agentleFS
UwayxtUwayxt/agent-skills/.agents/skills/mvp-scoping/SKILL.md

mvp-scoping

Skill4 starsChanged 3 months agoMITView on GitHub

Define the smallest product that tests the riskiest assumption. Use when MVP, minimum viable, what's the smallest version, cut scope, or phase 1.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

MVP Scoping

An MVP is not a half-built product. It's the smallest thing that tests your riskiest assumption. If you can't name the assumption, you can't scope the MVP.

1. Name the riskiest assumption

Identify what must be true for this product to work from the discovery brief or product strategy. That is exactly what the MVP tests.

2. List every feature

Pull the full feature list from the product strategy output or the user's brief.

3. Classify ruthlessly

Sort into three buckets: (a) Must-have: directly tests the core assumption, (b) Should-have: improves the test but not essential, (c) Out: everything else, with an explicit reason for each cut.

4. Draw the MVP boundary

The boundary is a line, not a gradient. Everything inside ships together. Everything outside waits.

5. Define the exit criterion

Specify what result from the MVP tells you to proceed, pivot, or kill.

Completion Criteria

Done when the scope strictly isolates the riskiest assumption with clear exit criteria.

Output Format

MVP Scope Document detailing the assumption being tested, an in/out feature table, and exit criteria.

Anti-patterns

  • "MVP" that includes 80% of the full product.
  • Scope creep disguised as "just one more thing".
  • MVPs that don't test anything — they're just v1.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.