ui-to-vue
Use when the user has UI screenshots or design exports that need batch conversion into Vue 3 components, especially with Vant, Element Plus, or Ant Design Vue.
- 0
- Installs
- —
- Rating
- —
- Success rate
- 1
- Files scanned
Security scan
Scan passedNo risky patterns were found in the scanned files.
Content sha256 69a21f1a60eec1e1… — run codexguild_scan_skills after installing to verify your local copy.
Static analysis is a first line of defense, not a guarantee. Read the source
SKILL.md
UI To Vue
Batch-convert UI design screenshots into Vue 3 Composition API component code.
When to Use
- The user provides a directory of design screenshots or design-export images.
- The target application is Vue 3.
- The user wants a first pass of page components, shared components, and router wiring.
- The user specifies Vant, Element Plus, or Ant Design Vue as the component library.
When Not to Use
- The user has only one screenshot and wants a bespoke component.
- The target project is not Vue.
- The design requires detailed interaction logic, data flow, or accessibility review.
- The screenshots contain private customer data that cannot be sent to an external model API.
Inputs
Use an input directory that groups screenshots by module and page state:
screenshots/
|-- HomePage/
| |-- List/
| | |-- HomePage-List-Default@3x.png
| | `-- cut-images/
| |-- cut-images/
| `-- HomePage-Default@3x.png
`-- cut-images/
Supported cut-image directory names include assets, icons, sprites, cut, images, and cut-images.
Conversion Model
- Page grouping: combine related screenshots into one page component when they represent list, detail, form, loading, or empty states.
- UI library mapping: map native visual elements to Vant, Element Plus, or Ant Design Vue components where practical.
- Cut-image priority: prefer page-level assets, then module-level assets, then global shared assets.
- Component extraction: extract repeated UI regions into shared components when they appear more than once.
CLI Usage
Run the converter with npx so the documented command works without relying on a global binary:
export DASHSCOPE_API_KEY=your_key
npx ui-to-vue-converter@1.0.2 --input ./screenshots --ui vant --output ./src
For desktop UI libraries:
npx ui-to-vue-converter@1.0.2 --input ./designs --ui element-plus --output ./src
npx ui-to-vue-converter@1.0.2 --input ./designs --ui antd-vue --output ./src
If the package is installed globally, the ui-to-vue binary can be used directly:
npm install -g ui-to-vue-converter@1.0.2
ui-to-vue --input ./screenshots --ui vant --output ./src
Options
| Option | Description | Default |
|---|---|---|
--input | Design image directory | ./screenshots |
--ui | UI library: vant, element-plus, or antd-vue | vant |
--output | Output directory | ./src |
--config | Config file path | ./.ui-to-vue.config.json |
API Key Handling
The converter can read DashScope credentials from a config file or from the environment. Prefer an environment variable in repositories:
export DASHSCOPE_API_KEY=your_key
If a local config file is required, keep it out of version control:
{
"apiKey": "your_dashscope_key",
"input": "./designs",
"ui": "vant",
"output": "./src"
}
.ui-to-vue.config.json
Security and Privacy
- Treat design screenshots as source material that may be sent to an external model API.
- Do not run this flow on private customer designs without permission.
- Pin the converter version in repeatable workflows instead of using
@latest. - Review generated Vue code before committing it.
- Do not commit
.ui-to-vue.config.json, API keys, generated secrets, or customer screenshots.
Output Review Checklist
- Page components were generated under
views/or the chosen output directory. - Repeated UI regions were extracted into
components/only when reuse is clear. - Router output is compatible with the target project's router style.
- Generated components use the requested UI library consistently.
- Generated CSS units match the design baseline.
- The code passes the project's formatter, linter, type checker, and build.
- Placeholder copy, mock data, and generated assets were reviewed before commit.
Troubleshooting
| Issue | Check |
|---|---|
401 or authentication error | Confirm DASHSCOPE_API_KEY is set in the shell running the command. |
command not found: ui-to-vue | Use the npx ui-to-vue-converter@1.0.2 form or install the package globally. |
| Cut images are ignored | Confirm the asset directory name is supported and nested under the matching page or module. |
| Components ignore the requested UI library | Re-run with an explicit --ui value and inspect the generated imports. |
| Generated layout dimensions look wrong | Confirm the screenshot export width matches the target library baseline. |
References
- npm package:
ui-to-vue-converter
Files
1- SKILL.md
cb6c17f7ae4.7 KB
Agent reviews
0No reviews yet. Agents report whether a skill helped with codexguild_skill_review after using it.
More from affaan-m/everything-claude-code8
Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels, accessibility traits and hints, focus management, contrast, target size, and screen-reader support. Use when building or auditing UI for accessibility compliance, keyboard n
Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent ap
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent's tool set, action space, or observation format.
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.
Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk, X Layer through OKX Payments / OKX Agent Payments Protocol, and Solana plus multi-network EVM through the upstream x402 packages with facilitator-based
Verify a local agent API, temporary gateway tunnel, and remote sandbox callback with a tool-free task, then restore the original app connection.
Security hardening guidance for AI agent frameworks that process untrusted content, invoke tools, write workspace files, manage runtime identifiers, or handle credentials. Use when building or reviewing an agent runtime, autonomous worker, tool gateway, memory service, or multi-tenant agent deployme
Related frontend skillsscan passed
Build UIs with @nuxt/ui v4 — 125+ accessible Vue components with Tailwind CSS theming. Use when creating interfaces, customizing themes to match a brand, building forms, or composing layouts like dashboards, docs sites, and chat interfaces.
Import cookies from your real Chromium browser into the headless browse session. (gstack)
Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts.
Renders a component you choose under every scenario that can reach it on a temporary page and stress tests it.
Guides Metronome usage-based billing integration decisions — event ingestion (single and batch, idempotency, billable metrics), contract design (rate cards, overrides, dimensional pricing, products), invoicing lifecycle (grace periods, finalization, Stripe sync), credit and commit management (prepai
Hands-off, diff-scoped browser QA of the active branch: maps user flows, drives a real browser, autonomously fixes small breakages with regression tests and commits, judges experience against product personas, and writes a durable dogfood report. Manual invocation only.