Founder skill
Eleven skills that test a business idea before launch: competitors, a panel of 100 buyers, pricing, a financial model and a 30-day plan
- 1,494 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Runs local Python scripts that read your JSON and CSV files and write reports to the project's `founder/` folder
- Searches public sources for competitors and prices if the agent has network access
- By default launches one sub-agent for each of the 100 buyers, which means many model calls
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/founder-skillDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Runs local Python scripts that read your JSON and CSV files and write reports to the project's `founder/` folder
- Searches public sources for competitors and prices if the agent has network access
- By default launches one sub-agent for each of the 100 buyers, which means many model calls
This is third-party code. Review the repository files before installing.
What it does
Founder skill is a set of eleven skills for Claude that take a business idea from a first assessment to a launch plan. It installs as a plugin with `/plugin marketplace add Jakeschincariol/founder-skill` and `/plugin install founder-skill@founder-skill`, and the skills run as `/founder-board`, `/founder-competitors`, `/founder-consumer` and so on. Each skill writes its results to a `founder/` folder inside the project and reads what the earlier ones left. The order is `board`, `competitors`, `consumer`, `pricing`, `offer`, `cfo`, `marketing`, `brand`, `ops`, `launch`, `plan`. Any skill also runs on its own. The board launches three sub-agents: each reads the idea through one published framework from a book, scores it, names the risks that would kill it and votes. The competitors skill maps direct, indirect and substitute competitors from public sources with a link for every fact. The buyer panel deals cards from your target customer description (100 by default), each with its own income, habits and objection, runs one sub-agent per card and tallies who buys, who does not and why. The pricing skill turns the panel's answers into an acceptable price range, and the offer skill builds a stack of bonuses, a guarantee and urgency and re-tests it on the panel. Four standard-library Python 3.8 or newer scripts do the calculations: `unit_economics.py` computes contribution per sale, break-even and year 1 by month, `panel.py` deals the cards and tallies the answers, `van_westendorp.py` finds the price range and `compile.py` assembles the business plan. The plan verdict `Profitable`, `Not yet` or `Incomplete` is computed from the numbers, and when a field is missing the script raises an error instead of guessing.
Who it is for. For founders and entrepreneurs who want to run a business idea through competitors, a demand model and financial calculations before putting money into a launch.
Good fit when
- You have a business idea and need buyer objections and a price spread before spending: `/founder-consumer`, then `/founder-pricing`
- You need unit economics, break-even and the startup cash from your own inputs in `founder/numbers.json`: `/founder-cfo`
- You need a dated 30-day launch plan and a cheap test on real people, such as a pop-up: `/founder-launch`
- The idea is still rough and you want a quick check: `/founder-consumer --quick` runs a lighter panel
- You need name candidates with a list of trademark, domain and handle checks that you will run yourself: `/founder-brand`
Not a fit when
- You need a sales forecast: the panel is made of simulated buyers, and the author advises reading the buy rate as an upper bound
- You need a legal, tax or financial opinion: the skills point out what to check, and a professional confirms it
- The machine has no Python 3.8 or newer: without the scripts the calculations are lost and the plan verdict is not computed
- You want the opinion of specific people: the board applies summaries of ideas from books and does not speak for their authors
Example request
Test my idea: a takeaway café with matcha lattes in the city center, 450 roubles a cup. Start with /founder-board, then competitors and the buyer panelLimitations
- The buyer panel is made of simulated agents, not customers. The author warns that language models lean agreeable, so the buy rate is an upper bound and the panel's answers must not be passed off as testimonials.
- The board applies summaries of ideas from books by Alex Hormozi and Peter Thiel and from Walter Isaacson's biography of Steve Jobs, does not quote the authors and is not affiliated with them.
- The calculations are only as good as the inputs: the skill marks estimates as estimates and asks for real supplier quotes. Taxes, payroll and company structure are confirmed by an accountant.
- The scripts need Python 3.8 or newer, do not use the network and need no packages. Without Claude Code a skill runs by pasting `SKILL.md` at the top of a chat, but sub-agents and scripts are unavailable then.
- The order matters: each stage reads the earlier stages' files in the `founder/` folder. License MIT.
How to disable. Remove the plugin with `/plugin uninstall founder-skill@founder-skill`. If you copied the folders into `~/.claude/skills/`, delete the `founder-*` directories. The files in the project's `founder/` folder stay and are deleted by hand.
FAQ
How do I test a business idea with Claude Code?
Install the plugin and run the skills in order, starting with `/founder-board`. Each one writes files to the `founder/` folder, and `/founder-plan` assembles them into a business plan with a computed verdict.
How does the panel of 100 buyers work?
`panel.py` deals cards from the target customer description, each with its own income, habits and objection. A sub-agent runs for each card, and the script checks the answers and tallies who buys, who does not and why. The script never answers for a buyer.
How does the skill compute break-even?
`unit_economics.py` reads one JSON file (an example is at `skills/founder-cfo/example.json`) and reports contribution per sale, break-even per day, the margin at plan, year 1 by month, the cash needed and payback. Every number traces to an input field, and a missing field is an error.
How do I find an acceptable price range?
`van_westendorp.py` reads four price answers per buyer, from the panel or from a CSV of a real survey, and finds the points of marginal cheapness and expensiveness, the optimal price and the indifference price. The `--price` argument compares your price with them.
Who decides that an idea is profitable?
`compile.py` computes the verdict. `Profitable` appears only if every unit earns money, year 1 makes a profit, break-even fits capacity and enough of the panel buys.
Can the skills run outside Claude Code?
You can paste any `SKILL.md` at the top of a chat and it runs as a mode. Sub-agents and the Python scripts are lost then, and only the method remains.
Discussion
No questions or reviews yet.
Related
SkillsA plugin of skills for startup validation and planning: market research, competitor analysis, positioning and pitch
Founder Skills (Emotix)
claude-skills-founder
Skills for startup founders: idea validation, a competitor matrix, pricing and a pitch deck with the result in the founder/ folder. A Claude Code plugin
Founder Playbook
founder-playbook
Fifteen business books as AI skills: retellings of frameworks, decision trees and templates for founders, from customer interviews to positioning
61 skills in ten plugins for non-technical founders: from validating an idea and building SaaS to launch, sales, pricing and bookkeeping
Ten Claude Code commands based on The Minimalist Entrepreneur: from finding a community and validating an idea to pricing, marketing and company values
A skills pack for founders and solo operators: decisions, research, second brain, content rotation, financial cadence
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Repository stars | Main difference |
|---|---|---|---|
| Founder skill (this entry) | no | 1,494 | |
| Founder Skills (Emotix) | no | 714 | per its description: idea validation, a competitor matrix, pricing and a pitch deck |
| Startup Skill | no | 1,216 | market research, competitor analysis, positioning and a pitch |
| Founder Playbook | no | 771 | fifteen business books as skills: summaries of frameworks, decision trees and templates |
README in short
The repository has eleven skill folders in `skills/`, a plugin manifest in `.claude-plugin/`, a license, unittest tests and four scripts. The documentation shows the run order on a matcha café in Toronto, with the unit economics numbers and the verdict computed on that data. A separate fine print section explains that the board rests on summaries of ideas, the panel on simulated buyers and the research on public sources with links, with no invented competitors or reviews.
README badge
Original SKILL.md
--- name: founder-board description: >- Your board of directors. Puts a business idea in front of a three-member board, each a sub-agent reading the idea through one published framework: the Offers lens (from Alex Hormozi's $100M Offers), the Monopoly lens (from Peter Thiel's Zero to One) and the Product lens (from Walter Isaacson's biography of Steve Jobs). Each member scores the idea, names the risks that would kill it and votes fund, fund with conditions, or pass. Use when the user says "test my business idea", "would this work", "pressure-test this", "what would a board say", "is this a good business", or starts the founder pack on a new idea. argument-hint: "<the business idea, or leave blank to use the conversation>" --- # founder-board The first meeting. Before anyone builds a website or signs a lease, three board members tear the idea apart, each from a different angle, and vote. What the user typed after `/founder-board`: `$ARGUMENTS`. If that is blank, take the idea from the conversation. ## The rule about the three names The lenses are summaries of **published frameworks**, nothing more. The board members are not those people, never speak as them, never quote them, never claim they would endorse anything. Write "the Offers lens", never "Alex Hormozi says". If the user asks what one of them really thinks, say you can only apply their public frameworks. ## Step 0: the idea file Everything in the founder pack reads `founder/idea.md` in the user's project. If it does not exist, write it now from the conversation: ```markdown # <business name, or a working name> - What it is: one sentence. - Who it is for: the target customer, as specific as the user can make it. - What it sells, at what price: the core product and its price. - Where and how: city or online, how customers find it, how it is delivered. - Budget and constraints: money, time, skills, anything already decided. ```