agentleFS
shinprshinpr/nautilus/.agents/skills/prototype-guide/SKILL.md

prototype-guide

Skill7 starsChanged 3 months agoMITView on GitHub

Defines evidence-grounded prototype quality and external-generator prompt construction. Use when generating or evaluating a prototype, or exporting a prompt for Lovable, v0, or a similar tool.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use domain-realistic content and data rather than generic placeholders.

    line 26
  2. Distinctive:

    Keep the visible UI product-native.

    line 29
  3. Very specific:

    WHEN generating or evaluating a prototype artifact: read references/prototype-quality.md and apply every applicable criterion.

    line 34
  4. Very specific:

    WHEN exporting a prompt for an external generator: also read references/prototype-prompt-guide.md and the selected platform template.

    line 35
  5. Very specific:

    WHEN product-specific usability, persona, state, or accessibility decisions are needed: load design-perspective.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

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

Prototype Guide

Purpose

A prototype makes one product decision observable before delivery. Apply product evidence and design decisions that affect that observation; leave unrelated implementation choices to the generator.

Required Context

Start from:

  1. the hypothesis and its success/failure criteria;
  2. the persona and scenario when they change behavior or evaluation;
  3. the product and design sources selected by references/prototype-quality.md.

Classify a missing input as blocking only when it controls the tested flow or interpretation. Name the missing decision and the evidence that would resolve it.

Shared Prototype Contract

  • Focus on one validation decision. Combine hypotheses only when the same interaction and evidence resolve them together.
  • Make the critical flow, consequences, and relevant recovery behavior observable.
  • Use domain-realistic content and data rather than generic placeholders.
  • Apply the highest-priority available design source instead of re-inferring existing decisions.
  • Implement the states that can occur and affect the validation decision. Report each implemented trigger and any non-obvious exclusion whose absence could change evaluation.
  • Keep the visible UI product-native; carry test setup and evaluation evidence in the completion report.
  • Preserve the artifacts needed to evaluate, reproduce, or reuse the result.

Reference Routing

  • WHEN generating or evaluating a prototype artifact: read references/prototype-quality.md and apply every applicable criterion.
  • WHEN exporting a prompt for an external generator: also read references/prototype-prompt-guide.md and the selected platform template.
  • WHEN product-specific usability, persona, state, or accessibility decisions are needed: load design-perspective.

Scope Boundary

This skill owns prototype quality and prompt construction. recipe-validate owns the validation lifecycle and hypothesis record. recipe-prototype-prompt owns explicit external prompt export. The prototype generator owns the HTML artifact.

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.