refine
Build data-intensive React applications with Refine. Use when a user asks to create admin panels, dashboards, or CRUD interfaces using Refine with REST, GraphQL, or custom data providers and Ant Design or Material UI.
Best use case
refine is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Build data-intensive React applications with Refine. Use when a user asks to create admin panels, dashboards, or CRUD interfaces using Refine with REST, GraphQL, or custom data providers and Ant Design or Material UI.
Teams using refine should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/refine/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How refine Compares
| Feature / Agent | refine | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Build data-intensive React applications with Refine. Use when a user asks to create admin panels, dashboards, or CRUD interfaces using Refine with REST, GraphQL, or custom data providers and Ant Design or Material UI.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Refine — React Framework for Admin Panels
## Overview
You are an expert in Refine, the open-source React framework for building data-intensive applications like admin panels, dashboards, and internal tools. Refine is headless — it provides data fetching, auth, access control, and routing hooks while you choose the UI library (Ant Design, Material UI, Chakra, Mantine, or custom).
## Instructions
### Quick Start
```bash
npm create refine-app@latest my-admin -- \
--ui antd \
--data-provider rest \
--auth-provider custom
cd my-admin && npm run dev
```
### Resource Definition
```tsx
// src/App.tsx — Define CRUD resources
import { Refine } from "@refinedev/core";
import { ThemedLayoutV2 } from "@refinedev/antd";
import dataProvider from "@refinedev/simple-rest";
import routerProvider from "@refinedev/react-router";
function App() {
return (
<Refine
dataProvider={dataProvider("https://api.example.com")}
routerProvider={routerProvider}
resources={[
{
name: "orders",
list: "/orders",
show: "/orders/:id",
edit: "/orders/:id/edit",
create: "/orders/create",
meta: { icon: <ShoppingCartOutlined />, label: "Orders" },
},
{
name: "users",
list: "/users",
show: "/users/:id",
edit: "/users/:id/edit",
meta: { icon: <UserOutlined /> },
},
{
name: "analytics",
list: "/analytics",
meta: { icon: <BarChartOutlined /> },
},
]}
>
<ThemedLayoutV2>
<Routes>
<Route path="/orders" element={<OrderList />} />
<Route path="/orders/:id" element={<OrderShow />} />
<Route path="/orders/:id/edit" element={<OrderEdit />} />
<Route path="/users" element={<UserList />} />
</Routes>
</ThemedLayoutV2>
</Refine>
);
}
```
### List Page with Filtering
```tsx
// src/pages/orders/list.tsx — Auto-generates table with CRUD
import { useTable, useSelect } from "@refinedev/antd";
import { Table, Tag, DatePicker, Select, Space, Button } from "antd";
export const OrderList: React.FC = () => {
const { tableProps, searchFormProps } = useTable({
resource: "orders",
sorters: { initial: [{ field: "created_at", order: "desc" }] },
filters: {
permanent: [{ field: "archived", operator: "eq", value: false }],
},
pagination: { pageSize: 20 },
});
const { selectProps: statusOptions } = useSelect({
resource: "order_statuses",
optionLabel: "name",
optionValue: "value",
});
return (
<Table {...tableProps} rowKey="id">
<Table.Column dataIndex="id" title="Order #" sorter />
<Table.Column dataIndex="customer_email" title="Customer" sorter />
<Table.Column
dataIndex="amount"
title="Amount"
render={(val) => `$${(val / 100).toFixed(2)}`}
sorter
/>
<Table.Column
dataIndex="status"
title="Status"
render={(status) => (
<Tag color={status === "paid" ? "green" : status === "refunded" ? "red" : "blue"}>
{status}
</Tag>
)}
filterDropdown={(props) => <Select {...statusOptions} {...props} />}
/>
<Table.Column dataIndex="created_at" title="Date" render={(d) => new Date(d).toLocaleDateString()} sorter />
<Table.Column
title="Actions"
render={(_, record) => (
<Space>
<ShowButton recordItemId={record.id} size="small" />
<EditButton recordItemId={record.id} size="small" />
</Space>
)}
/>
</Table>
);
};
```
### Data Providers
```typescript
// Refine works with any backend via data providers:
// Built-in: REST, GraphQL, Supabase, Strapi, Appwrite, Hasura,
// NestJS, Airtable, Firebase, Directus, Medusa
// Custom data provider for your API
import { DataProvider } from "@refinedev/core";
export const myDataProvider: DataProvider = {
getList: async ({ resource, pagination, sorters, filters }) => {
const params = new URLSearchParams();
params.set("page", String(pagination?.current ?? 1));
params.set("limit", String(pagination?.pageSize ?? 20));
if (sorters?.[0]) params.set("sort", `${sorters[0].field}:${sorters[0].order}`);
const response = await fetch(`/api/${resource}?${params}`);
const { data, total } = await response.json();
return { data, total };
},
getOne: async ({ resource, id }) => {
const response = await fetch(`/api/${resource}/${id}`);
const data = await response.json();
return { data };
},
create: async ({ resource, variables }) => {
const response = await fetch(`/api/${resource}`, {
method: "POST", body: JSON.stringify(variables),
headers: { "Content-Type": "application/json" },
});
const data = await response.json();
return { data };
},
update: async ({ resource, id, variables }) => {
const response = await fetch(`/api/${resource}/${id}`, {
method: "PATCH", body: JSON.stringify(variables),
headers: { "Content-Type": "application/json" },
});
const data = await response.json();
return { data };
},
deleteOne: async ({ resource, id }) => {
await fetch(`/api/${resource}/${id}`, { method: "DELETE" });
return { data: { id } as any };
},
getApiUrl: () => "/api",
};
```
## Installation
```bash
npm create refine-app@latest # Interactive setup
# Or manually:
npm install @refinedev/core @refinedev/antd @refinedev/react-router
```
## Examples
**Example 1: User asks to set up refine**
User: "Help me set up refine for my project"
The agent should:
1. Check system requirements and prerequisites
2. Install or configure refine
3. Set up initial project structure
4. Verify the setup works correctly
**Example 2: User asks to build a feature with refine**
User: "Create a dashboard using refine"
The agent should:
1. Scaffold the component or configuration
2. Connect to the appropriate data source
3. Implement the requested feature
4. Test and validate the output
## Guidelines
1. **Headless first** — Refine is UI-agnostic; choose Ant Design for speed, Material UI for familiarity, or go fully custom
2. **Data providers for any backend** — Use built-in providers for Supabase, Strapi, Hasura; write a custom one for your API in ~50 lines
3. **Hooks over components** — Use `useTable`, `useForm`, `useShow` hooks for full control; they handle data fetching, pagination, and caching
4. **Access control** — Implement `accessControlProvider` for role-based UI; Refine hides buttons/pages users can't access
5. **Inferencer for prototyping** — Use `@refinedev/inferencer` to auto-generate CRUD pages from API responses; replace with custom pages later
6. **Audit logs** — Enable `auditLogProvider` to track who changed what; critical for internal tools
7. **Real-time updates** — Add `liveProvider` for WebSocket updates; tables refresh when data changes
8. **i18n built-in** — Use `i18nProvider` for multi-language admin panels; Refine handles label translationRelated Skills
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when you have a vague idea that needs sharpening, want to stress-test a plan, or need to explore variations before committing to a direction. Produces a concrete markdown one-pager with problem statement, assumptions, MVP scope, and trade-offs.
zustand
You are an expert in Zustand, the small, fast, and scalable state management library for React. You help developers manage global state without boilerplate using Zustand's hook-based stores, selectors for performance, middleware (persist, devtools, immer), computed values, and async actions — replacing Redux complexity with a simple, un-opinionated API in under 1KB.
zoho
Integrate and automate Zoho products. Use when a user asks to work with Zoho CRM, Zoho Books, Zoho Desk, Zoho Projects, Zoho Mail, or Zoho Creator, build custom integrations via Zoho APIs, automate workflows with Deluge scripting, sync data between Zoho apps and external systems, manage leads and deals, automate invoicing, build custom Zoho Creator apps, set up webhooks, or manage Zoho organization settings. Covers Zoho CRM, Books, Desk, Projects, Creator, and cross-product integrations.
zod
You are an expert in Zod, the TypeScript-first schema declaration and validation library. You help developers define schemas that validate data at runtime AND infer TypeScript types at compile time — eliminating the need to write types and validators separately. Used for API input validation, form validation, environment variables, config files, and any data boundary.
zipkin
Deploy and configure Zipkin for distributed tracing and request flow visualization. Use when a user needs to set up trace collection, instrument Java/Spring or other services with Zipkin, analyze service dependencies, or configure storage backends for trace data.
zig
Expert guidance for Zig, the systems programming language focused on performance, safety, and readability. Helps developers write high-performance code with compile-time evaluation, seamless C interop, no hidden control flow, and no garbage collector. Zig is used for game engines, operating systems, networking, and as a C/C++ replacement.
zed
Expert guidance for Zed, the high-performance code editor built in Rust with native collaboration, AI integration, and GPU-accelerated rendering. Helps developers configure Zed, create custom extensions, set up collaborative editing sessions, and integrate AI assistants for productive coding.
zeabur
Expert guidance for Zeabur, the cloud deployment platform that auto-detects frameworks, builds and deploys applications with zero configuration, and provides managed services like databases and message queues. Helps developers deploy full-stack applications with automatic scaling and one-click marketplace services.
zapier
Automate workflows between apps with Zapier. Use when a user asks to connect apps without code, automate repetitive tasks, sync data between services, or build no-code integrations between SaaS tools.
zabbix
Configure Zabbix for enterprise infrastructure monitoring with templates, triggers, discovery rules, and dashboards. Use when a user needs to set up Zabbix server, configure host monitoring, create custom templates, define trigger expressions, or automate host discovery and registration.
yup
Validate data with Yup schemas. Use when adding form validation, defining API request schemas, validating configuration, or building type-safe validation pipelines in JavaScript/TypeScript.
yt-dlp
Download video and audio from YouTube and other platforms with yt-dlp. Use when a user asks to download YouTube videos, extract audio from videos, download playlists, get subtitles, download specific formats or qualities, batch download, archive channels, extract metadata, embed thumbnails, download from social media platforms (Twitter, Instagram, TikTok), or build media ingestion pipelines. Covers format selection, audio extraction, playlists, subtitles, metadata, and automation.