prototype skill
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
- GitHub stars
- 29
- Files
- 4
- Last commit
- Nov 11, 2026
- License
- MIT
- Allowed tools
- —
What does the prototype skill do?
prototype builds a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
How to install the prototype skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the prototype skill in Plugin
/plugin marketplace add svyatov/supermatt /plugin install supermatt@supermatt
Install the prototype skill in Claude Code
~/.claude/skills/prototype/SKILL.md
$ npx degit svyatov/supermatt/skills/prototype ~/.claude/skills/prototypeInstall the prototype skill in Claude Code (project)
.claude/skills/prototype/SKILL.md
$ npx degit svyatov/supermatt/skills/prototype .claude/skills/prototypeInstall the prototype skill in Codex
~/.agents/skills/prototype/SKILL.md
$ npx degit svyatov/supermatt/skills/prototype ~/.agents/skills/prototypeInstall the prototype skill in Gemini CLI
~/.gemini/skills/prototype/SKILL.md
$ npx degit svyatov/supermatt/skills/prototype ~/.gemini/skills/prototypeInstall the prototype skill in Claude.ai
npx degit svyatov/supermatt/skills/prototype prototype && zip -r prototype.zip prototype # claude.ai → Customize → Skills → + → Create skill → Upload a skill → prototype.zip
SKILL.md
View on GitHubPrototype
A prototype is throwaway code that answers a question. The question decides the shape.
Pick a branch
Identify which question is being answered from the user's prompt or surrounding code. If it remains ambiguous and the user is available, ask through the host's live multiple-choice capability, following its schema, or use chat when no such capability is usable:
- "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
- 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.
- 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. - 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. For a logic demo opened directly from disk, first probe
localStoragewith a guarded write/remove under that name: file-URL support varies by browser and can throw. When unavailable, show the limitation and provide explicit JSON export/import to preserve state. An in-memory fallback cannot establish persistence. - Skip the polish. No tests, no error handling beyond what makes the prototype runnable, no abstractions. The point is to learn something fast.
- 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.
- 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
prototype/<name>branch, out of main, push it when the repository has a remote so the pointer resolves, and leave a context pointer to that branch on the issue that asked the question (an implementation issue or a decision ticket). With no issue yet, put the pointer in the handoff or the conversation, soto-speccarries it into the spec. 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.
Files in this skill
4prototype skill questions
How do I install the prototype skill in Claude Code?
Run npx degit svyatov/supermatt/skills/prototype ~/.claude/skills/prototype. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the prototype skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.