Structures that disagree
Variants named by layout and primary affordance. Color, type, and density are wallpaper, not a test.
Premium skill
Test UI variants by stealing
Several layouts that disagree, one session, iterate by steal — not one mock with three color tweaks.
- Plan
- Premium
- Access
- Gated
- Install
- Tokenized
- Authored files
- 2
Install
Install with skills CLIPremium skills install through a short-lived private link.
$ npx skills add … --skill test-ui-variantsOpen Premium install
Sign in with Premium to generate a fresh install link.
Filesystem
Browse the authored file tree — tools, references, and evals included. Source unlocks with Premium.
SKILL.mdmarkdownUnlock skill source
Browse every authored SKILL.md with premium.
File tree for test-ui-variants stays visible so you can see the pack before unlocking.
What you get
One session above the switch
Load the records once. Flip. Compare structure, not a fresh story in every mock.
Iterate by steal
The note is never “I pick B.” It is the header from B with the inspector from A — shipped as a new variant.
Rewrite the winner
Fold the decision into the live route. Park the argument on a throwaway branch. Do not ship the switcher.
Where this skill lands
A testing loop, not a polish pass: disagree, flip, steal, remix, then fold in.
Three card grids offered as “variants” of the same dashboard.
Each layout fetched its own mock threads, so the comparison was stories.
A live route edited while the loop was still open.
“B is closest” treated as done, instead of stealing from A and C.
Put several opinions on one URL
Available with Premium. The private install link expires; the downloaded skill does not. Generate a fresh link when you want to update it.
Other Premium skills
Lifecycle skills and UI craft skills
- PlanPlan AI SDK AgentBefore you write agent code
- BuildAISDK AgentsImplementing agents, chat apps, and streaming UIs
- EvaluateBuild AI SDK Agent EvalsProtecting critical agent journeys before you optimize
- ObserveObserve AI SDK AgentDebugging and attributing agent behavior in production
- OptimizeOptimize AI SDK AgentImproving quality, speed, cost, or reliability with proof
- InstructWrite Agent PromptsAgents that ignore instructions or run on folklore prompts
- InstructWrite Prompt ContractsAgents that pick the wrong tool or narrate a plan instead of acting
- Chat UIBetter Chat UIBuilding or reviewing the conversation surface
- Generative UIBetter Generative UITurning model output into interactive product UI
- IngestIngest Messy DocumentsPDF, scan, and table-heavy corpora feeding RAG or extraction
- GroundGround AI SDK AgentMaking an agent answer from your data with proof
- MemoryAgent MemoryAgents that should remember users across sessions
- ExposeBuild MCP ServerMaking your product agent-accessible
- ExtractExtract Structured DataInvoices, resumes, contracts, forms, and free text to typed data
- ShipShip AI SDK on CloudflareGetting an AI SDK agent into production on Cloudflare
- ShipShip AI SDK on AWSGetting an AI SDK agent into production on AWS
- MobileAI SDK on MobileShipping AI SDK chat in an Expo or React Native app
- MigrateMigrate to AI SDKLeaving LangChain, the Assistants API, or hand-rolled LLM code