Install in seconds
Install this skill
Copy the command and run it in your terminal. You can review the source before installing.
terminal
git clone https://github.com/tt-a1i/matt-skills-with-to-goal

Works with Git. The repository opens in your current directory.

๐Ÿงช
QualityShell

Prototype

by tt-a1i

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.

14 stars3 forksAdded 2026/07/16
agent-skillsai-agentsclaude-codecodexcoding-agentsdeveloper-toolsworkflow

Documentation

README

Prototype

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

Pick a branch

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

  • "Does this logic / state model feel right?" โ†’ 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?" โ†’ 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 โ€” 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 โ†’ logic; a page or component โ†’ UI) and state the assumption at the top of the prototype.

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 โ€” 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.
  2. One command to run. Whatever the project's existing task runner supports โ€” pnpm <name>, python <path>, bun <path>, etc. The user must be able to start it 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, hit a scratch DB or a local file with a clear "PROTOTYPE โ€” wipe 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.
  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.
  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. Capture the answer too โ€” the verdict and the question it settled โ€” in the issue or a commit. The main branch keeps only the validated decision.

More from tt-a1i

Other Claude Code skills by this author in the directory.

๐Ÿงญ
2w ago

Ask Matt

A router that helps determine which skill or workflow to use for a given task. Use when you need guidance picking the right tool from a suite of AI agent skills.
AI Engineering
+17%143
๐Ÿ”
2w ago

Code Review

Reviews code changes since a fixed point along two independent axes: coding standards compliance and spec/issue fidelity. Runs both reviews in parallel sub-agents and reports findings side by side. Ideal for reviewing branches, PRs, or work-in-progress changes.
Quality
+17%143
๐Ÿงฑ
2w ago

Codebase Design

A shared vocabulary and principles for designing deep, testable modules with small interfaces and high leverage. Use when designing or improving module interfaces, deciding where to place seams, or making code more maintainable and AI-navigable.
Quality
+17%143
๐Ÿ”
2w ago

Diagnosing Bugs

Guides systematic debugging of hard bugs and performance regressions through building a tight feedback loop, reproducing, minimizing, hypothesizing, and instrumenting. Use when encountering difficult or flaky bugs.
Quality
+17%143
๐Ÿ—๏ธ
2w ago

Domain Modeling

Actively builds and sharpens a project's domain model, challenging vague terms, stress-testing concepts with edge cases, and capturing glossaries and architectural decisions (ADRs) as they crystallize.
Writing
+17%143
๐ŸŽฏ
2w ago

Goal Crafter

Craft verifiable goal prompts for AI coding agents like Claude Code, Codex, or Pi. Turns vague tasks into precise goals with checkable completion criteria, ensuring agents run unattended.
AI Engineering
+17%143