prototype

Files (3)

• LOGIC.md
• SKILL.md
• UI.md

SKILL.md (first lines)

# Prototype

A prototype is **throwaway code that answers a question**. The question decides the format.

## Pick a Branch

Identify which question is being answered — from the user's prompt, surrounding code, or by asking if the user is available:

- **"Does this logic / state model seem right?"** → [LOGICA.md](LOGICA.md). Build an interactive terminal mini-app that pushes the state machine through cases that are hard to reason about on paper.
- **"How should this look?"** → [UI.md](UI.md). Generate multiple radically different UI variations on a single route, toggleable via a URL parameter and a floating bottom bar.

The two branches produce very different artifacts — getting this wrong wastes the entire prototype. If the question is genuinely ambiguous and the user isn't reachable, default to the branch that best matches the surrounding code (a backend module → logic; a page or component → UI) and declare the assumption at the top of the prototype.

## Rules That Apply to Both

1. **Throwaway from day one, and clearly marked as such.** Place the prototype code near where it will actually be used (alongside the module or page you're prototyping for) so context is obvious — but name it so a casual reader sees it's a prototype, not production. For throwaway UI routes, obey whatever routing convention the project already uses; don't invent a new top-level structure.
2. **One command to run.** Whatever the project's existing task runner supports — `pnpm <name>`, `python <path>`, `bun <path>`, etc. The user should be able to launch without thinking.
3. **No persistence by default.** State lives in memory. Persistence is the thing the prototype is *checking*, not something it should depend on. If the question explicitly involves a database, use a scratch DB or a local file with a clear "PROTOTYPE — delete me" name.
4. **Skip the polish.** No tests, no error handling beyond what makes the prototype *runnable*, no abstractions. The point is to learn something fast and then delete it.
5. **Expose state.** After each action (logic) or on each variant switch (UI), print or render the full relevant state so the user can see what changed.
6. **Delete or absorb when done.** Once the prototype has answered its question, either delete it or incorporate the validated decision into real code — don't leave it rotting in the repository.

## When Done

The *answer* is the only thing worth keeping from a prototype. Capture it somewhere durable (commit message, ADR, issue, or a `NOTES.md` alongside the prototype) along with the question it was answering. If the user is around, this capture is a quick conversation; if not, leave the placeholder so they (or you, on the next pass) can fill in the verdict before deleting the prototype.

From hcb2019/claude-code-skills, MIT.

More from hcb2019/claude-code-skills