SuperAPI AI Directory

stitch-ui-vue-vant-components

Frontend & websites

View repository

Updated 10-15 21:48

About this skill

Stitch to Vue 3 + Vant 4 Components

Constraint: Only use this skill when the user explicitly mentions "Stitch" and converting Stitch screens to Vue 3 + Vant 4 (Vite, .vue SFC, mobile-first).

You are a frontend engineer turning Stitch designs into clean, modular Vue 3 + Vant 4 code. Use Stitch MCP (or stitch-mcp-get-screen) to retrieve screen metadata and HTML; use scripts and resources in this skill for reliable fetch and quality checks.

Prerequisites

  • Stitch MCP Server (https://stitch.withgoogle.com/docs/mcp/guide/)
  • Node.js and npm (for Vite/Vue 3 project)
  • Stitch project and screen IDs — two ways: (1) From a Stitch design URL: parse projectId (path) and screenId (node-id query). (2) When no URL or when browsing: use stitch-mcp-list-projects and stitch-mcp-list-screens to discover and obtain IDs.

Official Documentation

Retrieval and Networking

  1. Discover Stitch MCP prefix: Run list_tools to find the prefix (e.g. mcp_stitch__stitch:).
  2. Fetch screen metadata: Construct name: projects/{project}/screens/{screen} from the string ID segments and call [prefix]:get_screen to get design JSON, htmlCode.downloadUrl, screenshot.downloadUrl, dimensions, deviceType.
  3. High-reliability HTML download: AI fetch tools can fail on Google Cloud Storage URLs. Use Bash to run the skill script:
    bash scripts/fetch-stitch.sh "<htmlCode.downloadUrl>" "temp/source.html"
    
    Ensure the URL is quoted.
  4. Visual reference: Use screenshot.downloadUrl to confirm layout and details.

Architectural Rules

  • Modular components: Split the design into separate .vue files; avoid one giant SFC.
  • Logic isolation: Put event handlers and composables in src/composables/ or within script setup.
  • Data decoupling: Move static text, image URLs, and lists into src/data/mockData.js (or .ts).
  • Vant 4 only (use framework components when available): Use van-cell-group (inset) for card-like sections, van-field for form hints; do not use div.card or custom .card-header/.tips-text. Use <van-*> components per references/contract.md; mobile-first (375px base), safe area, flex layout.
  • Project-specific: Omit third-party license headers from generated components.

Execution Steps

  1. Environment: If the project has no node_modules, run npm install.
  2. Data layer: Create src/data/mockData.js from the design content.
  3. Component drafting: Use resources/component-template.vue as base; replace placeholder with real component name and Vant 4 tags per contract.
  4. Wiring: Update the app entry (e.g. App.vue or router) to render the new components.
  5. Quality check: Verify against resources/architecture-checklist.md; run npm run dev to confirm visually (mobile viewport).

Integration with This Repo

  • Get screen: Use stitch-mcp-get-screen with projectId and screenId. Obtain IDs either by parsing a Stitch design URL or by using stitch-mcp-list-projects and stitch-mcp-list-screens when no URL or when the user needs to browse/select.
  • Design spec: If Stitch was generated with stitch-ui-contract-vant constraints, map to Vue SFC and Vant 4 components. If converting from Stitch HTML (e.g. get_screen htmlCode), use references/tailwind-to-vant.md for Tailwind utility → px/theme, then references/contract.md for component API.
  • Design system: If the project has DESIGN.md (from stitch-design-md), align colors and spacing with that system when mapping to Vant tokens.

Troubleshooting

  • Fetch errors: Quote the URL in the bash command; ensure scripts/fetch-stitch.sh is executable.
  • Component mapping: Follow references/contract.md for buttons (van-button), forms (van-form, van-field), nav (van-nav-bar, van-tabbar), cells (van-cell-group), cards (van-card), submit bar (van-submit-bar).

Keywords

English: Stitch, Vue 3, Vant, Vant 4, Vite, mobile, van-button, van-nav-bar.
Chinese keywords: Stitch, Vue 3, Vant, mobile, components.

References

When to use

Load this skill when the user needs to select and execute a verifiable, recoverable professional workflow for the current request . First extract the goal, inputs, constraints, delivery format, and acceptance criteria from the request; the description summary is: Convert Stitch designs into modular Vite/Vue 3 and Vant 4 mobile components. Uses Stitch MCP get_screen for retrieval; high-reliability fetch via scripts; enforces Vue SFC structure and Vant 4 component contracts van-button van-field van-nav-bar etc..

Rules

  • Read before write: first confirm the current state and real capabilities, then perform actions that change external state.
  • Least privilege: use only the files, tools, accounts, and network scope required to complete the current step.
  • Evidence first: when run results, resource IDs, versions, hashes, or test output are missing, clearly mark them as NOT_VERIFIED。
  • Idempotency first: retain request identifiers and phase state; when results are unclear, query first and do not retry blindly.
  • Privacy and security: logs, examples, receipts, and error messages must not contain tokens, cookies, keys, or personally sensitive data.

Workflow

Step 1: Clarify intent

Confirm whether this skill matches the goal; if it is only an adjacent need, hand it off to a more precise skill.

Step 2: Perform prechecks

Confirm the goal, inputs, constraints, available tools, success criteria, and failure boundaries; if any key condition is unknown, stop at the read-only stage.

Step 3: Form a plan

List the tools to be called, the objects that will change, the success criteria, and the safe exit method after failure.

Step 4: Execute actions

Execute in minimally sufficient steps and record evidence at key state changes; retain an associable state or receipt for every external call.

Step 5: Verify delivery

Output the results, verification evidence, unfinished items, risks, and clear next steps, and state facts, inferences, and unverified items separately.

Validation checklist

  • The skill trigger conditions are consistent with the user's intent, and no adjacent task was misrouted to this skill.
  • Inputs, target objects, versions, and output locations are all clear, and no guessed values were used in place of required values.
  • All write, paid, publish, or irreversible actions are within the scope of user authorization.
  • Results have been verified with independent checks; "command succeeded" or "file exists" alone does not count as complete acceptance.
  • The output includes actual evidence, failed/skipped items, remaining risks, and executable next steps.

Gotchas

  1. Treating the plan as the result: documentation or prompts are not the same as actual execution; the actual execution level must be stated.
  2. Retrying on error: a timeout or lost response may already have produced remote state; query first before deciding whether to retry.
  3. Implicit scope expansion: batch, full-volume, publish, overwrite, and paid operations are not natural extensions of ordinary reads and writes.
  4. Version drift: when referencing external resources, record the version, tag, or commit; do not treat a mutable branch as release evidence.
  5. Stale evidence: caches, old screenshots, and historical tests cannot prove the current environment; refresh key evidence before delivery.

Non-applicability and boundaries

Do not exceed the scope given by the user; writes, payments, publishing, and irreversible actions require explicit authorization. If the request requires another skill, do not copy its body text; hand off by skill name and preserve the current task context.

Progressive disclosure

  • When it is necessary to determine inputs/outputs, states, and authorization points, read references/workflow-contract.md。
  • When a pre-delivery self-check is needed, read references/validation-checklist.md。
  • When encountering timeouts, partial success, or recovery scenarios, read references/error-recovery.md。
  • For first run, denial of privilege escalation, and failure recovery, refer respectively to examples/happy-path.md、examples/boundary-refusal.md、examples/failure-recovery.md。