mvp-spec
Skill0 starsChanged 5 months agoMITView on GitHub
Turns a raw idea into a lean MVP spec: problem, goals/non-goals, core user flow, scope cut, and a single success metric. Trigger on "scope my MVP", "what should I build first", "MVP spec", "cut this to an MVP", or "turn my idea into a build plan".
1 other project uses a version of this.
Adopted by
Most recently taken up by
- xeno-xeno/mvp-spectheir own version, first seen Oct 25, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- xeno-xeno/mvp-spec★ 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 repository9 other files it gives its agents.
- cold-outreachSkill
- competitor-analysisSkill
- fundraising-narrativeSkill
- growth-experimentsSkill
- landing-page-copySkill
- market-researchSkill
- pricing-experimentsSkill
- pricing-strategySkill
- tam-sam-somSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
When a founder has an idea (or a bloated feature list) and needs the smallest thing that proves the core value and can ship in 2-4 weeks.
- Distinctive: line 43
Avoid: scope creep disguised as "table stakes".
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
When to use
When a founder has an idea (or a bloated feature list) and needs the smallest thing that proves the core value and can ship in 2-4 weeks.
Inputs to gather
- The idea in one sentence and the ICP.
- The single riskiest assumption that must be true for this to work.
- The one user outcome that, if delivered, proves value.
- Any hard constraints (time, budget, solo vs. team, existing tools).
Process
- State the problem sharply: who, in what situation, fails to do what today.
- Pick ONE core flow — the single path from trigger to value. Everything else waits.
- Goals / non-goals: list 2-3 goals and, crucially, 3-5 explicit non-goals (the features you are not building yet). Non-goals are where MVPs are won.
- Cut scope ruthlessly with the test: "Does the user reach the core outcome without this?" If yes, defer it. Fake the rest (manual ops, no-code, Wizard-of-Oz).
- Pick one success metric with a number and a deadline (e.g. "10 users complete the core flow and 3 say they'd pay, within 3 weeks").
- Moat seed: note what proprietary data or workflow lock-in this MVP starts accruing — so v1 isn't a disposable thin wrapper.
Output
- Problem statement (1-2 sentences).
- Core user flow as numbered steps (trigger → action → value).
- Goals (2-3) and Non-goals (3-5, explicit).
- Scope cut list: in v1 vs. deferred, with the reason for each cut.
- Success metric: one number + one deadline.
- Riskiest-assumption test: the cheapest experiment that de-risks it before building.
Quality bar & pitfalls
- Good = a solo founder (or 2 people + AI) could ship it in 2-4 weeks and learn something real.
- An MVP tests the riskiest assumption, not "version 1.0 minus polish".
- Manual/concierge backends beat building automation you haven't validated.
- Avoid: scope creep disguised as "table stakes"; no success metric; building before the riskiest assumption is tested; shipping a thin wrapper with nothing proprietary started.
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.