Agent skill

Prototype

by nicknisi in nicknisi/claude-plugins

Build a throwaway prototype to answer a design question before committing to real implementation.

MITAuto-check passedDevelopment

Install Prototype

skills CLI
$ npx skills add nicknisi/claude-plugins --skill prototype -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nicknisi/claude-plugins prototype --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nicknisi/claude-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/essentials/skills/prototype .claude/skills/prototype && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
prototype
GitHub stars
114
Token cost
~1.2k tokens
SKILL.md length
601 words
Files
4 (incl. scripts)
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Build a throwaway prototype to answer a design question before committing to real implementation.

  • Works in 6 steps: Throwaway from day one, and clearly… → One command to run. Whatever the… → No persistence by default. State lives… → …
  • The user wants to prototype
  • SKILL.md covers Pick a branch, Scaffolder, Rules that apply to both and When done
  • Runs TypeScript scripts from its folder; calls npx, pnpm and python

What it does

Prototype is an agent skill from nicknisi/claude-plugins. Build a throwaway prototype to answer a design question before committing to real implementation. Generates either a runnable terminal app (for state machines, data models, business logic) or several radically different UI variations on one route (for visual/layout decisions). Use when the user wants to prototype, spike, POC, sanity-check a data model, mock up a UI, explore design options, or says "prototype this", "spike this out", "let me play with it", "try a few designs", "sketch this in code", "I want to try…

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `LOGIC.md`, `UI.md` and `scripts/scaffold.ts`).

It sits in Development, covering Prototyping. The repository describes itself as: Nick's own marketplace of Claude Plugins. The licence is MIT.

When your agent uses it

  • The user wants to prototype
  • Sanity-check a data model
  • Explore design options
  • Says prototype this

Example prompts

  • “prototype this”
  • “spike this out”
  • “let me play with it”
  • “/prototype”

Requirements

  • Python 3
  • Node.js

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  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…
  2. One command to run. Whatever the project's existing task runner supports — pnpm , python , bun , etc. The user must be able 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…
  4. Skip the polish. No error handling beyond what makes the prototype runnable, no abstractions. Don't build a test suite — if a single…
  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…
  6. Delete or absorb when done. When the prototype has answered its question, either delete it or fold the validated decision into the real…

What it can do on your machine

Read from SKILL.md and the folder at commit 6a6decd. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (TypeScript), which the agent can run.

    Shell commands in SKILL.md call:

    • npx
    • pnpm
    • python
    • bun

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx and pnpm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Prototype loads about 1.2k tokens when it runs. Until then it costs about 168 tokens; SKILL.md has 601 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~168
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from nicknisi/claude-plugins at commit 6a6decd, republished under its MIT licence (© nicknisi). 601 words, ~1,224 tokens.

Download SKILL.mdSave it as .claude/skills/prototype/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
prototype
description
Build a throwaway prototype to answer a design question before committing to real implementation. Generates either a runnable terminal app (for state machines, data models, business logic) or several radically different UI variations on one route (for visual/layout decisions). Use when the user wants to prototype, spike, POC, sanity-check a data model, mock up a UI, explore design options, or says "prototype this", "spike this out", "let me play with it", "try a few designs", "sketch this in code", "I want to try something before building it for real", "quick and dirty version", or "validate this approach" — even if they don't use the word "prototype."
argument-hint
What question should the prototype answer?

Prototype

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

If the user passed arguments, treat them as the question the prototype should answer.

Pick a branch

Identify which question is being answered — from the user's prompt, the arguments, the surrounding code, or by asking if the user is around. The litmus test: if the user could answer the question by looking at a screen, it's UI. If they'd need to push buttons and watch state change, it's logic.

  • "Does this logic / state model feel right?" → LOGIC.md. Build a tiny interactive 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.

Scaffolder

Before writing boilerplate, run the bundled scaffolder to generate the repetitive parts (switcher component, TUI shell, variant stubs). Then fill in the interesting parts — the actual variants or the domain logic.

bash
# UI prototype: generates PrototypeSwitcher + variant shells
npx tsx ${CLAUDE_PLUGIN_ROOT}/skills/prototype/scripts/scaffold.ts ui --variants 3 --framework next --outdir ./src/app/settings

# Logic prototype: generates portable logic module + TUI shell
npx tsx ${CLAUDE_PLUGIN_ROOT}/skills/prototype/scripts/scaffold.ts tui --name checkout-flow --outdir ./src/checkout

The scaffolder handles React UI (Next, React Router, Vite) and TypeScript TUI. For other UI frameworks, it creates the directory structure with React components — adapt them to your framework.

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. Use a naming convention that makes it impossible to confuse with production code — prefix files or folders with __prototype- or put them in a prototype/ subfolder next to the target module. 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 — 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 — wipe me" name.
  4. Skip the polish. No error handling beyond what makes the prototype runnable, no abstractions. Don't build a test suite — if a single assertion would save you from a dumb mistake while iterating, that's fine, but if you're writing more than one you've left prototype territory. The point is to learn something fast and then delete it.
  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. Delete or absorb when done. When the prototype has answered its question, either delete it or fold the validated decision into the real code — don't leave it rotting in the repo.
Show full SKILL.md (68 more words)Show less

When done

The answer is the only thing worth keeping from a prototype. Capture it somewhere durable (commit message, ADR, issue, or a NOTES.md next to the prototype) along with the question it was answering. If the user is around, that capture is a quick conversation; if not, leave the placeholder so they (or you, on the next pass) can fill in the verdict before deleting the prototype.

© nicknisi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in plugins/essentials/skills/prototype of nicknisi/claude-plugins.

  • SKILL.md
  • LOGIC.md
  • UI.md
  • scripts/scaffold.ts

Open the folder on GitHubat commit 6a6decd

Compare with similar skills

Prototype next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Prototype compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prototype this skillnicknisi/claude-plugins114—~1.2kAutomated safety check: PassMIT
Native Feel Cross Platform Desktopyetone/native-feel-skill1.9k1 repos~1.5kAutomated safety check: PassMIT
Compound Engineering PrototypeEveryInc/compound-engineering-plugin25k—~1.9kAutomated safety check: PassMIT
Collaborating With CodexGuDaStudio/collaborating-with-codex1321 repos~712Automated safety check: PassMIT
Digikeyaklofas/kicad-happy1.4k1 repos~4.5kAutomated safety check: PassMIT
Collaborating With Antigravityappautomaton/agent-designer1311 repos~2.4kAutomated safety check: PassNone

Similar skills

  • Native Feel Cross Platform Desktop

    yetone/native-feel-skill

    A skill your agent uses when the user is designing, prototyping, or rewriting a desktop app that must run on multiple OSes (macOS + Windows, optionally Linux) AND feel indistinguishable from a…

    1.9k GitHub starsUsed in 1 repo~1.5k tokens
    DevelopmentAuto-check passed
  • Compound Engineering Prototype

    EveryInc/compound-engineering-plugin

    Builds a throwaway prototype at just the fidelity needed to settle a specific how-it-should-work-or-feel question, before committing to an approach other work will treat as fixed.

    25k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Collaborating With Codex

    GuDaStudio/collaborating-with-codex

    Delegates coding tasks to Codex CLI for prototyping, debugging, and code review.

    132 GitHub starsUsed in 1 repo~712 tokens
    DevelopmentAuto-check passed
  • Digikey

    aklofas/kicad-happy

    Search DigiKey for electronic components and download datasheets — primary source for prototype orders and the preferred API method for fetching datasheets.

    1.4k GitHub starsUsed in 1 repo~4.5k tokens
    DevelopmentAuto-check passed
  • Collaborating With Antigravity

    appautomaton/agent-designer

    Delegate tasks to Google's Antigravity CLI (agy) for prototyping, debugging, code review, and research.

    131 GitHub starsUsed in 1 repo~2.4k tokens
    DevelopmentAuto-check passed
  • Collaborating With Gemini

    haoyu-haoyu/Multi-AI-Workflow

    Delegates coding tasks to Gemini CLI for prototyping, debugging, and code review.

    109 GitHub stars~521 tokensUpdated 5 mo ago
    DevelopmentAuto-check passed

More from nicknisi/claude-plugins

All 12 skills in this repo
  • Blog Post Writer

    nicknisi/claude-plugins

    Turn Nick Nisi's raw material into a blog post draft in his voice.

    114 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Image Gen

    nicknisi/claude-plugins

    Generate or edit images via Google Gemini (nano-banana-pro) or OpenAI gpt-image-2.

    114 GitHub stars~502 tokensUpdated 1 mo ago
    Auto-check passed
  • Squad Review

    nicknisi/claude-plugins

    Review the current branch with six specialist lenses (security, correctness, conventions, tests, architecture, duplication), then put every finding through an adversarial verifier that tries to…

    114 GitHub stars~751 tokensUpdated 1 mo ago
    Auto-check passed
  • Tmux

    nicknisi/claude-plugins

    Read and drive other tmux panes when Claude runs inside tmux.

    114 GitHub stars~3.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Youtube Notes

    nicknisi/claude-plugins

    Pull captions from a YouTube video and turn them into chapter-aligned notes where every claim carries a clickable timestamp.

    114 GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Conference Talk Builder

    nicknisi/claude-plugins

    Create conference talk outlines and slide-by-slide content plans using narrative frameworks.

    114 GitHub stars~2.7k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Prototype

What does Prototype do?

Build a throwaway prototype to answer a design question before committing to real implementation. Prototype is an agent skill from nicknisi/claude-plugins. Build a throwaway prototype to answer a design question before committing to real implementation.

When should I use Prototype?

Prototype fits situations like: the user wants to prototype; sanity-check a data model; explore design options; says prototype this.

How do I install Prototype in Claude Code?

Run `npx skills add nicknisi/claude-plugins --skill prototype -a claude-code`. Or copy the skill folder (plugins/essentials/skills/prototype in nicknisi/claude-plugins) into .claude/skills/prototype in your project. Claude Code loads it when a task matches its description.

How do I install Prototype in Codex?

Run `npx skills add nicknisi/claude-plugins --skill prototype -a codex`. Or copy the skill folder (plugins/essentials/skills/prototype in nicknisi/claude-plugins) into .agents/skills/prototype in your project. Codex loads it when a task matches its description.

Can I use Prototype in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nicknisi/claude-plugins --skill prototype -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prototype, .gemini/skills/prototype, .github/skills/prototype and .opencode/skills/prototype in your project.

What does Prototype need to run?

Going by SKILL.md and its folder, Prototype needs TypeScript for the scripts in its folder and the command-line tools its instructions call (npx, pnpm, python and bun). Our summary lists: Python 3; Node.js.

Does Prototype access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Prototype safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Prototype use?

Prototype is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prototype use?

About 1.2k tokens (SKILL.md is roughly 4.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Prototype?

Skills that share tags, products or a category with Prototype: Native Feel Cross Platform Desktop (yetone/native-feel-skill, 1.9k stars), Compound Engineering Prototype (EveryInc/compound-engineering-plugin, 25k stars), Collaborating With Codex (GuDaStudio/collaborating-with-codex, 132 stars) and Digikey (aklofas/kicad-happy, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prototype?

nicknisi (a GitHub user) maintains it in nicknisi/claude-plugins, which has 114 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on August 11, 2026.

Source: nicknisi/claude-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.