Skip to content
Back to skills

Prototype

ASecurity

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

  • 583 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 5, 2026
ai-agentsrust

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned September 5, 2026

npx -y skills add stevesolun/ctx --skill prototype --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Prototype?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Prototype
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/stevesolun-prototype-ctx/badge)](https://www.skillsdirectory.com/skills/stevesolun-prototype-ctx)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: prototype
description: Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
---

# Prototype

A prototype is disposable code that answers a specific design question. Let the
question, repository, and cheapest credible feedback loop determine its shape.

## Pick a branch

Infer the branch from the request and surrounding code:

- **Logic or state-model uncertainty** → read [LOGIC.md](LOGIC.md).
- **Visual or interaction uncertainty** → read [UI.md](UI.md).

If both are involved, prototype the riskiest uncertainty first. State a material
assumption instead of blocking when the choice can be reversed cheaply.

## Shared guidance

- Mark the artifact clearly as a prototype and follow existing project structure.
- Keep it runnable with a simple documented command or URL.
- Prefer in-memory or stubbed dependencies unless persistence or integration is
  the question being tested.
- Add only the error handling, tests, and structure needed for trustworthy
  feedback. Avoid production polish and speculative flexibility.
- Make the relevant state, alternatives, or outcomes easy to inspect.
- Stop when the evidence answers the question.

Report the answer, how to exercise the prototype, and its limitations. Do not
promote, commit, branch, publish, or preserve the artifact unless the user asks.
When preservation is useful, record the question and conclusion alongside it.

Files in this skill

  • LOGIC.md1.7 KB
  • SKILL.md1.5 KB
  • UI.md2 KB
  • agents/openai.yaml100 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.