Mvp scoping

Skill Dragoon0x/everything-design-taste/skills/mvp-scoping

A taste system for AI agents. 288 skills, 80 agents, 12 rules, and 8 hooks that turn generic AI output into work with genuine design quality. Anti-slop detection, typography craft, color systems, brand voice, product strategy, and 50+ specialized reviewers across UI, industry, platform, and content domains.

Install

npx -y skills add Dragoon0x/everything-design-taste --skill mvp-scoping

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Defining minimum viable products, feature scoping, launch criteria, and iterative design.

SKILL.md

1.4 KB, as published. Nobody here has run it

MVP Scoping

What MVP Actually Means

Not the worst possible version. The smallest version that proves the core hypothesis.

Scoping Framework

What's the hypothesis? 'Users will [behavior] because [reason]'
What's the minimum to test it? Strip to the core value proposition
What can be manual? Automate later, validate first (Wizard of Oz)
What can be borrowed? Use existing tools/services, don't build infrastructure
What can wait? Settings, admin, edge cases, polish

Feature Triage

CORE: Without this, the hypothesis can't be tested
  → Build it

SUPPORTING: Makes the core better but isn't essential
  → Build only if fast (<2 days)

NICE: Users might want it eventually
  → Cut it. Add after validation.

PREMATURE: Scaling, admin, optimization
  → Definitely cut it.

Launch Criteria

Core user flow works end-to-end
Critical errors handled gracefully
Performance is acceptable (not optimized, acceptable)
One complete use case is satisfying
Measurement is in place (can you tell if it's working?)

Post-MVP

Watch what users actually do (not what they said they'd do)
Measure the hypothesis metric
Iterate based on evidence, not feature requests