international-ai-deploy

International AI Deploy - WorkBuddy skill

Feature Overview

Help users configure international AI models with one click. Users only need to provide baseurl(API endpoint),provider(provider), and api-key(API key) to automatically generate the AI model configuration file.

Trigger Keywords

Use this skill when the user says the following:

• "Add GPT model"
• "Configure Claude API"
• "Deploy international AI model"
• "Add custom model"
• "Configure model proxy"
• "I want to use GPT"
• "Add OpenAI"
• "Configure Anthropic"

Usage Flow

Step 1: Collect user configuration information

Collect the following information from the user:

Parameter	Description	Example
baseurl	API endpoint address	https://api.openai.com/v1
provider	Model provider	openai, anthropic, google, custom
api-key	API key	sk-xxxxxx
model-name	Model name (optional)	gpt-4o, claude-3-opus

Step 2: Generate configuration

Generate the corresponding configuration based on the provider type provided by the user:

OpenAI configuration:

{
  "models": [{
    "id": "openai/gpt-4o",
    "name": "GPT-4o",
    "vendor": "OpenAI",
    "apiKey": "${api-key}",
    "url": "https://api.openai.com/v1/chat/completions",
    "maxInputTokens": 128000,
    "maxOutputTokens": 4096
  }]
}

Anthropic configuration:

{
  "models": [{
    "id": "anthropic/claude-3-sonnet",
    "name": "Claude 3 Sonnet",
    "vendor": "Anthropic",
    "apiKey": "${api-key}",
    "url": "https://api.anthropic.com/v1/messages",
    "maxInputTokens": 200000,
    "maxOutputTokens": 4096
  }]
}

Google configuration:

{
  "models": [{
    "id": "google/gemini-1.5-pro",
    "name": "Gemini 1.5 Pro",
    "vendor": "Google",
    "apiKey": "${api-key}",
    "url": "https://generativelanguage.googleapis.com/v1/models/gemini-1.5-pro:generateContent",
    "maxInputTokens": 1000000,
    "maxOutputTokens": 8192
  }]
}

Custom configuration:

{
  "models": [{
    "id": "custom/${model-name}",
    "name": "${model-display-name}",
    "vendor": "${provider}",
    "apiKey": "${api-key}",
    "url": "${baseurl}/chat/completions",
    "maxInputTokens": 128000,
    "maxOutputTokens": 4096
  }]
}

Supported Models

OpenAI (GPT series)

• Endpoint: https://api.openai.com/v1
• Supported models: gpt-4o, gpt-4-turbo, gpt-3.5-turbo

Anthropic (Claude series)

• Endpoint: https://api.anthropic.com/v1/messages
• Supported models: claude-3-opus, claude-3-sonnet, claude-3-haiku

Google (Gemini series)

• Endpoint: https://generativelanguage.googleapis.com/v1
• Supported models: gemini-1.5-pro, gemini-1.5-flash

Custom/proxy service

• SiliconFlow: https://api.siliconflow.cn/v1
• OpenRouter: https://openrouter.ai/api/v1
• Any service compatible with the OpenAI API

Configuration Save Location

• Project directory: .codebuddy/models.json
• User directory: ~/.config/codebuddy/models.json

Example Conversation

User: I want to add GPT-4o Skill: Please provide your OpenAI API key

User: sk-xxxxxx Skill: ✅ Successfully configured GPT-4o! The configuration has been saved to .codebuddy/models.json

---

Version: 1.0.0
Author: hangtiger
License: MIT