Builds new UI prototypes and makes targeted changes to existing prototypes using consumer-owned context. Use when asked to build a prototype, mock up a UI, or add, change, refine or recreate part of an existing prototype. Do not use for unrelated tasks, routine commands, Git lifecycle actions, acknowledgements or infrastructure work.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
When asked to create controls for variants, scenarios, adjustable previews or data-source switches, read the adjacent prototype-controls skill, even when the request never says "canvas controls". Product UI form fields and filters alone stay in this skill. Controls guidance does not establish panel availability.
Determine the branch from the original request, prior answers and current target before loading any workflow files. Use a short, targeted lookup of consumer repository instructions or the named target if needed, not a broad repository tour. The word "new" alone does not decide: "add a new tab to this prototype" is iteration.
| Request | Required read, only for this branch |
|---|---|
| Clear new build, such as "build an offline inventory prototype" | create |
| Change to an existing prototype, such as "add filtering to this page" | iterate |
| Consequential missing information, including an unresolved target or create-versus-iterate choice | clarify, then the selected build or iteration workflow |
| Unrelated task or routine command | Stop using this skill and continue the original task |
Load only the selected workflow, not all companions as a required-read bundle. Clarification is conditional, not a startup step. Either build or iteration can need it later, but a clear request skips it entirely. Do not load the other branch for orientation. If the selected companion is missing, report its exact installed path and stop. Do not improvise it or use the other branch.
Preserve the original request and every answer in session context throughout the work. A choice answers only its question, not unrelated scope. There is no mandatory brief file, schema, build-mode quiz or separate intake skill.
Stay in the current target and worktree unless the user explicitly requests a different destination. A reference URL is not permission to fork, duplicate, publish, delete or activate anything. Approved references are 1:1 requirements except for the requested delta, not design inspiration.
The selected workflow reads the shared
authoring reference before implementation.
It owns context resolution, design evidence, data boundaries and completion.
It does not load another workflow. Install product-design, setup-skills
and the context-templates library alongside this skill.
Missing installed dependencies stop
the affected work with their exact paths, never trigger automatic installation.
Context research uses the centralized library through setup-skills. The shared authoring reference declares this consumer's context reads. Templates are setup inputs, not additional per-task reads or active product facts.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Audits actual components and routes against applicable WCAG 2.2 A/AA criteria using consumer-owned design-system evidence and repository tools. Use when asked for an accessibility audit, a11y check, keyboard or focus review, contrast check, or screen-reader verification.
The English summary is being prepared. Showing the original description.
Creates or updates believable deterministic raw fixture scenarios without breaking an existing prototype. Use when asked to add or change fixtures, seed data, sample data, scenarios, or cross-record relationships. Not for UI redesign, live-data infrastructure, or unrelated commands.
The English summary is being prepared. Showing the original description.
Use for explicit agent-browser CLI checks or a named browser capability neither the Copilot canvas nor configured Playwright MCP can supply. Ordinary rendered checks and browser selection belong to browser-canvas-validation.
The English summary is being prepared. Showing the original description.
Use the Copilot browser canvas first for rendered route checks, interaction tests, screenshots and visual, responsive or accessibility evidence. Use configured isolated Playwright MCP only when the canvas is unavailable for a required check.
The English summary is being prepared. Showing the original description.
Review Replica pull requests using the same shared conventions and project guides as implementation agents. Use when reviewing changes to code, tests, workflows, or documentation in this repository.
The English summary is being prepared. Showing the original description.
Reviews existing UI components for design-system consistency, states, responsiveness and accessibility using consumer-owned context. Use when asked to review component quality, check design-system adherence or audit component consistency.
The English summary is being prepared. Showing the original description.