Skip to content
Agentmart
Submit a tool

prototype

Build a throwaway artifact to answer "how should it look/behave?" Use when a wayfinder ticket needs a concrete artifact to react to before a decision can be…

Skill by lynchypin

IndexedMIT
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/lynchypin-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

Build a throwaway artifact to answer "how should it look/behave?" Use when a wayfinder ticket needs a concrete artifact to react to before a decision can be made. Two modes — logic (terminal) or UI (browser).

Use cases: design, frontend

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. Checked Oct 25, 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
Build a throwaway artifact to answer "how should it look/behave?" Use when a wayfinder ticket needs a concrete artifact to react to before a decision can be made. Two modes — logic (terminal) or UI (browser).
License
MIT
Instructions
52 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Prototype

Raise the fidelity of a discussion by making a cheap, rough, concrete
artifact to react to. Prototypes are throwaway — once the decision is
captured on the wayfinder map, the prototype code is deleted.

## When to use

- A wayfinder ticket typed as `prototype`
- When "how should it look?" or "how should it behave?" is the key
  question and plain-English options aren't resolving the decision
- Especially valuable for anything touching UI or complex state machines

## Two modes

### Logic prototype

For state machines, algorithms, edge-case behavior.

- Terminal app (Node/Python script, whatever's fastest)
- Exercise the specific state transitions or edge cases under discussion
- Output should make the behavior visible: print state transitions,
  show before/after, highlight the edge case
- Keep it under 100 lines — it's a conversation piece, not a draft

### UI prototype

For visual design, layout, interaction patterns.

- Self-contained HTML file with inline styles
- Multiple variants switchable via URL params (`?variant=a`, `?variant=b`)
- Use real (or realistic) data, not lorem ipsum — decisions change when
  content is real-shaped
- Open in browser for the user to react to
- No framework, no build step — raw HTML/CSS/JS only

## Process

1. Confirm which mode fits (ask if unclear)
2. Build the minimal artifact
3. Present it to the user
4. Capture the decision on the wayfinder map
5. Delete the prototype code

## What this skill must never do

- Never let a prototype survive past the decision it was built to inform
- Never build a prototype as a "head start" on implementation
- Never spend more than 15 minutes on a prototype — if it's taking
  longer, the question needs more grilling first

From lynchypin/project-onboard, MIT.

More from lynchypin/project-onboard

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 5, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from lynchypin

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/lynchypin-prototype (last updated 2026-10-24)