Prototype

Source: mattpocock/skills - engineering/prototype

Prototype

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

Pick a branch

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

• "Does this logic / state model feel right?" -> LOGIC.md. Build a tiny interactive terminal app that pushes the state machine through cases that are hard to reason about on paper.
• "What should this look like?" -> UI.md. Generate several radically different UI variations on a single route, switchable via a URL search param and a floating bottom bar.

The two branches produce very different artifacts - getting this wrong wastes the whole prototype. If the question is genuinely ambiguous and the user isn't reachable, default to whichever branch better matches the surrounding code (a backend module -> logic; a page or component -> UI) and state the assumption at the top of the prototype. (review-time: branch-selection judgment from the question shape)

Rules that apply to both

1. Throwaway from day one, and clearly marked as such. Locate the prototype code close to where it will actually be used (next to the module or page it's prototyping for) so context is obvious - but name it so a casual reader can see 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. (review-time: naming/placement judgment, not pattern-checkable)
2. One command to run. Whatever the project's existing task runner supports - pnpm <name>, python <path>, bun <path>, etc. The user must be able to start it without thinking. (review-time: matches the host project's runner, varies per repo)
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, hit a scratch DB or a local file with a clear "PROTOTYPE - wipe me" name. (review-time: judging when persistence is the actual question)
4. Skip the polish. No tests, no error handling beyond what makes the prototype runnable, no abstractions. The point is to learn something fast. (review-time: prototype scope discipline)
5. Surface the state. After every action (logic) or on every variant switch (UI), print or render the full relevant state so the user can see what changed. (review-time: prototype-legibility judgment)
6. Capture it when done. Fold any validated decision into the real code, then capture the prototype itself as a primary source: commit it to a throwaway branch, out of main, and leave a context pointer to that branch on the implementation issue or the plan in .claude/state/. Capture the answer too - the verdict and the question it settled - in the issue, the plan, or a commit. The main branch keeps only the validated decision. (review-time: capture discipline; adapts to whether a tracker or a .claude/state plan is in play)