Skills

Extend your AI coding assistant with Atlas Cloud Skills for intelligent API integration

What are Skills?

Skills are reusable knowledge packages that extend AI coding assistants with specialized domain knowledge, API references, and code templates. By installing the Atlas Cloud skill, your AI assistant gains deep understanding of the Atlas Cloud API — enabling it to help you generate images, create videos, chat with LLMs, and more through natural language.

Atlas Cloud Skills currently support Claude Code and can be adapted for other AI coding tools that support similar skill/knowledge systems.

What's Included

The official Atlas Cloud Skills package provides:

Complete API reference documentation for all Atlas Cloud endpoints
Code templates in Python, Node.js/TypeScript, and cURL
Popular model identifiers with pricing information
OpenAI SDK compatibility guidance for LLM models
MCP tool descriptions and usage patterns
Error handling and best practice recommendations

GitHub Repository: AtlasCloudAI/atlas-cloud-skills

Installation

Quick Install (Recommended)

npx skills add AtlasCloudAI/atlas-cloud-skills

Shell Script

curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/atlas-cloud-skills/main/install.sh | sh

Manual Installation

Copy the atlas-cloud/ directory to your skill storage location. For Claude Code, this is ~/.claude/skills/atlas-cloud/.

Setup

Set your Atlas Cloud API key as an environment variable:

export ATLASCLOUD_API_KEY="your-api-key"

To persist across terminal sessions, add this to your shell profile (~/.bashrc, ~/.zshrc, etc.).

Get your API key from the Atlas Cloud Console.

Usage Examples

Once installed, you can use natural language to interact with Atlas Cloud:

Image Generation

"Generate an image of a futuristic city skyline at sunset using Seedream"

Video Generation

"Create a 5-second video of ocean waves crashing on rocks using Kling v3"

LLM Chat

"Ask DeepSeek V3 to review this code for security issues"

Model Discovery

"What image generation models are available on Atlas Cloud?"

"Show me the pricing for Kling video models"

Media Upload

"Upload this image to Atlas Cloud and use it for an image-to-video generation"

Supported Capabilities

Capability	Endpoint	Example Models
Image Generation	`POST /api/v1/model/generateImage`	Seedream v5.0, FLUX, Qwen-Image
Video Generation	`POST /api/v1/model/generateVideo`	Kling v3.0, Seedance v1.5, Vidu
LLM Chat	`POST /v1/chat/completions`	DeepSeek V3, Qwen, Kimi, GLM
Media Upload	`POST /api/v1/model/uploadMedia`	File upload utility
Model Search	Fuzzy keyword matching	Discover by name/type/provider

Skills vs MCP Server

Both Skills and the MCP Server bring Atlas Cloud into your development environment, but they work differently:

Feature	Skills	MCP Server
Works with	Claude Code (and compatible tools)	Cursor, Claude Desktop, VS Code, Claude Code, and 10+ more
How it works	Provides knowledge and code templates	Provides executable tools via MCP protocol
Setup	One command install	JSON config per IDE
Best for	Code generation guidance	Direct API interaction from any IDE

Recommendation: Install both for the best experience. The MCP Server provides direct tool execution, while Skills give your AI assistant deeper API knowledge for writing integration code.

For MCP Server setup, see the MCP Server guide.

On This Page