prototype
Build a throwaway prototype to answer a design question.
Skill by officialunofficial
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/officialunofficial-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
- 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.
- License
- Apache-2.0
- Instructions
- 27 lines in SKILL.md · view on GitHub
Files (3)
- LOGIC.md
- SKILL.md
- UI.md
SKILL.md (first lines)
# Prototype A prototype is **throwaway code that answers a question**. The question dictates the shape. ## Pick a branch Work out which question you're answering — read it off the user's prompt, the surrounding code, or ask if they're reachable: - **"Does this logic / state model feel right?"** → [LOGIC.md](LOGIC.md). Stand up a tiny interactive terminal app and push the state machine through the cases that are hard to hold in your head on paper. - **"What should this look like?"** → [UI.md](UI.md). Produce several sharply different UI variations on one route, toggled by a URL search param and a floating bottom bar. The two branches yield very different artifacts, and choosing wrong throws away the entire prototype. When the question is truly ambiguous and the user can't weigh in, fall back to whichever branch fits the surrounding code (a backend module → logic; a page or component → UI), and record that assumption at the top of the prototype. ## Rules for both branches 1. **Throwaway from the first line, and labelled that way.** Put the prototype code beside the module or page it's exploring, so its context is obvious — but name it so any reader can tell at a glance it's a prototype, not shipping code. For throwaway UI routes, follow the routing convention the project already uses; don't invent a fresh top-level structure. 2. **One command to run it.** Whatever the project's task runner already supports — `pnpm <name>`, `python <path>`, `bun <path>`, and so on. The user should launch it without thinking. 3. **No persistence unless the question demands it.** Keep state in memory. Persistence is usually the thing under test, not a dependency. If the question genuinely turns on a database, point at a scratch DB or a local file named something like "PROTOTYPE — wipe me". 4. **Drop the polish.** No tests, no error handling past what's needed to make it run, no abstractions. You're here to learn one thing fast and then bin it. 5. **Show the state.** After each action (logic) or on each variant switch (UI), print or render the full relevant state so the change is visible. 6. **Delete or absorb it once answered.** When the question is settled, either delete the prototype or fold the confirmed decision into the real code — never let it rot in the repo. ## When done The one thing worth keeping from a prototype is the **answer**. Record it somewhere durable — a commit message, an ADR, an issue, or a `NOTES.md` beside the prototype — paired with the question it settled. When the user is present, that capture is a short exchange; when they're not, leave the placeholder so they (or you, next pass) can fill in the verdict before deleting the prototype.
From officialunofficial/skills, Apache-2.0.
More from officialunofficial/skills
- 0.584score
to-conformance
officialunofficial
Distill a conformance suite out of a spec and the current conversation — every normative requirement turned into an implementation-independent test any…
SkillBFreshness: B★ 7Claude Code +9 - 0.584score
domain-modeling
officialunofficial
Actively build and refine a project's domain model as you design.
SkillBFreshness: B★ 7Claude Code +9 - 0.584score
codebase-design
officialunofficial
Shared vocabulary and principles for designing deep modules.
SkillBFreshness: B★ 7Claude Code +9 - 0.581score
stacked-pr-loop
officialunofficial
Recurring check-in on a stack of dependent PRs — rebase children onto updated parents, surface CI state, flag anything waiting on a human-only gate, and…
SkillBFreshness: B★ 7Claude Code +9 - 0.581score
audit-issue
officialunofficial
Audit an issue tree (issue + epic + siblings) for continued relevance — verify its claims against HEAD, then recommend keep, rescope, or close, with drafted…
SkillBFreshness: B★ 7Claude Code +9 - 0.581score
designing-loops
officialunofficial
Reference for designing agent loops — cycles of work that repeat until a stop condition is met.
SkillBFreshness: B★ 7Claude Code +9 - 0.581score
dependency-update-loop
officialunofficial
Recurring maintenance pass over automated dependency-bump PRs (Dependabot, Renovate, or similar) — rebase, relock, verify, and report what's ready to merge.
SkillBFreshness: B★ 7Claude Code +9 - 0.581score
deploy-verify-loop
officialunofficial
Post-deploy verification loop — poll a rollout until every instance is on the new version and healthy, then run one smoke check against a real user path.
SkillBFreshness: B★ 7Claude Code +9 - 0.579score
latest-docs
officialunofficial
Fetch a library or framework's current official docs and changelog on the spot, then report what changed from what training data or existing code assumes.
SkillBFreshness: B★ 7Claude Code +9 - 0.579score
best-practices
officialunofficial
Check a language, framework, or library's current idiomatic patterns against its own docs and style guides, then answer directly or review given code against…
SkillBFreshness: B★ 7Claude Code +9 - 0.564score
diagnosing-bugs
officialunofficial
Diagnosis loop for hard bugs and performance regressions.
SkillBFreshness: B★ 7Claude Code +9 - 0.559score
tdd
officialunofficial
Test-driven development.
SkillBFreshness: B★ 7Claude Code +9
Signals
- Stars
- 7
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 7, 2026 (3 months ago)
- Last release
- Aug 25, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/officialunofficial/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from officialunofficial
- 0.584score
codebase-design
officialunofficial
Shared vocabulary and principles for designing deep modules.
SkillBFreshness: B★ 7Claude Code +9 - 0.584score
to-conformance
officialunofficial
Distill a conformance suite out of a spec and the current conversation — every normative requirement turned into an implementation-independent test any…
SkillBFreshness: B★ 7Claude Code +9 - 0.584score
domain-modeling
officialunofficial
Actively build and refine a project's domain model as you design.
SkillBFreshness: B★ 7Claude Code +9 - 0.581score
designing-loops
officialunofficial
Reference for designing agent loops — cycles of work that repeat until a stop condition is met.
SkillBFreshness: B★ 7Claude Code +9 - 0.581score
deploy-verify-loop
officialunofficial
Post-deploy verification loop — poll a rollout until every instance is on the new version and healthy, then run one smoke check against a real user path.
SkillBFreshness: B★ 7Claude Code +9 - 0.581score
dependency-update-loop
officialunofficial
Recurring maintenance pass over automated dependency-bump PRs (Dependabot, Renovate, or similar) — rebase, relock, verify, and report what's ready to merge.
SkillBFreshness: B★ 7Claude 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/officialunofficial-prototype (last updated 2026-10-24)