idea-to-mvp
Skill0 starsChanged 38 days agoMITView on GitHub
Turns a rough app idea into a small first version and a one-page brief. Use when someone has an app idea, or asks 'what should I build first', 'plan my app', 'write a brief' or 'MVP'.
In this repository13 other files it gives its agents.
- access-checkSkill
- data-checkSkill
- deploy-doctorSkill
- domain-helperSkill
- first-tenSkill
- keys-checklistSkill
- make-it-yoursSkill
- payment-testSkill
- project-starterSkill
- review-loopSkill
- safe-changeSkill
- sketch-itSkill
- stack-checkSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Ask them to paste or dictate everything about the idea, messy is fine: who it's for, what those people do today instead, what would make …
- Distinctive: line 16
Ask: "What does your app need to remember?" Help them name the 2–5 core things (for example: members, videos, purchases).
- Distinctive: line 23
When they haven't decided something, help them decide now, not halfway through the build.
- Very specific: line 32
Write a one-page brief (as a document they can keep, or BRIEF.md if a project folder is open):
≈ “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
Idea to MVP
You're helping someone who doesn't code plan an app before anything gets built. Nothing gets built in this skill. The output is a brief they trust because they shaped it.
Tell them which step you're on. Ask one question at a time, with tap-to-answer options (pick one, pick several, or rank) wherever you can.
1. Brain dump
Ask them to paste or dictate everything about the idea, messy is fine: who it's for, what those people do today instead, what would make them pay. Read it all before asking anything.
2. Start from what the app remembers
Ask: "What does your app need to remember?" Help them name the 2–5 core things (for example: members, videos, purchases). Everything on screen is just a way of showing or changing these. Write each as a one-line definition with its key details.
3. Check who already solves this
Look up 3–5 existing products that do something similar (use web search if available). For each: what it does, roughly what it costs, and what it does badly that this idea could do better. Keep it short and honest. If the idea is already done well, say so and help them find their angle.
4. Interview until it's clear
Ask about the decisions that matter, one at a time. Who pays, and how (one-off or subscription)? Can visitors see anything before signing up? What's the one thing a user must be able to do? What happens after someone pays? Anything they want to avoid? When they haven't decided something, help them decide now, not halfway through the build.
5. Rank and cut
List every feature mentioned. Ask them to rank it, most important first (use a ranking question if you can). Draw a line under the smallest set someone would actually pay for. Everything below the line goes on a Later list: not deleted, later.
6. Look for holes
Before writing the brief, check the plan for gaps: anything that could let someone get the paid thing for free, a step with no way forward, data that's visible to the wrong person. Fix them in the plan now, while a fix costs one sentence.
7. Write the brief
Write a one-page brief (as a document they can keep, or BRIEF.md if a project folder is open):
# <App name>: brief
## What it is
## Who it's for
## What it remembers
## Version one (above the line)
## How it makes money
## Decisions made
## Later
## Still undecidedPlay it back and ask "Is this right?" Keep editing it with them until they're about 80–90% happy. Then tell them the brief is their plan: a list of steps they can check, not magic.
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.

