prototype skill
✓ VerifiedBuilds throwaway prototypes to validate business logic via terminal apps or explore UI variations through switchable web routes.
- GitHub stars
- 27,586
- Files
- 3
- Last commit
- Nov 11, 2026
- License
- MIT
- Allowed tools
- —
What does the prototype skill do?
prototype builds throwaway prototypes to validate business logic via terminal apps or explore UI variations through switchable web routes.
Summary generated from the skill's SKILL.md.
About the prototype skill
Developers who need to validate business logic or explore design options can use this skill to generate temporary, functional code. It creates two distinct types of artifacts depending on the specific question being asked. One path produces a small interactive terminal application designed to test state machines and complex data models through memory-based state management. The other path generates multiple UI variations on a single route that users can toggle using a floating bottom bar and URL search parameters.
An agent should load this skill when a user asks to prototype a feature, play with a design, or sanity-check a model. The resulting code is intentionally unpolished, lacking tests or error handling, and is meant to be deleted once the question is answered. It integrates with existing project task runners like pnpm, bun, or python to ensure the prototype runs with a single command. By focusing on surfacing the full state after every action, it provides immediate feedback for rapid decision-making.
What an agent can do with it
- 1Validate complex state machinesCreate an interactive terminal application to test if a specific business logic or state model feels correct.
- 2Explore multiple design directionsGenerate several different UI variations on a single route to compare different visual approaches.
- 3Sanity-check data modelsUse a throwaway terminal app to verify that a data model handles difficult edge cases.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
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 Claude Code
~/.claude/skills/prototype/SKILL.md
$ npx degit yikart/AiToEarn/project/aitoearn-backend/.agents/skills/prototype ~/.claude/skills/prototypeInstall the prototype skill in Claude Code (project)
.claude/skills/prototype/SKILL.md
$ npx degit yikart/AiToEarn/project/aitoearn-backend/.agents/skills/prototype .claude/skills/prototypeInstall the prototype skill in Codex
~/.agents/skills/prototype/SKILL.md
$ npx degit yikart/AiToEarn/project/aitoearn-backend/.agents/skills/prototype ~/.agents/skills/prototypeInstall the prototype skill in Gemini CLI
~/.gemini/skills/prototype/SKILL.md
$ npx degit yikart/AiToEarn/project/aitoearn-backend/.agents/skills/prototype ~/.gemini/skills/prototypeInstall the prototype skill in Claude.ai
npx degit yikart/AiToEarn/project/aitoearn-backend/.agents/skills/prototype prototype && zip -r prototype.zip prototype # claude.ai → Customize → Skills → + → Create skill → Upload a skill → prototype.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachableyikart/aitoearn/project/aitoearn-backend/.agents/skills/prototype is public and reachablegithub.com/yikart/aitoearn/tree/HEAD/project/aitoearn-backen ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-11github.com/yikart/aitoearn/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/yikart/aitoearn/blob/HEAD/project/aitoearn-backen ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/yikart/aitoearn/blob/HEAD/project/aitoearn-backen ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 31 linesgithub.com/yikart/aitoearn/blob/HEAD/project/aitoearn-backen ↗Pass
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, the surrounding code, or by asking if the user is around:
- "Does this logic / state model feel right?" → LOGIC.md. Build a tiny interactive terminal 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.
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.
- 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. - 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.
- Skip the polish. No tests, no error handling beyond what makes the prototype runnable, no abstractions. The point is to learn something fast and then delete it.
- 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.
- 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.
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.
Files in this skill
3prototype skill questions
How do I install the prototype skill in Claude Code?
Run npx degit yikart/AiToEarn/project/aitoearn-backend/.agents/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.
What are the two main types of prototypes I can build?
You can build a terminal-based app to test logic and state models, or a UI-based prototype that allows switching between different design variations.
Should prototypes include database persistence?
No, state should live in memory by default unless the specific question being answered involves a database, in which case a temporary scratch DB or local file should be used.
How should I handle the code once the prototype has answered its question?
You should either delete the prototype or integrate the validated decisions into the actual production code to prevent it from rotting in the repository.