skill · built into metaphor
/artifact-mockup
UI mockups, side-by-side comparison grids, metric cards, and structured data records for HTML artifacts
- Built in
- Slash command
you ›/artifact-mockup
metaphor ›Loaded the artifact-mockup skill. What should I work on?
What the agent is told
This is the skill's SKILL.md, exactly what Metaphor reads before the task.
Use kind: "mockup" for side-by-side option comparisons, structured data records, and component/screen wireframes.
1. Side-by-side comparison grid
When comparing 2–4 options (libraries, architectures, plans, tradeoffs):
- Use
style="display: grid; grid-template-columns: repeat(auto-fit, minmax(160px, 1fr)); gap: 12px;". - Put each option in a
.raised-card. - Highlight the recommended option with
style="border: 2px solid var(--color-border-info);"and a compact pill badge (c-blue) in the header. - Keep attribute rows aligned across cards (latency, complexity, failure mode, best for) and add a
"Explore option"button wired tosendPrompt(...)when helpful.
<div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(160px, 1fr)); gap: 12px;">
<div class="raised-card flex flex-col justify-between gap-3" style="border: 2px solid var(--color-border-info);">
<div>
<div class="flex items-center justify-between gap-2 mb-2">
<span class="font-medium text-base">SQLite WAL</span>
<span class="c-blue text-xs px-2 py-1 rounded-sm">Recommended</span>
</div>
<p class="text-xs text-fg-subtle">Single-writer, concurrent readers, zero external process.</p>
<div class="flex flex-col gap-1.5 mt-3 pt-3 border-t text-xs">
<div class="flex justify-between"><span class="text-fg-subtle">Read p99</span><span class="font-mono">0.4 ms</span></div>
<div class="flex justify-between"><span class="text-fg-subtle">Ops overhead</span><span>None</span></div>
</div>
</div>
<button onclick="sendPrompt('Show the SQLite WAL schema and pragmas')">Inspect setup</button>
</div>
<div class="raised-card flex flex-col justify-between gap-3">
<div>
<div class="flex items-center justify-between gap-2 mb-2">
<span class="font-medium text-base">External Postgres</span>
<span class="c-gray text-xs px-2 py-1 rounded-sm">Alternative</span>
</div>
<p class="text-xs text-fg-subtle">Multi-node writes, requires managed instance or Docker.</p>
<div class="flex flex-col gap-1.5 mt-3 pt-3 border-t text-xs">
<div class="flex justify-between"><span class="text-fg-subtle">Read p99</span><span class="font-mono">2.8 ms</span></div>
<div class="flex justify-between"><span class="text-fg-subtle">Ops overhead</span><span>Daemon + migrations</span></div>
</div>
</div>
<button onclick="sendPrompt('Compare migration strategy for Postgres vs SQLite')">Compare migrations</button>
</div>
</div>
2. Structured data records & UI wireframes
- Data records (an API payload, PR summary, incident timeline, or config profile): place inside one
.raised-cardwith a header row (title + status pill), a 2–4 column key-value strip, and a cleanoverflow-x-autotable if needed. - UI wireframes: Frame the mockup inside a
.raised-cardwith a subtle header bar showing the route or view name infont-mono text-xs text-fg-subtle. Use real bare<input>,<select>, and<button>elements so the user can click and interact with the prototype. - Wide dashboards: Set
layout: "wide"on theartifacttool call only when building a multi-column dashboard that genuinely needs more than720px.
Questions
What is the artifact-mockup skill?
UI mockups, side-by-side comparison grids, metric cards, and structured data records for HTML artifacts
How do I use artifact-mockup in Metaphor?
It is built into Metaphor. Type /artifact-mockup in the composer, or describe the task and the agent loads the skill when it fits.
What is a skill?
A skill is a set of written instructions the agent reads before it starts a kind of task. It changes how the agent works, not what it is allowed to do.
More built-in skills
- /ai-ciSkillBudgeted investigation of failed GitHub Actions / PR checks — bootstrap annotations first, then failed logs, localize to code, classify flake vs real vs infraships with metaphor
- /ai-prSkillBudgeted whole-PR critique via the pr subagent — map diff, evidence findings, return a pr_review_draft for the Agent Review canvasships with metaphor
- /ai-securitySkillBudgeted security and AI-agent risk review — ai_security scan, OSV CVE/GHSA lookups, OWASP LLM/MCP/Top10 tagging, draft for Agent Review canvasships with metaphor
- /ai-sreSkillBudgeted production investigation against connected observability/logs MCP servers — scope, resolve schema, query, correlate, conclude with evidenceships with metaphor
- /artifactSkillDesign and publish self-contained HTML + Tailwind + SVG visual artifacts (diagrams, interactive explainers, charts, mockups, structured docs) that blend…ships with metaphor
- /artifact-chartSkillChart.js rules for HTML artifacts — offline lib:chart script, wrapper-div sizing, custom HTML legends with values, hex palette for canvas, and honest data rulesships with metaphor