prototype-builder
Skill9 starsChanged 48 days agoMITView on GitHub
Builds a single-file, clickable HTML prototype of the target UI following the project's design.md, for use as the visual reference in Gate 2 (UI review). Use for new features where no reference app exists, before the UI gate runs.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- calven-ai/marketing-as-codetheir own version, first seen Oct 7, 2026
- darker2016/WorkbuddySkillGroups4DSHtheir own version, first seen Aug 14, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- calven-ai/marketing-as-code★ 10same name
- darker2016/WorkbuddySkillGroups4DSH★ 6same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- adversarial-reviewSkill
- checkpoint-plannerSkill
- design-plannerSkill
- orchestratorSkill
- test-plannerSkill
- ui-reviewerSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Clickable: Every button, tab, form, and navigation element responds.
- Very specific: line 16
Faithful to design.md: Follow the project's design file exactly: spacing scale, type scale, colors, component patterns.
- Very specific: line 20
Read design.md (or the project's design tokens/components).
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Prototype Builder
You build the visual reference the UI gate compares against. When there's no existing app to migrate from, you create the spec the implementation must match.
Output
A single self-contained HTML file (inline CSS/JS, no build step, no external dependencies that require network) at .helix/prototype/<name>.html. It must be:
- Clickable. Every button, tab, form, and navigation element responds. This is a demo you can click through, not a static mockup.
- Stateful. Include the key states the UI gate will compare: empty, filled, loading, error, submitted — each reachable by interacting with the prototype or via a small state-switcher toolbar you add for review purposes.
- Faithful to design.md. Follow the project's design file exactly: spacing scale, type scale, colors, component patterns. If design.md doesn't exist, run the
design-plannerskill first — do not invent a design system.
Process
- Read
design.md(or the project's design tokens/components). - Build the prototype screen by screen, simplest states first.
- Open it and click through every interaction yourself. Fix anything dead or broken — a prototype with dead buttons teaches the UI gate nothing.
- List the states you covered at the top of the file as an HTML comment, so the UI reviewer knows what to match:
<!-- STATES: default, empty-list, form-errors, submitted, loading -->
Contract with the UI gate
The prototype is the reference. The implementation must match it in structure, spacing, alignment, and behavior for every state you declared. If the human later changes the design, the prototype is updated first and the affected checkpoints re-run their UI gate.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

