Throwaway prototype

Builds throwaway code to answer one design question: a single-file clickable HTML demo for a state model, or several structurally different UI variants on one route switched by a URL param. Use when checking whether logic holds or how a page should look.

Vibe codingPack: Matt Pocock's skills26 linesprototype
Author
Source
mattpocock/skills/skills/engineering/prototype @ abeeaf9
License
MIT · Copyright (c) 2026 Matt Pocock

About this skill

What it does

The skill builds throwaway code that answers one design question, and the question decides the shape. For "does this logic or state model feel right?" it follows LOGIC.md: one self-contained HTML file with no framework or server, opened by double-click. The logic sits in a pure module, such as a reducer or a state machine, that can later move into the real code. Around it sit a state panel redrawn after every click, a button per action and guided scenarios, such as an action that should be illegal. Labels use domain language, so a designer or PM can drive it.

For "what should this look like?" it follows UI.md: three variants by default, at most five, that differ in structure rather than colour, on one route switched by ?variant=, preferably an existing page with real data. A floating bar cycles them by arrows or ← → and is hidden in production builds.

Both kinds are marked as prototypes, start with one command, keep state in memory and skip tests and polish. Afterwards the decision goes into the real code and the prototype onto a throwaway branch outside main, linked from the issue. If the question is unclear and you are away, the agent picks by the surrounding code (a backend module means logic, a page means UI) and says so. agents/openai.yaml holds the Codex display name and description.

When to use it, and when not

Use it before committing to a design: to push a state model through tricky cases or to compare layouts in the browser.

It is not a shortcut to production code: only the pure logic module is meant to survive, and a winning UI variant is rewritten properly when folded in.

How to run it

The install command below puts the whole folder in place. The agent picks the skill up by its description when you want to try a design out; to call it yourself:

  • Claude Code: /prototype, or ask for the skill by name.
  • Codex: $prototype.
  • Cursor: type / in the Agent chat and pick prototype.

Example: /prototype Does our refund state machine cope with a partial refund after a chargeback? Make a clickable demo.

It calls no other skill. wayfinder uses it for prototype tickets, and to-spec and to-tickets may quote a snippet a prototype produced.

How it differs from similar skills

Prototype to production from our catalog goes the other way: it hardens a working prototype for real users instead of rewriting it. The visual companion in Brainstorming before you build shows HTML mockups in a browser tab and records your click. This skill builds the variants inside your app on its real data, and for logic gives you a working model rather than a picture.

Install

Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.

Claude Code — macOS, Linux
curl -fsSL --create-dirs -o ~/.claude/skills/prototype/SKILL.md https://anymodel.org/en/skills/matt-pocock/prototype/SKILL.md -o ~/.claude/skills/prototype/LICENSE https://anymodel.org/en/skills/matt-pocock/prototype/LICENSE -o ~/.claude/skills/prototype/LOGIC.md https://anymodel.org/en/skills/matt-pocock/prototype/LOGIC.md -o ~/.claude/skills/prototype/UI.md https://anymodel.org/en/skills/matt-pocock/prototype/UI.md -o ~/.claude/skills/prototype/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/prototype/agents/openai.yaml
Codex, Cursor — macOS, Linux
curl -fsSL --create-dirs -o ~/.agents/skills/prototype/SKILL.md https://anymodel.org/en/skills/matt-pocock/prototype/SKILL.md -o ~/.agents/skills/prototype/LICENSE https://anymodel.org/en/skills/matt-pocock/prototype/LICENSE -o ~/.agents/skills/prototype/LOGIC.md https://anymodel.org/en/skills/matt-pocock/prototype/LOGIC.md -o ~/.agents/skills/prototype/UI.md https://anymodel.org/en/skills/matt-pocock/prototype/UI.md -o ~/.agents/skills/prototype/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/prototype/agents/openai.yaml
Claude Code — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE','LOGIC.md','UI.md','agents/openai.yaml') { $p = Join-Path "$HOME\.claude\skills\prototype" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/prototype/$f" -UseBasicParsing -OutFile $p }
Codex, Cursor — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE','LOGIC.md','UI.md','agents/openai.yaml') { $p = Join-Path "$HOME\.agents\skills\prototype" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/prototype/$f" -UseBasicParsing -OutFile $p }

Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/matt-pocock/prototype/SKILL.md

SKILL.md

Raw

Prototype

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

Pick a branch

Identify which question is being answered, using 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 single shareable HTML file (free-play buttons plus tabbed guided walkthroughs) that pushes the state machine through cases that are hard to reason about on paper, and that a non-developer can drive.
  • "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, so 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.

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.
  2. Trivial to run. A UI prototype starts from one command in the project's task runner: pnpm <name>, python <path>, bun <path>, etc. A logic demo is a single HTML file the user double-clicks. Either way, no thinking required to start it.
  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.
  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 (the verdict and the question it settled) in the issue or a commit. The main branch keeps only the validated decision.

Connect through AnyModel API

This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.

More from the pack Matt Pocock's skills

Code review against standards and spec

Reviews the diff since a commit, branch or tag on two axes in parallel subagents: the repo's written standards plus a baseline of Fowler code smells, and the originating spec or issue. Use when a branch or PR needs checking against its spec.

Deep module design

Fixes a shared vocabulary for deep modules (interface, seam, adapter, depth, leverage), with the deletion test, dependency categories and a design-it-twice pattern on parallel subagents. Use when designing a module's interface or deciding where a seam goes.

Diagnosing hard bugs

Diagnoses hard bugs and slowdowns by first building a fast, deterministic command that reproduces the exact symptom, then minimising it, ranking falsifiable hypotheses and adding a regression test at a real seam. Use when something fails, throws or got slow.

Domain modeling

Sharpens a project's domain language during design: challenges fuzzy or conflicting terms, writes resolved ones to GLOSSARY.md at once and offers a short ADR only for hard-to-reverse trade-offs. Use when discussing terminology or recording an ADR.

Implement a spec

Implements a spec and its tickets on one integration branch: a fresh implementer subagent per ticket in its own worktree, run in parallel along the blocking graph, then a code review and one fix pass. Use when the tickets from to-tickets are ready.

Improve codebase architecture

Finds shallow modules worth deepening, starting from the code that changes most, shows the candidates in an HTML report with before/after diagrams and grills the chosen one with you. Use when a codebase has grown hard to test or navigate.

Coding session retrospective

Reviews a finished coding session from its logs and proposes changes to the agent's environment: navigation pointers, lint rules, pre-commit and CI checks, reviewer standards, tool use. Use when an agent session went slowly or made avoidable mistakes.

TDD with integration tests

Drives test-first work through public interfaces: agrees the seams to test with the user, runs one red-green cycle per test, mocks only at system boundaries and leaves refactoring to review. Use when building a feature or fixing a bug test-first.

Conversation to spec

Turns the current conversation and codebase into a spec with user stories, implementation and testing decisions, and publishes it to the issue tracker as ready-for-agent, without interviewing the user. Use when a discussed feature needs writing up.

Spec to tickets

Splits a spec, plan or conversation into tracer-bullet tickets, vertical slices that each fit one agent session, with blocking edges, and publishes them as local files or tracker issues. Use when work is too big for one session and needs a task graph.

Issue and PR triage

Triages issues and external PRs on the tracker: gives each a category and a state, checks for existing code and past rejections, reproduces bugs and writes agent briefs for ready work. Use when a maintainer works through incoming issues and PRs.

Wayfinder for huge work

Charts work too big for one agent session as a map issue with child decision tickets on the tracker, then resolves one ticket per session until the route to the goal is clear. Use when a large effort has open questions that block a spec or plan.

Bash wizard for manual steps

Generates an interactive bash script that walks a person through manual steps such as dashboard setup, API keys and CI secrets, opening each URL and saving values to .env and GitHub secrets. Use when setup or a migration needs steps only a human can take.

Git guardrails for Claude Code

Installs a Claude Code PreToolUse hook that stops the usual forms of git push, reset --hard, clean -f, branch -D and checkout or restore of the whole tree, for one project or all, then tests it. Use when you want a safety net against an agent pushing or discarding work on its own.

Migrate tests to shoehorn

Replaces as and as unknown as casts in TypeScript tests with fromPartial and fromAny from @total-typescript/shoehorn, adds the imports and runs the type check. Use when tests fake whole objects or cast partial test data to satisfy the compiler.

Pre-commit hooks setup

Sets up Husky and lint-staged in a Node repo so each commit runs Prettier on staged files, then the typecheck and test scripts, matched to the lockfile, and makes the first commit through the hook. Use when a repo has no commit-time checks.

Grilling a plan

Questions the user about a plan or decision in rounds of numbered questions with recommended answers, looks facts up itself through subagents and stops only when no decision is left assumed. Use when a plan needs stress-testing before work starts.

Teach me a topic

Runs a multi-session course in the current folder: a mission, trusted sources, short HTML lessons with quizzes, reference sheets and learning records that set the next lesson. Use when the user wants to learn a topic over time, not get one answer.

Decision questionnaire

Writes a Markdown questionnaire for someone who holds knowledge the user lacks, after asking only who it goes to and what answers are needed, with the most important questions first. Use when a decision depends on facts from another person.

Writing for agents

Gives the rules for writing text agents read: skill descriptions as context pointers, what to keep inline and what to move to a separate file, completion criteria, leading words and pruning. Use when creating or editing a skill, AGENTS.md or CLAUDE.md.