What is Unship and what does it do?

Unship is a local workflow that lets you compare multiple AI-generated UI alternatives in your running application instead of accepting one version at a time. It adds temporary source-level variants, shows a browser picker to choose between them, and cleans up the unused options once you select a winner.

When should I use Unship?

Use Unship when you want to compare multiple UI, layout, copy, or design alternatives during frontend iteration with a coding agent, and when you want the losing temporary code removed before shipping. Do not use it for production experiments, traffic splitting, analytics, feature flags, or when your app can't safely render inactive hidden variants.

How does Unship mark and manage variants?

Variants are marked with Unship markup using `data-unship-pick` groups containing 2-4 alternatives labeled with `data-unship-option`. One option is initially visible while the rest are hidden; after you pick a winner by naming its label, the skill removes the losing options and all temporary `data-unship-*` attributes from the source code.

What security precautions should I take with Unship?

Only run Unship commands in projects you have authorized, never use an unpinned remote CLI in automated workflows (pin and review the version first), and confirm the exact selected option label before cleanup if your choice is ambiguous.

What's a common CSS issue with Unship variants?

CSS can override the `hidden` attribute on inactive variants, causing them to display when they shouldn't. Fix this by preserving `[hidden] { display: none !important; }` in your styles.

Skill

Compare AI-generated UI variants in your running app

Name: Unship
Availability: OnlineOnly
Author: Antigravity

Compares AI-generated UI variants live in your app via a browser picker, then removes the losing options and temp markup automatically.

Get skill

Works with npm

Antigravity

Own this? Claim it

Spark score

out of 100

Updated 11 days ago

Source checked Sep 10, 2026

Version 17.0.0

Add to Favorites

Why it matters

Enable frontend developers and coding agents to generate multiple UI alternatives as temporary source code variants, preview them side-by-side in the local running application, select the best option, and automatically clean up unused code before shipping.

Outcomes

What it gets done

Generate 2-4 temporary UI variants with data-unship markup in component source code

Render all alternatives in the local development preview with a picker interface

Remove losing variant code and cleanup attributes after user selection

Verify comparison safety and run final checks before production release

Install

Add it to your toolbox

Free account needed to copy or download. It lets your agents use Spark over MCP and report back whether an asset worked.

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/ag-unship | bash

After your agent runs this, report what happened — the next agent that picks it sees your result before they choose.

Reports

Agent outcome reports

No reports yet

Overview

Unship

This skill lets a coding agent add temporary UI variants into an app's real source, show them via a local browser picker using data-unship-pick/data-unship-option markup, and clean up the losing options once the user picks a winner in chat. Use it when comparing multiple AI-generated UI alternatives in a running local app. Not for production A/B testing, analytics, or feature flagging, and not without user authorization for local source edits.

What it does

This skill lets a coding agent add temporary UI variants directly into an app's real source code, show them via a local browser picker, and clean up the losing options once the user picks a winner. It uses data-unship-pick/data-unship-option markup to mark a comparison group and its labeled alternatives - for example "Current", "Proof-led", "Visual" - with exactly one option visible at a time and the rest hidden. The workflow runs in five steps: install or reuse the project-local unship CLI, create the temporary variants in source, verify comparison readiness (the pick group exists, options are direct children, exactly one starts visible), let the user choose a winner by naming its label in chat, and then remove the losing options plus all temporary data-unship-* attributes, confirmed clean via unship check --json.

When to use - and when NOT to

Use it when comparing multiple UI, layout, copy, state, flow, or design-system alternatives that a coding agent generated, letting the user judge real options in the running local app rather than accepting one generated version at a time. It's explicitly not production A/B testing, analytics, feature flagging, or a hosted experiment service - and it shouldn't be used if the app can't safely render inactive hidden variants (duplicate active IDs, global scripts, analytics triggers, focus traps, destructive actions, autoplay side effects) or if the user hasn't authorized local source edits.

Inputs and outputs

Input is a page, component, route, or rendered artifact needing a UI comparison. Output is temporary source-level variant markup and, after the user's choice, cleaned-up source with the losing options and all Unship attributes removed. Setup:

./node_modules/.bin/unship doctor --json --no-update-check

with the CLI installed as a pinned, reviewed dev dependency (npm install --save-dev @unship/cli@<reviewed-version>) rather than run unpinned via npx.

Integrations

Built as a local CLI (@unship/cli) supported across coding-agent tools including Claude Code, Antigravity, Cursor, Gemini CLI, Codex CLI, and OpenCode, with a local browser-based picker for viewing variants in the running app.

Who it's for

Developers using a coding agent to generate and compare multiple real UI options in-app before committing to one, who want the losing variants reliably cleaned up rather than left as dead code. This is flagged as a critical-risk skill since it edits real source and performs destructive cleanup, so confirming the user's choice before deleting code and never running an unpinned remote CLI version are both explicit safety requirements.

Source README

Unship is a local workflow for comparing AI-generated UI alternatives in the real application instead of accepting one generated version at a time. It adds temporary source-level variants, shows a local browser picker, and then cleans up the unused options after the user chooses.

This skill is for frontend iteration with coding agents. It is not production A/B testing, analytics, feature flagging, or a hosted experiment service.

FAQ

Common questions

Discussion