@skillmaster/sdk

Node.js SDK for SkillMaster API - AI-powered image/video generation, media analysis, document processing, and more.

Installation

npm install @skillmaster/sdk

Quick Start

import { SkillMasterClient } from '@skillmaster/sdk';

// Reads SKILLMASTER_API_KEY from environment variable
const client = new SkillMasterClient();

// Or with explicit config
const client = new SkillMasterClient({
  apiKey: 'your-api-key',
  baseUrl: 'https://skillmaster.fieldshortcut.com',
  taskDir: './tasks',
  timeout: 900000 // 15 minutes
});

// Generate image
const imageResult = await client.image.jimeng({
  prompt: 'A beautiful sunset over mountains',
  size: '2048x2048'
});

// Generate image with GPT Image
const gptImageResult = await client.image.gpt({
  prompt: 'A clean ecommerce product photo',
  aspect_ratio: '1:1',
  size: '2K'
});

// Generate video (Kling)
const videoResult = await client.video.kling({
  prompt: 'A cat playing piano',
  model: 'kling-v2-6',
  aspect_ratio: '16:9',
  duration: '5'
});

// Generate video (Wan 3.0)
const wan3Result = await client.video.wan3({
  action: 'reference',
  prompt: 'A cinematic city flythrough',
  resolution: '1080P',
  ratio: 'adaptive',
  duration: '5'
});

// Translate document (local file will be auto-uploaded to get tmp_url)
const docResult = await client.document.translate({
  attachment: [{ path: './files/doc.pdf' }],
  source_language: { value: 'en', label: 'English' },
  target_language: { value: 'zh', label: 'Chinese' }
});

// Analyze media
const mediaResult = await client.media.analyze({
  url: [{ link: 'https://youtube.com/watch?v=...' }]
});

// Video shot analysis
const shotAnalysisResult = await client.media.videoAnalysis({
  attachment: [{ path: './video.mp4' }],
  prompt: '拆解镜头、景别、节奏和叙事结构'
});

Configuration

Environment Variables

• SKILLMASTER_API_KEY - Your SkillMaster API key
• SKILLMASTER_BASE_URL - API base URL (optional, defaults to https://skillmaster.fieldshortcut.com)

CLI Configuration

Use the CLI to persist configuration:

# Install globally
npm install -g @skillmaster/sdk

# Set API key (stored in ~/.skillmaster/config.json)
skillmaster-sdk config set apiKey your-api-key

# Set custom base URL
skillmaster-sdk config set baseUrl https://custom.example.com

# View current configuration
skillmaster-sdk config

# Get a specific value
skillmaster-sdk config get apiKey

Configuration Priority

1. Constructor parameters (highest priority)
2. Environment variables
3. Config file (~/.skillmaster/config.json)
4. Default values (lowest priority)

Task Folders

Each SDK execution creates a task folder with:

• logs/request.json - Request details
• logs/response.json - API response
• logs/execution.log - Execution log
• attachments/ - Downloaded attachments (to avoid link expiration)

Default Task Directory

Tasks are stored in ~/Documents/tasks/ by default. You can override this:

const client = new UnityClawClient({
  taskDir: '/path/to/custom/tasks'
});

API Reference

Image Generation

// JiMeng
await client.image.jimeng({
  prompt: 'A sunset over mountains',
  size: '2048x2048'
});

// JiMeng (Doubao)
await client.image.jimeng({
  prompt: 'A futuristic city',
  model: 'v6.0'
});

// GPT Image
await client.image.gpt({
  prompt: 'A premium product render',
  aspect_ratio: '1:1',
  size: '2K',
  output_format: 'png'
});

// GPT Image Stable
await client.image.gptStable({
  prompt: 'A crisp campaign visual',
  aspect_ratio: '16:9',
  quality: 'low',
  output_format: 'webp'
});

Video Generation

// Kling
await client.video.kling({
  prompt: 'A dancing robot',
  model: 'kling-v1-5'
});

// Wan 2.x
await client.video.wan({
  prompt: 'A samurai in snowfall',
  model: 'wan2.5-t2v',
  size: '1280*720',
  duration: '5'
});

// Wan 3.0
await client.video.wan3({
  action: 'reference',
  prompt: 'A model walking through a neon street',
  resolution: '1080P',
  ratio: 'adaptive',
  duration: '5'
});

// Seedance 2.0 Mini
await client.video.seedance2Mini({
  prompt: 'A playful product animation',
  resolution: '720p',
  ratio: '16:9'
});

// Seedance 2.5
await client.video.seedance25({
  prompt: 'A longer travel montage',
  resolution: '720p',
  ratio: '21:9',
  duration: '30'
});

Document Processing

// Translate document
await client.document.translate({
  attachment: [{ tmp_url: 'https://...', name: 'doc.pdf' }],
  source_language: { value: 'en', label: 'English' },
  target_language: { value: 'zh', label: 'Chinese' }
});

// Convert document
await client.document.convert({
  attachment: [{ path: './files/doc.pdf' }],
  input_format: 'pdf',
  output_format: 'docx'
});

Media Analysis

const result = await client.media.analyze({
  url: [{ link: 'https://youtube.com/watch?v=...' }]
});

console.log(result.response.data?.summary);
console.log(result.response.data?.subtitle);

// Multi-language local media analysis
await client.media.analyzeLangs({
  attachments: [{ path: './meeting.mp4' }]
});

// Video shot analysis
await client.media.videoAnalysis({
  attachment: [{ path: './scene.mp4' }],
  prompt: '拆解镜头、景别、声音、节奏和转场'
});

Text

await client.text.gemini3({
  prompt: 'Summarize this file',
  attachment: [{ path: './brief.pdf' }]
});

License

MIT