an
Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces,…
Use Design for UI/UX exploration, side-by-side design directions, interactive prototype previews, user selection, iteration, and design-to-code handoff through the hosted Design MCP app.
$ npx -y skills add builderio/agent-native --skill design-exploration --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/design-explorationContext preview
The summary Claude sees to decide when to auto-load this skill.
Use Design for UI/UX exploration, side-by-side design directions, interactive prototype previews, user selection, iteration, and design-to-code handoff through the hosted Design MCP app.
name: design-exploration description: >- Use Design for UI/UX exploration, side-by-side design directions, interactive prototype previews, user selection, iteration, and design-to-code handoff through the hosted Design MCP app. metadata: visibility: exported
Use the Design app when a workflow needs visual UI exploration, prototype iteration, or a human-in-the-loop choice among design directions.
design as ready until it has renderable HTML.
directions (2-5, three by default) and call `present-design-variants`. Each direction should be one representative screen or directional snapshot, not a full app per variant. Design saves every option as a normal screen on the overview board and renders an inline chat choice with one button per screen name. After the user picks, delete the unchosen variant screens and continue from the kept screen by first calling `get-design-snapshot` with that screen's `fileId`, then calling `edit-design` on that same `fileId` in a bounded single-file pass. Use `mode: "replace-file"` when expanding the representative placeholder into the full chosen direction. Do not call `generate-design` after a variant pick.
tell you the screen name they prefer. The variants are already real screens on the board, so do not ask them to paste HTML or copy a generated handoff summary.
`get-design-snapshot`, edit from the current tuned HTML, and use `edit-design` for surgical changes or `mode: "replace-file"` for a bounded selected-file replacement. Use `generate-design` for new files only.
design in a codebase.
1. Default to three variants unless the user asks for a different count (`present-design-variants` accepts 2-5; three is the sweet spot). 2. Make variants structurally and stylistically distinct, not just color swaps. 3. Each variant must be a compact, complete standalone HTML document that renders without a build step. 4. For product UI redesigns, prefer cleaner hierarchy, progressive disclosure, and realistic controls over decorative mockups. 5. After `present-design-variants`, wait for the user's pick before generating the next version. Keep the chosen screen, delete the other variant screens, call `get-design-snapshot` with `fileId` for the kept screen, then call `edit-design` on that same `fileId` in a bounded pass. Use `mode: "replace-file"` when expanding the representative placeholder into the full chosen direction. Do not call `generate-design` after a variant pick. Stop after the first successful `edit-design` save.
Generic "AI slop" comes from letting one prompt set taste, explore, and emit code at once — so the model returns the training-average (Inter, an indigo/violet gradient, a centered hero, three rounded cards). The variant flow above exists to separate those jobs; use it, and hold this bar:
the visual thesis. If the brief is vague, make a reasonable choice and state it instead of producing a generic dashboard/landing-page default.
just makes you reach for Roboto). Avoid Inter/Roboto/system fonts, the indigo/violet slop palette (`#6366F1`/`#8B5CF6`/`#A855F7`) and purple-on-white gradients, and centered-hero + three-icon-card layouts; instead pick a distinctive font pairing, one non-default palette family with a single decisive accent, and an asymmetric layout with a clear focal point.
Give every variant one memorable signature choice, then keep the surrounding chrome disciplined. Even your creative picks converge (Space Grotesk everywhere) — vary deliberately so two directions never share a fingerprint.
component language before inventing a new direction. Treat any drift back to a default as a missing token to pin, and vary layout per screen so on-brand does not become same-in-your-colors.
content and first-party/generated assets when images matter; avoid lorem ipsum, vague SaaS filler, and decorative placeholder boxes.
keyboard focus, useful loading/empty/error states for app UI, and reduced motion support when custom motion is present.
a screenshot-capable host before calling it ready. Fix obvious hierarchy, overflow, contrast, broken interaction, and placeholder-content issues first.
Do not put shared secrets in skill files.
running until browser authorization finishes. Stopping it early can leave the browser approved but the local MCP config unwritten. Restart or reload the agent client after installing or connecting if Design tools do not appear in the live session.
tasks, Assets for image/media selection, Slides for decks, and so on.
design" link instead of pasting large HTML blobs into chat.
Agent-Native is an open-source TypeScript framework for building agents that pair autonomous work with a purpose-built UI. Define each capability once as an action: the agent uses it as a tool, and the UI calls it from code.
Repo: builderio/agent-native
Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces,…
Use Agent-Native Assets for image and video generation requests, brand-safe asset…
Use Content for repo-backed Markdown/MDX docs, blogs, resources, rich document editing, local…
Visualize local Codex and Claude Code context usage, open a report, flag warnings, and…
Turns a thread, skill, spreadsheet, or Claude/ChatGPT project into a polished, visual…
Open and collaboratively edit a running local app in Design, with shared fallback previews…