New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Prototype

by tobihagemann in tobihagemann/turbo

Build a self-contained local prototype at .turbo/prototypes/<slug.html, drive it, and hand it to the user to settle unknowns that prose cannot answer.

MITAuto-check passedDevelopment

Install Prototype

skills CLI
$ npx skills add tobihagemann/turbo --skill prototype -a claude-code

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

GitHub CLI
$ gh skill install tobihagemann/turbo 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/tobihagemann/turbo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/codex/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
407
Token cost
~1.3k tokens
SKILL.md length
818 words
Files
1
Skills in repo
81
Repo updated
First seen
Licence
MIT

At a glance

Build a self-contained local prototype at .turbo/prototypes/<slug.html, drive it, and hand it to the user to settle unknowns that prose cannot answer.

  • Works in 7 steps: Name What the Prototype Must Settle → Resolve the Prototype Path → Build It → …
  • The user asks to prototype this
  • SKILL.md covers Step 1: Name What the…, Step 2: Resolve the Prototype…, Step 3: Build It and Step 4: Operate It, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Prototype is an agent skill from tobihagemann/turbo. Build a self-contained local prototype at .turbo/prototypes/<slug.html, drive it, and hand it to the user to settle unknowns that prose cannot answer. Use when the user asks to "prototype this", "build a prototype", "mock this up", "show me what it would look like", "let me try the interaction first", or when a decision waits on seeing a surface or using it firsthand.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Prototyping. The repository describes itself as: Reusable workflows for planning, building, reviewing, and shipping with Claude Code and Codex. The licence is MIT.

When your agent uses it

  • The user asks to prototype this
  • Build a prototype
  • Show me what it would look like
  • Let me try the interaction first

Example prompts

  • “prototype this”
  • “build a prototype”
  • “mock this up”
  • “/prototype”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Name What the Prototype Must Settle
  2. Resolve the Prototype Path
  3. Build It
  4. Operate It
  5. Hand It Over
  6. Act on the User's Reply
  7. Record What It Settled

What it can do on your machine

Read from SKILL.md and the folder at commit 4b9f4cf. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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 1.3k tokens when it runs. Until then it costs about 95 tokens; SKILL.md has 818 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~95
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from tobihagemann/turbo at commit 4b9f4cf, republished under its MIT licence (© tobihagemann). 818 words, ~1,336 tokens.

Download SKILL.mdSave it as .claude/skills/prototype/SKILL.md (or your agent's skills folder).
name
prototype
description
Build a self-contained local prototype at .turbo/prototypes/<slug>.html, drive it, and hand it to the user to settle unknowns that prose cannot answer. Use when the user asks to "prototype this", "build a prototype", "mock this up", "show me what it would look like", "let me try the interaction first", or when a decision waits on seeing a surface or using it firsthand.

Prototype

Build a throwaway prototype that answers named unknowns, operate it, and hand it to the user for judgment.

Step 1: Name What the Prototype Must Settle

Take the open unknowns from what was passed in. When nothing was passed in, derive them from the current work: the questions whose answers in prose would still leave the user guessing, such as what a surface looks like or whether an interaction pattern makes sense in the hand.

State each unknown as a question the user answers by using the prototype rather than by reading a description. When the work that prompted the prototype already named competing alternatives, state the unknown as a comparison between them. Output that list as text before building, and keep anything outside it out of the prototype.

Step 2: Resolve the Prototype Path

Reuse the slug of the plan that governs the work when there is one. Honor an explicit slug or output path the user passed in. Otherwise generate a slug from the task title:

  • Lowercase
  • Replace non-alphanumeric characters with hyphens
  • Collapse consecutive hyphens
  • Trim leading and trailing hyphens
  • Truncate to 40 characters at a word boundary

Write to .turbo/prototypes/<slug>.html, creating the directory when it does not exist. State the resolved path before writing. Later rounds of the same prototype rewrite that same file. When the path holds a prototype of a different subject, append -2, -3, and so on until the path is free.

Step 3: Build It

Write one self-contained .html file at the resolved path, with markup, styles, script, and sample data inline. It runs from file:// with no build step, no package install, and no dependency on the real application. Start the styles with [hidden] { display: none !important; }: an element whose own CSS sets any display value otherwise ignores the hidden attribute and paints anyway.

Build only what the Step 1 questions require. Hardcode the data behind them, stub anything that would cross a network boundary, and leave persistence out.

When a Step 1 question compares alternatives, build every alternative into the same file behind a header toggle, kept visually separate from the design as prototype chrome, so the user compares them in place rather than across descriptions. Label each position of the toggle by what the user will see or feel differ. When the user could not see or feel two alternatives differ, build one of them, leave the other out of the prototype, and say so when handing it over. Keep that chrome in normal document flow rather than position: sticky or fixed, where it covers the controls scrolled beneath it.

Show full SKILL.md (387 more words)Show less

Step 4: Operate It

Open the file and drive it yourself before handing it over, using the browser-use@openai-bundled plugin.

Exercise every control and flow that the Step 1 questions depend on, and confirm each one is reachable and responds. Fix whatever does not work and drive it again. A render or a screenshot leaves the controls untested, so it does not establish that the user can reach what they are being asked to judge.

When a Step 1 question turns on how an interaction feels, such as a drag, scrub, or resize, drive the gesture as one continuous sequence of many small pointer moves. After each move, record the position of every element that should stay put and the moved element's offset from the pointer. Treat any change between consecutive moves that the interaction does not call for as broken, fix it, and drive the sequence again.

Step 5: Hand It Over

Give the user the file path, the Step 1 questions the prototype answers, and what to try for each. For a gesture driven move by move in Step 4, also give the largest change between consecutive moves in the values it recorded. Close with how to reply once they have tried it: say it settled the questions, or describe what to change.

Then end the turn.

Step 6: Act on the User's Reply

A goal continuation turn that carries no reply from the user is not a verdict: end it without calling any tool and without advancing.

  • Needs changes — return to Step 3 with the changes the user describes and continue from there, so every later round is driven in Step 4 before it reaches the user.
  • Settled — continue to Step 7.

Step 7: Record What It Settled

Delete from the prototype file every approach it disproved, so that nothing which failed survives in the file as apparent implementation. Remove any comparison toggle along with the alternatives it switched between. Keep what the settled answers rest on.

Then state each Step 1 question with the answer the prototype produced, and name separately anything it disproved. Carry these answers into the work that prompted the prototype. Then call update_plan to mark this step completed and continue with the next step of the active workflow.

Rules

  • The prototype file is the only output. Application code stays untouched.

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

Files

Just SKILL.md in codex/skills/prototype of tobihagemann/turbo.

Open the folder on GitHubat commit 4b9f4cf

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 skilltobihagemann/turbo407—~1.3kAutomated 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 tobihagemann/turbo

All 81 skills in this repo

  • Consult Oracle

    tobihagemann/turbo

    Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches.

    407 GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed

  • Fetch PR Comments

    tobihagemann/turbo

    Fetch and summarize review feedback and conversation from a GitHub PR (unresolved review threads, review bodies, and PR conversation comments) without making changes.

    407 GitHub starsUsed in 1 repo~967 tokens
    Auto-check passed

  • Recall Rationale

    tobihagemann/turbo

    Recall why a past change was made by locating the Claude Code transcript that produced it.

    407 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Codex Exec

    tobihagemann/turbo

    Run autonomous task execution using the codex CLI. An agent skill from tobihagemann/turbo.

    407 GitHub starsUsed in 1 repo~2.4k tokens
    Auto-check passed

  • Resolve PR Comments

    tobihagemann/turbo

    Evaluate, fix, answer, and reply to GitHub pull request review comments and conversation comments.

    407 GitHub stars~3.8k tokensUpdated today
    Auto-check passed

  • Investigate

    tobihagemann/turbo

    Systematically investigate bugs, test failures, build errors, performance issues, or unexpected behavior by cycling through characterize-isolate-hypothesize-test steps.

    407 GitHub starsUsed in 1 repo~3.2k tokens
    Auto-check passed

Categories

Questions about Prototype

What does Prototype do?

Build a self-contained local prototype at .turbo/prototypes/<slug.html, drive it, and hand it to the user to settle unknowns that prose cannot answer. Prototype is an agent skill from tobihagemann/turbo.html, drive it, and hand it to the user to settle unknowns that prose cannot answer.

When should I use Prototype?

Prototype fits situations like: the user asks to prototype this; build a prototype; show me what it would look like; let me try the interaction first.

How do I install Prototype in Claude Code?

Run `npx skills add tobihagemann/turbo --skill prototype -a claude-code`. Or copy the skill folder (codex/skills/prototype in tobihagemann/turbo) 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 tobihagemann/turbo --skill prototype -a codex`. Or copy the skill folder (codex/skills/prototype in tobihagemann/turbo) 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 tobihagemann/turbo --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?

SKILL.md names no scripts, command-line tools or credentials: Prototype is instructions for the agent only.

Does Prototype access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. 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. Review the folder before installing.

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 1.3k tokens (SKILL.md is roughly 5.3k 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?

tobihagemann (a GitHub user) maintains it in tobihagemann/turbo, which has 407 GitHub stars. The repository holds 81 skills in this directory. The repository was last updated on October 7, 2026.

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