qclaw-openclaw-desktop
```markdown
What this skill does
```markdown
---
name: qclaw-openclaw-desktop
description: GUI desktop client for OpenClaw — lets non-technical users run and configure OpenClaw AI gateway without the command line
triggers:
- set up Qclaw desktop app
- configure OpenClaw with GUI
- add IM channel to Qclaw
- develop Qclaw electron app
- build Qclaw from source
- connect feishu dingtalk to OpenClaw
- manage OpenClaw models in Qclaw
- Qclaw skill plugin management
---
# Qclaw OpenClaw Desktop
> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection.
Qclaw is an Electron-based desktop GUI for [OpenClaw](https://github.com/openclaw/openclaw), a self-hosted AI gateway. It removes the need for CLI configuration by providing visual wizards for model setup, IM channel integration (Feishu, DingTalk, QQ, WeCom), skill management, and gateway monitoring.
## What Qclaw Does
- **Environment auto-check** — detects and installs Node.js and OpenClaw CLI automatically
- **Model management** — configure any OpenClaw-supported model with OAuth or API key
- **IM integration** — scan QR codes to connect Feishu, DingTalk, QQ, WeCom, WeChat
- **Gateway dashboard** — real-time status, one-click restart/repair
- **Skills management** — install and manage OpenClaw skill plugins
- **Backup/restore** — auto and manual config backups
- **Auto-update** — keeps OpenClaw CLI up to date
## Installation (End Users)
Download from:
- **Official site**: https://qclawai.com/
- **GitHub Releases**: https://github.com/qiuzhi2046/Qclaw/releases
Supported platforms:
- macOS 11 (Big Sur)+
- Windows 10+ x64 (in development)
- Linux (planned)
## Development Setup
### Prerequisites
- Node.js 22+ (Node.js 24 recommended)
- macOS (primary dev platform)
- Git
### Clone and Run
```bash
git clone https://github.com/qiuzhi2046/Qclaw.git
cd Qclaw
npm install
# Start dev server (Electron + Vite hot reload)
npm run dev
# Type check
npm run typecheck
# Run tests
npm test
# Build production app
npm run build
```
### Key npm Scripts
| Command | Description |
|---|---|
| `npm run dev` | Start Electron dev server with HMR |
| `npm run build` | Build and package app with electron-builder |
| `npm test` | Run test suite |
| `npm run typecheck` | TypeScript type checking |
## Project Structure
```
electron/
main/ # Main process: window, CLI calls, IPC handlers
preload/ # Preload scripts (secure IPC bridge)
src/
pages/ # React pages: wizard steps, Dashboard, Chat
components/ # Shared UI components
lib/ # Business logic: channel/provider registration
shared/ # Config workflows, gateway diagnostics
assets/ # Icons and static assets
docs/ # Architecture docs, changelogs
scripts/ # Build, signing, notarization, versioning, COS release
build/ # App icons and packaging resources
```
## Tech Stack
| Layer | Technology |
|---|---|
| Desktop | Electron |
| Frontend | React + TypeScript |
| Build | Vite + vite-plugin-electron |
| UI | Mantine + Tailwind CSS |
| Packaging | electron-builder |
## Architecture Overview
```
┌─────────────────────────────────────────────┐
│ Qclaw │
│ │
│ Main Process (Node.js) ◄─IPC─► Renderer │
│ ┌──────────────────┐ (React) │
│ │ cli.ts │ │
│ │ OpenClaw CLI │ Wizard pages │
│ │ invocation │ Dashboard │
│ ├──────────────────┤ Chat UI │
│ │ File I/O │ │
│ │ Process mgmt │ │
│ │ System integration│ │
│ └────────┬─────────┘ │
│ │ │
│ ▼ │
│ OpenClaw CLI (~/.openclaw/) │
└─────────────────────────────────────────────┘
```
## IPC Communication Pattern
Qclaw uses Electron's contextBridge for secure main ↔ renderer communication.
### Preload Bridge (electron/preload/index.ts)
```typescript
import { contextBridge, ipcRenderer } from 'electron'
contextBridge.exposeInMainWorld('electronAPI', {
// Invoke main process handlers
invoke: (channel: string, ...args: unknown[]) =>
ipcRenderer.invoke(channel, ...args),
// Subscribe to events from main
on: (channel: string, callback: (...args: unknown[]) => void) => {
ipcRenderer.on(channel, (_event, ...args) => callback(...args))
},
// Remove listeners
removeAllListeners: (channel: string) => {
ipcRenderer.removeAllListeners(channel)
},
})
```
### Main Process IPC Handler (electron/main/index.ts)
```typescript
import { ipcMain } from 'electron'
import { runOpenClawCli } from './cli'
// Handle CLI invocation from renderer
ipcMain.handle('openclaw:start', async (_event, config) => {
try {
const result = await runOpenClawCli(['start', '--config', config])
return { success: true, output: result }
} catch (error) {
return { success: false, error: (error as Error).message }
}
})
ipcMain.handle('openclaw:status', async () => {
return await runOpenClawCli(['status'])
})
ipcMain.handle('openclaw:restart', async () => {
return await runOpenClawCli(['restart'])
})
```
### Renderer Usage
```typescript
// src/pages/Dashboard.tsx
const handleRestart = async () => {
const result = await window.electronAPI.invoke('openclaw:restart')
if (result.success) {
notifications.show({ message: 'Gateway restarted', color: 'green' })
}
}
```
## Adding a New IM Channel
Channels are registered in `src/lib/` following a provider pattern.
```typescript
// src/lib/channels/myChannel.ts
import type { IMChannel } from '../types'
export const myChannel: IMChannel = {
id: 'my-channel',
name: 'My Platform',
icon: '/assets/my-channel-icon.png',
pluginPackage: '@openclaw/plugin-my-channel',
// Fields shown in the setup wizard
configFields: [
{
key: 'appId',
label: 'App ID',
type: 'text',
required: true,
placeholder: 'Enter your App ID',
},
{
key: 'appSecret',
label: 'App Secret',
type: 'password',
required: true,
placeholder: 'Enter your App Secret',
},
],
// Called when user saves the channel config
async install(config: Record<string, string>) {
// Install plugin via CLI
await window.electronAPI.invoke('openclaw:install-plugin', this.pluginPackage)
// Write config
await window.electronAPI.invoke('openclaw:write-channel-config', {
channel: this.id,
config,
})
},
}
```
Register it in `src/lib/channels/index.ts`:
```typescript
import { myChannel } from './myChannel'
export const channels = [
feishuChannel,
dingtalkChannel,
qqChannel,
wecomChannel,
myChannel, // add here
]
```
## Adding a New AI Provider/Model
```typescript
// src/lib/providers/myProvider.ts
import type { AIProvider } from '../types'
export const myProvider: AIProvider = {
id: 'my-provider',
name: 'My AI Provider',
authType: 'api-key', // or 'oauth'
models: [
{ id: 'my-model-v1', name: 'My Model V1', contextLength: 128000 },
{ id: 'my-model-v2', name: 'My Model V2', contextLength: 200000 },
],
configFields: [
{
key: 'apiKey',
label: 'API Key',
type: 'password',
required: true,
envVar: 'MY_PROVIDER_API_KEY', // shown as hint to user
},
{
key: 'baseUrl',
label: 'Base URL',
type: 'text',
required: false,
defaultValue: 'https://api.myprovider.com',
},
],
}
```
## Gateway Diagnostics (src/shared/)
```typescript
// src/shared/gatewayDiagnostics.ts
import { ipcRenderer } from 'electron'
export async function diagnoseGateway(): Promise<DiagnosticResult> {
const checks = await Promise.allSettled([
checkNodeVersion(),
checkOpenClawInstalled(),
checkConfigFile(),
checkGatewayProcess(),
])
return {
nodeOk: checks[0].status =Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.