ui-preview

ui-preview is a skill for Claude Code, Codex from mindverse-ltd/macaron-artifacts. It costs 108 tokens per session (1,183 once invoked), scanned A, original, Apache-2.0.

A workflow for changing an existing web interface and showing the proposed result in a visual preview before code is saved. It covers pages, sections, and components such as buttons, cards, forms, and dashboards.

In plain words
What is it for?
Use it to rewrite interface copy, adjust layouts and spacing, restyle components, add controls, or move between component libraries.
Why use it?
It lets you inspect the intended visual result before changing files, which makes layout and styling changes easier to review.

Skill for Claude CodeCodex

Part of the macaron plugin — 5 skills, 1 command shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/mindverse-ltd/macaron-artifacts/ui-preview
Any agent
npx skills add mindverse-ltd/macaron-artifacts --skill ui-preview
Clone the repo
git clone --depth 1 https://github.com/mindverse-ltd/macaron-artifacts

Made for: Claude Code, Codex.

Or install macaron, the plugin that ships this one along with the rest of its 5 skills, 1 command.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ui-preview

README.md
[![agentmods](https://agentmods.dev/badge/skills/mindverse-ltd/macaron-artifacts/ui-preview.svg)](https://agentmods.dev/skills/mindverse-ltd/macaron-artifacts/ui-preview)
Your own site
<a href="https://agentmods.dev/skills/mindverse-ltd/macaron-artifacts/ui-preview"><img src="https://agentmods.dev/badge/skills/mindverse-ltd/macaron-artifacts/ui-preview.svg" alt="Measured on agentmods" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00108 $0.01183
Opus 5 $0.00054 $0.00592
Sonnet 5 $0.00022 $0.00237
Haiku 4.5 $0.00011 $0.00118

Measured 4d ago against content hash e98fa83cda93, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ui-preview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ui-preview/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Preview (see it before you write it)

Frontend edits are a class of change where "read the diff to know if it's right" is much slower than "look at it". This skill inverts the usual write-first-then-user-eyeballs flow: render the proposed after-state in chat as a working preview, and only touch files when the user clicks Apply.

When this fires

Any request to modify an existing UI area:

  • "Redesign this button / card / hero / modal"
  • "Change the login form to have avatars on the left"
  • "Make this list more compact / spacier / dark-mode / mobile-first"
  • "Move the submit button to the top"
  • "Add a settings panel to the sidebar"
  • "Migrate from Material to shadcn / from Tailwind v2 to v3"
  • "Improve the copy on this landing page hero"
  • "Tighten spacing across the dashboard cards"

Does NOT fire for:

  • Non-visual code changes (business logic, API handlers, tests).
  • Brand-new files with no existing UI to compare against — that's a normal render_ui.
  • Purely visual TODO you're asked to just describe, not implement.

The flow

Step 1: read the current source. Find the target component(s). Read enough surrounding code to know what props / state / classes are in play. If it's a large page, read the specific section only.

Step 2: render the AFTER state. Call render_ui with a TSX module that IS the proposed replacement — same visual, same interactions, ideally re-using the same $macaron/ui components. Inline any state / mock props needed to make it visually complete. Do NOT stub interactive parts as "placeholder" — a preview the user can't play with is useless.

Step 3: end the widget with 3 buttons.

<Row className="gap-2 justify-end mt-4">
  <Button variant="ghost"
    onClick={() => sendUserMessage("Discard this preview, keep the current UI.")}>
    Discard
  </Button>
  <Button variant="outline"
    onClick={() => sendUserMessage("Tweak this preview: [describe what to change]. Re-render.")}>
    Tweak
  </Button>
  <Button
    onClick={() => sendUserMessage("Apply this preview to the actual file(s). Write the changes now.")}>
    Apply →
  </Button>
</Row>

Read the full file on GitHub · 84 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 84 lines · 108 tokens per session scan A e98fa83cda93

Subscribe to this mod's changes

ui-preview is a skill published in the GitHub repository mindverse-ltd/macaron-artifacts (10 stars, last pushed 11d ago), licensed Apache-2.0. It adds 108 tokens to every session and 1,183 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

archscribe

Create premium hand-drawn architecture, workflow, and swimlane diagrams in a dark neon or light paper style, with editable Excalidraw sources, PNG/SVG previews, animated GIF/MP4 output, and interactive HTML. Use whenever the user asks for 岚叔动态架构图、手绘架构图、Excalidraw 风格图、DailyDoseOfDS 风格技术图、动态流程图、泳道图、系统可视化,或希望复刻并提升参考架构图。.

lazypay/Archscribe · 110 tokens

artifact-styler

Restyle an artifact (an Artifact Organizer HTML/JSON output, or any content you can express as a component envelope) into a chosen visual theme — notion, linear, vercel, stripe, supabase, apple, or tailwind. Use when the user says "restyle this", "make it look like apple/tailwind/stripe", "apply the X theme", "change…

keepYaoung/artifact-organizer · 119 tokens

design-standards

Data visualization design standards and 100-point scoring rubric for dashboards — visual hierarchy, color discipline, spacing, chart hygiene. Derived from Tableau Viz of the Day winners. Use when designing a dashboard layout or lint-scoring a rendered dashboard screenshot.

blakefeiza/vizwright · 53 tokens

Explainer

Generate dense, visual-first HTML explainers in a signature dark aesthetic — diagrams carry the design, prose is captions only. Every section has a custom inline-SVG visualization: pipeline DAGs, archetype grids, hub-and-spoke diagrams, decision trees, risk matrices, gantt timelines, layer cakes, palette swatches…

Angelopvtac/explainer-pack · 209 tokens

html-artifact-guide

Use when creating, reviewing, or improving standalone single-file HTML artifacts for comparison matrices, dashboards, timelines, review surfaces, visual explainers, research synthesis, or interactive checklists. Do not use for simple documentation, meeting notes, knowledge base articles, or content where Markdown…

ClawEnable/html-artifact-best-practices · 62 tokens

json-render-catalog

Skill "json-render-catalog" from yonatangross/orchestkit, covering json-render component catalogs, storybook → catalog import (#1529, 2026-04), new in 2026-04 → 2026-08 (json-render 0.14 → 0.20), directives — @json-render/directives (0.19) and registration.

yonatangross/orchestkit · 99 tokens