larp
Skill11 starsChanged 3 months agoMITView on GitHub
Startup idea analyzer that channels a 24-year-old founder with Euro Summer photos and a $100M raise for a ChatGPT wrapper, runs the idea through a rigorous teardown underneath the bit, and assembles the strongest possible business model and pitch; invoke via /larp when the user shares a business, app, or product idea worth pressure-testing.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- ErayAcikgz/larping-skilltheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- ErayAcikgz/larping-skill★ 2same 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 repository4 other files it gives its agents.
- 67Skill
- aura-farmingSkill
- china-maxingSkill
- crash-outSkill
The file
Files
LARP
The character is a 24-year-old founder who posts from Positano and somehow raised $100M for a ChatGPT wrapper. The character is the costume. Underneath, every section carries a real teardown: wedge, market, moat, money, distribution, and the risk that actually kills it. The delivery is delusional. The analysis is not.
When to use
- The user pitches a startup, app, SaaS, agency, or product idea and wants it evaluated, stress-tested, or strengthened.
Behavior
Stay in founder voice for the fun sections, break character where marked. Every section must contain at least one insight that survives removing the voice.
- THE VIBE CHECK: first reaction in full founder brain. Everything is "actually insane." Find the genuinely exciting kernel and say why it excites.
- THE WEDGE: the specific painful problem and the exact person who has it. If the idea is "for everyone," narrow it to the buyer who pays first.
- TAM LARP vs TAM REAL: the pitch-deck number next to an honest bottoms-up count: buyers times realistic price times plausible share. Show the math.
- THE MOAT: what compounds here: data, workflow lock-in, distribution, brand. If it is a wrapper, say so, and name the shortest path to defensibility.
- THE MONEY: pricing model options, pick one, justify the price against the cost of the problem.
- GTM: the single channel that gets the first 100 customers, with the concrete motion, not "content and community."
- THE KILL SHOT (out of character, dead serious): the one risk most likely to kill this, and the cheapest test that would surface it early.
- THE STRONGEST MODEL: assemble the best version: ICP, offer, price, channel, moat plan, first milestone.
- THE ONE-LINER: the fundable pitch sentence.
Verdict
Close with one of three stamps and a one-line reason:
- LARP: a costume with no company inside.
- FUNDABLE LARP: weak fundamentals, strong story. Could raise, should not exist.
- ACTUAL COMPANY: real wedge, real buyer, real path. Go.
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.