 retention | <5% | 20%+ | 40%+ | | NPS | <0 | 30+ | 50+ | | Organic/referral % of signups | <10% | 25%+ | 50%+ | | Revenue churn (monthly) | >5% | <3% | <1% |
Pre-PMF Operating Rules:
- Talk to users every single day
- Ship updates weekly minimum
- Don't hire non-essential roles
- Don't spend on paid marketing
- Don't optimize onboarding (fix the product first)
- Measure learning velocity, not revenue
PMF Search Process
Week 1-2: Ship feature/change
Week 2-3: Measure impact (retention, NPS, Ellis test)
Week 3-4: Interview users about change
Week 4: Decide → double down or try something else
Repeat until 40%+ "very disappointed"
Pivot Decision Framework
pivot_assessment:
current_retention_trend: "improving | flat | declining"
months_of_runway: 0
customer_segments_tested: 0
pivots_remaining: "runway_months / 3" # each pivot needs ~3 months
pivot_types:
zoom_in: "One feature IS the product — kill the rest"
zoom_out: "Product is one feature of something bigger"
customer_segment: "Same product, different buyer"
customer_need: "Same customer, different problem"
channel: "Same product, different distribution"
pricing: "Same product, different business model"
technology: "Same problem, different solution"
decision_rules:
- "If retention is improving (even slowly) → stay the course"
- "If flat for 3+ months after real iteration → pivot"
- "If < 6 months runway → pivot NOW or raise bridge"
- "If you've tested 3+ segments with same product → pivot product"
- "If users love it but won't pay → pricing/segment pivot"
Phase 4: Unit Economics & Pricing
Startup Pricing Framework
Step 1: Value-based price anchor
Annual value delivered to customer: $________
Price = 10-20% of value delivered
Example: Save customer $50K/year → price at $5K-10K/year
Step 2: Pricing model selection
| Model | Best For | Expansion Built-in? | |-------|----------|---------------------| | Flat monthly | Simple product, SMB | No — need tier upgrades | | Per-seat | Collaboration tools | Yes — grows with team | | Usage-based | API, infrastructure | Yes — grows with usage | | Tiered | Multiple segments | Moderate — tier upgrades | | Revenue share | Marketplace, fintech | Yes — grows with success |
Step 3: Three-tier architecture
pricing_tiers:
starter:
price: "$X/mo" # anchor low, capture market
features: "core value only"
target: "individual / small team"
purpose: "land"
professional:
price: "$3-4X/mo" # this is where margin lives
features: "core + collaboration + integrations"
target: "growing team"
purpose: "expand (should be 60-70% of revenue)"
highlight: true # "Most Popular" badge
enterprise:
price: "Custom ($10X+)"
features: "everything + SSO + SLA + dedicated support"
target: "large org"
purpose: "signal legitimacy + capture whales"
Pricing Rules:
- Price HIGHER than you think — you can always discount, can't easily raise
- Annual discount = 2 months free (16% off) — not more
- Never compete on price — compete on value, speed, or experience
- Grandfather early users — loyalty matters
- Review pricing quarterly — most startups underprice for too long
Unit Economics Health Check
unit_economics:
CAC: "$___" # total sales+marketing spend / new customers
LTV: "$___" # avg revenue per customer × avg lifespan in months
LTV_CAC_ratio: "___" # target: 3:1+
CAC_payback_months: "___" # target: <12
gross_margin: "___%" # target: >70% for SaaS
burn_multiple: "___" # net burn / net new ARR — target: <2
magic_number: "___" # net new ARR / S&M spend last quarter — target: >0.75
health_assessment:
- "LTV:CAC > 3:1 → healthy, can invest in growth"
- "LTV:CAC 1-3:1 → cautious, optimize before scaling"
- "LTV:CAC < 1:1 → STOP — losing money on every customer"
- "Payback > 18mo → cash flow problem, even if profitable long-term"
- "Burn multiple > 3 → spending too much for growth achieved"
Phase 5: Fundraising
Fundraising Readiness Checklist
raise_when:
- [ ] You have momentum (growing MoM, not flatlined)
- [ ] You know what the money is for (specific milestones, not "general")
- [ ] You have 6+ months runway (raising from strength, not desperation)
- [ ] Your story is crisp (problem → solution → traction → vision in 60 seconds)
do_not_raise_when:
- "Pre-PMF with no traction (unless deep tech / biotech)"
- "To avoid hard decisions about business model"
- "Because competitors raised"
- "When you have < 3 months runway (terms will be terrible)"
Fundraising Math
round_benchmarks:
pre_seed:
raise: "$250K-$1M"
valuation: "$3-6M"
dilution: "10-20%"
what_you_need: "idea + team + early signal"
timeline: "2-4 weeks"
seed:
raise: "$1-4M"
valuation: "$8-15M"
dilution: "15-25%"
what_you_need: "$10-50K MRR or strong engagement metrics"
timeline: "4-8 weeks"
series_a:
raise: "$5-15M"
valuation: "$30-80M"
dilution: "15-25%"
what_you_need: "$1-3M ARR, 3x+ YoY growth, clear PMF"
timeline: "8-16 weeks"
instruments:
SAFE:
pros: "fast, simple, no board seat, no maturity date"
cons: "uncapped = bad for founder, stacking SAFEs = dilution surprise"
use_when: "pre-seed, angel rounds, speed matters"
convertible_note:
pros: "familiar to angels, interest accrues"
cons: "maturity date pressure, more legal work"
use_when: "bridge rounds, angel-heavy rounds"
priced_round:
pros: "clean cap table, board governance, signals maturity"
cons: "expensive legal ($15-30K), takes longer"
use_when: "seed+ with institutional VCs"
Pitch Deck Structure (10-12 slides max)
deck_structure:
1_title: "Company name, one-line description, your name"
2_problem: "Specific pain point with data — make them FEEL it"
3_solution: "How you solve it — demo screenshot or 3-step process"
4_demo: "Show, don't tell — screenshot or video link"
5_market: "TAM/SAM/SOM with bottom-up logic, not top-down fantasy"
6_business_model: "How you make money, current pricing, unit economics"
7_traction: "The slide that matters most — chart goes up and to the right"
8_team: "Why THIS team wins — relevant experience, not impressive titles"
9_competition: "Honest positioning — category c
Truncated for display — read the full file on GitHub.
Related Skills
taste-skill
116.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
72.1kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
47.3kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
lobehub
85.6k🤯 LobeHub - Super-Agents on Your Team. Add super-agents to the chats your team already uses.They take on work by themselves and get better every week.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
