Skip to content
Agentmart
Submit a tool

prototype

做一個用完即丟的原型來回答一個設計問題 — 狀態與邏輯用可執行的程式,UI 則做幾個可切換的變體。當一個設計問題在紙上定不下來時使用,也對應 "prototype"、"spike"、「先做個雛形看看」等說法。

Skill by Luca0x5755

IndexedMIT★ 3
Write a review

Chalk Labs

Need help deploying prototype?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/luca0x5755-prototype

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

做一個用完即丟的原型來回答一個設計問題 — 狀態與邏輯用可執行的程式,UI 則做幾個可切換的變體。當一個設計問題在紙上定不下來時使用,也對應 "prototype"、"spike"、「先做個雛形看看」等說法。

Use cases: design

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/prototype

What's inside

Skill name
prototype
Description
做一個用完即丟的原型來回答一個設計問題 — 狀態與邏輯用可執行的程式,UI 則做幾個可切換的變體。當一個設計問題在紙上定不下來時使用,也對應 "prototype"、"spike"、「先做個雛形看看」等說法。
License
MIT
Instructions
32 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Prototype

A small, disposable program that answers **one** design question. Throwaway from day one: keep the answer, delete the code.

## Before writing anything

State the question in one sentence, and state what answer would change the design. "Does this state machine handle a mid-flight cancellation cleanly?" is a question. "Explore the checkout flow" is not — it has no failure condition, so it never finishes.

If you cannot name what result would make you choose differently, you do not have a prototype question. Go back to `/grilling`.

## Two shapes

**State and logic** → a runnable demo with no UI chrome — deliver it as a **single HTML file the user double-clicks**; fall back to a script in the project's task runner only when the question needs the project's real runtime. Drive it with the awkward cases directly: the concurrent edit, the expired token mid-request, the empty collection. What you are looking for is whether the model *forces* you into special cases. Three `if` branches for conditions the model should have made impossible means the model is wrong.

**UI and shape** → several **radically different** variations, toggleable from one place, started by **one command** in the project's task runner. Not three shades of the same layout — genuinely different structures, so the comparison teaches something. Static data, no backend, no state persistence.

Either way, running it must take zero thought.

## Rules

- **Real constraints, fake everything else.** The awkward part of the domain must be real. Auth, persistence, error handling, styling — fake all of it.
- **No tests.** Tests pin behaviour down; this code is being deleted. Testing a prototype is the clearest sign it stopped being one.
- **No reuse.** Prototype code that graduates into production carries every shortcut with it, unlabelled. Rebuild against the answer instead.
- **Stop when the question is answered.** Not when the prototype is finished — it is never finished.

## Finish

Write down: the question, the answer, and the one or two surprises. That paragraph is the deliverable.

If this was a detour from a main-flow session, `/handoff` that paragraph back and delete the prototype.

From Luca0x5755/luca-skills, MIT.

More from Luca0x5755/luca-skills

Signals

Stars
3
Forks
1
Open issues
0
Last commit (this folder)
Aug 6, 2026 (3 months ago)
Last release
Oct 8, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Luca0x5755

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get prototype running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying prototype?

CallGet help
Cite this page

prototype skill. Agent Mart. https://agentmart.dev/skills/luca0x5755-prototype (last updated 2026-10-24)