Eleven free Claude skills that test a business before you launch it: a board trained on Hormozi, Thiel and Jobs, a marketing director, a CFO, and a consumer panel of 100 buyer agents. Free, MIT.
# Add to your Claude Code skills
git clone https://github.com/Jakeschincariol/founder-skillGuides for using ai agents skills like founder-skill.
See how founder-skill compares with popular alternatives.
founder-skill is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by Jakeschincariol. Eleven free Claude skills that test a business before you launch it: a board trained on Hormozi, Thiel and Jobs, a marketing director, a CFO, and a consumer panel of 100 buyer agents. Free, MIT. It has 66 GitHub stars.
founder-skill's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/Jakeschincariol/founder-skill" and add it to your Claude Code skills directory (see the Installation section above).
founder-skill is primarily written in Python. It is open-source under Jakeschincariol on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh founder-skill against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
Eleven Claude skills that test a business before you launch it. Free, MIT, no signup, no API key, nothing to connect.
skills/founder-board skills/founder-marketing skills/founder-cfo
skills/founder-consumer skills/founder-launch skills/founder-pricing
skills/founder-offer skills/founder-competitors skills/founder-brand
skills/founder-ops skills/founder-plan
One of them is your board of directors, trained on the frameworks of Alex Hormozi, Peter Thiel and Steve Jobs. One is your marketing director. One is your CFO and finds your real profit margins. And one is the consumer panel: it spins up 100 buyer agents trained on your target customer and runs your business through 100 buyer scenarios.
So you know how to launch, how to market and how to actually make money, before you spend thousands of dollars finding out the hard way.
Paste this repo link into Claude and say install skill:
https://github.com/Jakeschincariol/founder-skill
install skill
Or as a plugin, in Claude Code:
/plugin marketplace add Jakeschincariol/founder-skill
/plugin install founder-skill@founder-skill
Claude Code namespaces plugin skills, so installed as a plugin they show up as
/founder-skill:founder-board and so on. Copy the folders instead if you want
plain /founder-board:
git clone https://github.com/Jakeschincariol/founder-skill.git
cp -r founder-skill/skills/founder-* ~/.claude/skills/
Project-local instead of global: copy the same folders into your repo's
.claude/skills/. No Claude Code at all? Paste any single SKILL.md at the top
of a chat and it runs as a mode. You lose the sub-agents and the Python tools,
but the method works.
The tools need Python 3.8 or newer. Nothing to pip install.
| command | job | what it does |
|---|---|---|
/founder-board |
Board of Directors | Three board members, each a sub-agent applying one published framework (Offers, from $100M Offers; Monopoly, from Zero to One; Product, from Isaacson's Steve Jobs), score the idea, name what would kill it and vote. |
/founder-competitors |
Competitor Scout | Maps direct competitors, indirect ones and substitutes from public sources, with prices, positioning and what their customers complain about, every fact linked. |
/founder-consumer |
Consumer Panel | Spins up a swarm of buyer agents (100 by default) from your target customer, each with its own income, habits and objection, and tallies who buys, who doesn't and why. |
/founder-pricing |
Pricing Strategist | Turns the panel's price answers into an acceptable price range, sets it against competitors and your margin, and picks what to test. |
/founder-offer |
Offer Architect | Builds the offer stack (bonuses, guarantee, real urgency, a name) that answers the panel's objections, then re-tests it on the panel. |
/founder-cfo |
CFO | Unit economics: contribution per sale, the real profit margin, break-even per day, year 1 month by month, cash needed, payback, what-ifs. |
/founder-marketing |
Marketing Director | Positioning, the channels your buyers use, a dated 30-day launch campaign, ten hooks and the most you can pay for a customer. |
/founder-brand |
Brand Designer | Name candidates with the trademark, domain and handle checks to run, a voice, a promise and a brief for the look. |
/founder-ops |
Operations Manager | Suppliers, staffing, day-one routines, tools, the permits to check and a risk register, feeding real costs back to the CFO. |
/founder-launch |
Launch Lead | A cheap real-world test first, then a dated countdown, the launch-day run sheet and the first 30 days. |
/founder-plan |
Business Planner | Compiles everything into one business plan with a verdict computed from the numbers: Profitable, Not yet or Incomplete. |
Run them in this order. Each one reads what the others wrote, in a founder/
folder in your project.
board -> competitors -> consumer -> pricing -> offer -> cfo -> marketing -> brand -> ops -> launch -> plan
An example: a matcha café in Toronto, iced matcha lattes at $6.50 a cup. (Every input is in the example files in this repo, so you can run the tools on it.)
/founder-board writes founder/idea.md from what you told it and puts it
in front of three board members. Each scores it, lists the risks and votes:
fund, fund if, or pass. The conditions become a checklist for the rest./founder-competitors maps the matcha bars and coffee shops within walking
distance, what they charge for a latte and what their reviews complain about./founder-consumer builds the target customer (urban professionals, 24 to
38, who buy coffee most days), deals 100 buyer cards across income, habits and
objections, and runs one sub-agent per buyer. Back comes who buys, who passes,
the reasons in their words ("my coffee place is closer", "$6.50 is steep for a
drink") and what would flip a no./founder-pricing reads the panel's four price answers per buyer into a
price range and checks $6.50 against it and against the competitors./founder-offer answers the top objections with the offer (a launch-week
price, a loyalty card) and re-runs a quick panel to see if the buy rate moves./founder-cfo runs the unit economics. With the example numbers: each cup
leaves $4.76 after its own costs, break-even is 186 cups a day, the profit
margin at the planned 383 cups a day is 38%, year 1 makes $93,926 on operations
after a slow ramp, the $25,280 startup spend is earned back in month 8, and the
founder needs $34,092 in cash before it pays for itself./founder-marketing, /founder-brand, /founder-ops and
/founder-launch turn it into a 30-day campaign, a name and a look, the
suppliers and routines, and a dated launch that starts with a pop-up to test
real buyers./founder-plan compiles founder/business-plan.md. Its verdict is
computed, not written: Profitable only if every unit earns money, year 1 makes
a profit, break-even fits capacity and enough of the panel buys.You can also run any one on its own. /founder-consumer --quick on an idea you
are only thinking about is a good way to find out if you should.
Four of them, all standard-library Python. None touch the network.
python3 skills/founder-cfo/unit_economics.py founder/numbers.json --out founder/cfo.md # margins, break-even, year 1
python3 skills/founder-consumer/panel.py init --customer founder/customer.json --pitch founder/pitch.md
python3 skills/founder-pricing/van_westendorp.py founder/panel/answers --price 6.50 # the acceptable price range
python3 skills/founder-plan/compile.py --dir founder # the plan and its verdict
unit_economics.py reads one JSON (example: skills/founder-cfo/example.json)
and reports contribution, break-even, the margin at plan, year 1 by month, cash
needed, payback and three what-ifs. Every number traces to an input; a missing
field is an error, never a guess.
panel.py deals persona cards from your target customer (same seed, same
cards), writes one brief per buyer, checks the answers and tallies them. It never
answers for a buyer.
van_westendorp.py reads four price answers per buyer (from the panel, or a
CSV from a real survey) and finds the points of marginal cheapness and
expensiveness, the optimal and the indifference price.
compile.py assembles the plan and computes the verdict.
python3 -m unittest discover -s tests -v
The board applies published frameworks. It is not those people. The three lenses are short summaries, in our words, of ideas from $100M Offers by Alex Hormozi, Zero to One by Peter Thiel with Blake Masters, and Walter Isaacson's biography of Steve Jobs. The board never speaks as them, quotes them or claims they endorse anything. This project is not affiliated with any of them.
The consumer panel is simulated buyers, not customers. It is a fast, cheap way
to find objections, segments and wording before you spend. It is not a forecast:
language models lean agreeable, so read the buy rate as an upper bound, and
confirm the big calls with real people. /founder-launch starts with exactly that
test. Panel answers are research; never use them as testimonials.
The numbers are only as good as the inputs. The CFO marks every estimate as an estimate and asks for real quotes. Check costs with suppliers and the structure, payroll and tax with an accountant.
Research uses public sources, with links. No invented competitors, prices, reviews or quotes. No scraping against a site's terms.
Not financial, legal or tax advice. Permits, trademarks and claims depend on where you are. The skills tell you what to check and where; a professional confirms it.
skills/founder-board/ SKILL.md, lenses.md
skills/founder-competitors/ SKILL.md
skills/founder-consumer/ SKILL.md, panel.py, customer.example.json, pitch.example.md
skills/founder-pricing/ SKILL.md, van_westendorp.py
skills/founder-offer/ SKILL.md
skills/founder-cfo/ SKILL.md, unit_economics.py, example.json
skills/founder-marketing/ SKILL.md
skills/founder-brand/ SKILL.md
skills/founder-ops/ SKILL.md
skills/founder-launch/ SKILL.md
skills/founder-plan/ SKILL.md, compile.py
tests/ the tests for every tool
Your own files live in founder/ in your project. The skills read each other's.
Made by Jake Schincariol, opusjake.ai. Siblings: Arena, Replica, X, [LinkedIn](https://github.com/Jakeschincariol/linkedin-ag