plugins/v1tamins/skills/v1-html-it/SKILL.md
Use when creating a polished self-contained HTML page would help the user understand, compare, review, present, tune, or interact with information better than Markdown. Triggers on "make an HTML page", "HTML artifact", "nice HTML", "visual report", "interactive explainer", "one-page dashboard", "shareable page".
npx skillsauth add v1-io/v1tamins v1-html-itInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Create a self-contained HTML artifact when a visual, spatial, interactive, or easily shareable page will help the user actually inspect and use the work.
Use HTML when the output benefits from at least one of these:
Do not use HTML for:
Create one self-contained .html file and tell the user where it is.
Default location:
artifacts/html-it/<short-slug>.html
If the repo already has an artifact convention, follow it. If the page is temporary or contains private local context, use /tmp/<short-slug>.html.
The file must:
| Need | HTML Shape | | --- | --- | | Explore directions | Grid of options with labels, tradeoffs, and selection affordances | | Compare implementations | Side-by-side panels, callouts, scorecards, and risks | | Explain code | Module map, annotated snippets, execution path, glossary | | Review a PR | Annotated diff, severity tags, jump links, reviewer focus areas | | Product/design review | Component contact sheet, state matrix, design tokens, flow mockups | | Prototype interaction | Clickable flow, animation sandbox, sliders for timing/easing/values | | Research/learning | TL;DR, collapsible sections, diagrams, tabs, glossary, FAQ | | Status/reporting | Timeline, metrics, shipped/slipped/blocked sections, next actions | | Incident/postmortem | Minute-by-minute timeline, log excerpts, impact bands, follow-ups | | Custom editing | Purpose-built editor with export/copy as JSON, Markdown, prompt, or diff |
State the artifact's job in one sentence before building:
This page helps the user [compare/review/understand/tune/present/export] [subject].
If the job is vague, pick the closest artifact type from the table. Ask only when the wrong artifact type would waste substantial time.
Use the available repo, files, conversation, web pages, or command output. Keep a compact evidence list:
/tmp.Do not invent data to make the page look complete. Mark unknowns visibly.
Make the first viewport useful:
Good interactions:
Avoid interaction that is just ornamental. If the page is interactive, include a no-surprise fallback path: visible default state, clear reset, and copy/export result.
Use this skeleton unless the task calls for something more specific:
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title><!-- concise title --></title>
<style>
:root {
color-scheme: light;
--bg: #f7f7f5;
--panel: #ffffff;
--ink: #1f2933;
--muted: #64707d;
--line: #d8dde3;
--accent: #2563eb;
--good: #0f766e;
--warn: #b45309;
--bad: #b91c1c;
}
* { box-sizing: border-box; }
body {
margin: 0;
font: 15px/1.5 -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif;
color: var(--ink);
background: var(--bg);
}
main { max-width: 1180px; margin: 0 auto; padding: 32px 20px 56px; }
.panel {
background: var(--panel);
border: 1px solid var(--line);
border-radius: 8px;
padding: 18px;
}
@media print {
body { background: white; }
.no-print { display: none !important; }
.panel { break-inside: avoid; }
}
</style>
</head>
<body>
<main>
<!-- content -->
</main>
<script>
// Small, local interactions only.
</script>
</body>
</html>
Before finishing, check:
Keep the chat response short:
Created: [artifact.html](/absolute/path/to/artifact.html)
What it covers:
- ...
Validation:
- Opened locally / checked static HTML / not opened because ...
If the artifact is temporary, say so and give the /tmp path.
tools
Use when planning or synthesizing user tests for prototypes, mockups, clickable demos, product concepts, design flows, landing pages, or early product specs. Triggers on "test this prototype", "prototype testing", "user test plan", "validate this product idea", "test with users".
data-ai
Use when turning a textbook, PDF, blog post, article, paper, course, notes, transcript, or other source material into suggested agent skills or skill improvements. Triggers on "what skills could come from this", "extract skills from", "turn this into skills", "skill ideas from this source".
development
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for large prs, new features/architectures, a deep code quality audit, or especially harsh maintainability review.
testing
Commit, push, open, and land a pull request through CI handoff. Use when work is complete and the user wants an agent to create or update a PR, open it as a draft, monitor GitHub checks with `gh pr checks`, fix failed checks, retry up to three remediation pushes, mark the PR ready for review once green, and move a linked Linear ticket to Human Review when one exists. Trigger on requests like 'land this PR', 'open and monitor a PR', 'commit push and watch CI', 'get this ready for review', or 'finish the PR workflow'.