agentleFS
lglucaslglucas/ai-dev-operating-system/.claude/skills/prototype-lab/SKILL.md

prototype-lab

Skill12 starsChanged 45 days agoMITView on GitHub

Build three genuinely distinct HTML/CSS/JS prototype directions — brand, color, typography, UI, UX — from BP v0.0.2 and the research, then extract the approved one into docs/product/DESIGN-DIRECTION.md. Runs at WIZARD Phase 3, BEFORE the Product Brief and Technical Plan. Use when the user says "quero ver como vai ficar", "me mostra umas ideias de layout", "qual vai ser a cara do produto?", "que cores a gente usa?", or runs /prototype-lab.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create three distinct HTML/CSS/JS prototype directions using the same mock data.

    line 8
  2. Very specific:

    All prototypes must reflect BP v0.0.2 (personas, positioning, MVP scope, primary flow) and the research in knowledge-base/.

    line 14
  3. Distinctive:

    Do not contaminate the production app with prototype code.

    line 24
  4. Very specific:

    After the user picks a direction, write docs/product/DESIGN-DIRECTION.md — tokens, typography scale, spacing, component inventory, screens, …

    line 28

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Prototype Lab Skill

Create three distinct HTML/CSS/JS prototype directions using the same mock data.

Runs at Phase 3 of WIZARD.md — before the Product Brief and the Technical Plan, not after.

Inputs

All prototypes must reflect BP v0.0.2 (personas, positioning, MVP scope, primary flow) and the research in knowledge-base/.

The Product Brief is NOT an input. It does not exist yet — Phase 4 derives it from the direction approved here. If you find yourself needing the Product Brief, the thing you actually need is missing from BP v0.0.2; go add it there.

Rules

  • Three directions, genuinely distinct — not three shades of one idea. Without direction the model falls back on a few default looks; none of the three should rest on them: cream or beige background, italic accent words in headlines, numbered "01 / 02 / 03" section labels, monospace labels, pill-shaped buttons. If a first draft uses one, replace it and add it to this list.
  • All three read the same file: prototype-lab/shared/mock-data.js. Not "equivalent data" — the same file. Phase 4.2 derives the Technical Plan's entities from it, so it needs one guaranteed shared source.
  • Same core flows across all three, so the comparison is about design and not content.
  • Each direction carries an explicit brand hypothesis: palette, typography, density, tone.
  • Do not contaminate the production app with prototype code.

Output

After the user picks a direction, write docs/product/DESIGN-DIRECTION.md — tokens, typography scale, spacing, component inventory, screens, the flow as actually clicked, and what was rejected. That file is what Phase 4 reads.

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.