prototype
Use when you need to sanity-check a state model or interaction before building it, or when you need to decide what a UI should look like.
Skill by hellsan631
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.
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/hellsan631-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.
About
Use cases: design
Reviews
Write a reviewNo 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
- Use when you need to sanity-check a state model or interaction before building it, or when you need to decide what a UI should look like. Builds a throwaway prototype to answer the question.
- License
- MIT
- Instructions
- 23 lines in SKILL.md · view on GitHub
Files (4)
- LOGIC.md
- SKILL.md
- UI.md
- openai.yaml · agents/
SKILL.md (first lines)
# Prototype A prototype is **throwaway code that answers a question**. The question decides the shape. ## Pick a branch Use the user's prompt and the surrounding code to identify the question. If they do not settle it and the user is available, ask: - **"Does this logic / state model feel right?"** → [LOGIC.md](LOGIC.md). Build one shareable HTML file with free-play buttons and tabbed guided walkthroughs. It must push the state machine through cases that are hard to reason about on paper, and a non-developer must be able to drive it. - **"What should this look like?"** → [UI.md](UI.md). Generate several radically different UI variations on one route. Make them switchable through a URL search parameter and a floating bottom bar. The branches produce different artifacts, and choosing the wrong one wastes the prototype. If the question remains ambiguous and the user is unavailable, use the surrounding code: choose logic for a backend module and UI for a page or component. State the assumption at the top of the prototype. ## Rules for both branches 1. **Mark it as throwaway code from the start.** Put the prototype next to the module or page it tests so its context is visible. Name it as a prototype so a casual reader does not mistake it for production code. For throwaway UI routes, follow the project's existing routing convention. Do not add a new top-level structure. 2. **Make it one step to run.** Start a UI prototype with one command in the project's task runner, such as `pnpm <name>`, `python <path>`, or `bun <path>`. Make a logic demo a single HTML file the user can open by double-clicking. 3. **Keep state in memory by default.** Add persistence only when the prototype is checking persistence. If the question explicitly involves a database, use a scratch database or a local file with a clear "PROTOTYPE, wipe me" name. 4. **Build only enough to answer the question.** Add no tests or abstractions, and no error handling beyond what makes the prototype runnable. The point is to learn something fast. 5. **Show the state.** After every logic action and every UI variant switch, print or render the full relevant state so the user can see what changed. 6. **Capture the result.** Fold every validated decision into the real code. Preserve the prototype as a **primary source** by committing it to a throwaway branch outside main and leaving a context pointer to that branch on the implementation issue. Record the answer, including the verdict and the question it settled, in the issue or a commit. Keep only the validated decision on the main branch.
From hellsan631/skills, MIT.
More from hellsan631/skills
- 0.570score
game-visual-identity
hellsan631
Develops a recognizable visual identity for video game characters, icons, items, and related art.
SkillAFreshness: AClaude Code +9 - 0.570score
game-ui-design
hellsan631
Use when designing or redesigning game HUDs, menus, inventories, character screens, maps, progression screens, or results screens; when creating their…
SkillAFreshness: AClaude Code +9 - 0.570score
midjourney-prompting
hellsan631
Use when the user requests Midjourney prompts, reference and model setup, guided image generation, or revisions based on generated results.
SkillAFreshness: AClaude Code +9 - 0.539score
visual-identity-grilling
hellsan631
Use when the user wants to quickly iterate on game visual identity through challenging questions and rendered comparisons, or asks to combine grilling with…
SkillAFreshness: AClaude Code +9 - 0.529score
why
hellsan631
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds.
SkillBFreshness: BClaude Code +9 - 0.524score
codebase-design
hellsan631
Use when designing or improving a module's interface, when deciding where a seam goes, when code needs to be more testable or navigable, or when another skill…
SkillBFreshness: BClaude Code +9 - 0.524score
domain-modeling
hellsan631
Use when codebase terminology is in dispute, when writing or editing a CONTEXT.md, or when recording an ADR.
SkillBFreshness: BClaude Code +9 - 0.524score
principal-game-designer
hellsan631
Use when drafting a game system's design, revising one, critiquing a design document, or checking whether a spec is buildable.
SkillBFreshness: BClaude Code +9 - 0.524score
improve-codebase-architecture
hellsan631
Use when a codebase has architectural friction and the user wants refactoring options.
SkillBFreshness: BClaude Code +9 - 0.524score
wizard
hellsan631
Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or…
SkillBFreshness: BClaude Code +9 - 0.521score
principle-encode-lessons-in-structure
hellsan631
Apply when you write the same instruction a second time or notice a recurring correction.
SkillBFreshness: BClaude Code +9 - 0.521score
blast-radius
hellsan631
Use for 'blast radius of X', 'what could this break', or when reviewing a small diff you do not trust.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 29, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/hellsan631/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from hellsan631
- 0.570score
game-ui-design
hellsan631
Use when designing or redesigning game HUDs, menus, inventories, character screens, maps, progression screens, or results screens; when creating their…
SkillAFreshness: AClaude Code +9 - 0.570score
midjourney-prompting
hellsan631
Use when the user requests Midjourney prompts, reference and model setup, guided image generation, or revisions based on generated results.
SkillAFreshness: AClaude Code +9 - 0.570score
game-visual-identity
hellsan631
Develops a recognizable visual identity for video game characters, icons, items, and related art.
SkillAFreshness: AClaude Code +9 - 0.539score
visual-identity-grilling
hellsan631
Use when the user wants to quickly iterate on game visual identity through challenging questions and rendered comparisons, or asks to combine grilling with…
SkillAFreshness: AClaude Code +9 - 0.529score
why
hellsan631
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds.
SkillBFreshness: BClaude Code +9 - 0.524score
codebase-design
hellsan631
Use when designing or improving a module's interface, when deciding where a seam goes, when code needs to be more testable or navigable, or when another skill…
SkillBFreshness: BClaude Code +9
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.
Cite this page
prototype skill. Agent Mart. https://agentmart.dev/skills/hellsan631-prototype (last updated 2026-10-24)