Awesome-omni-skill switchailocal

Unified LLM proxy for AI agents. Route all model requests through http://localhost:18080/v1. Provides FREE access to Gemini CLI, Claude CLI, Codex, and Vibe via your existing subscriptions. Use when: (1) making LLM calls using provider prefixes, (2) switching between CLI/Local/Cloud providers, (3) needing to attach local files/folders to prompts via CLI, (4) requiring intelligent routing between models, or (5) needing to monitor provider health and analytics.

install

source · Clone the upstream repo

git clone https://github.com/diegosouzapw/awesome-omni-skill

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/diegosouzapw/awesome-omni-skill "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data-ai/switchailocal-majiayu000" ~/.claude/skills/diegosouzapw-awesome-omni-skill-switchailocal && rm -rf "$T"

manifest: skills/data-ai/switchailocal-majiayu000/SKILL.md

source content

switchAILocal Proxy

Unified LLM proxy for AI agents. Always use

http://localhost:18080/v1

as your base URL.

The killer feature: Use your paid CLI subscriptions (Gemini Pro, Claude Pro, etc.) via the API - it's FREE because you already pay for the subscription!

Quick Start

1. Make a request (FREE with CLI)

curl http://localhost:18080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "geminicli:",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

2. Configure Python Client

from openai import OpenAI
client = OpenAI(base_url="http://localhost:18080/v1", api_key="sk-test-123")
response = client.chat.completions.create(model="geminicli:", messages=[{"role": "user", "content": "Hi!"}])

🗺️ Skill Files

File	Description
SKILL.md (this file)	Core workflow and endpoint reference
references/routing.md	Intelligent routing and matrix setup
references/multimodal.md	Vision and image processing
references/examples.md	Real-world agentic use cases
references/management-api.md	Full Monitoring & Operations API
references/steering.md	Conditional routing rules
references/hooks.md	Automation and event hooks
references/memory.md	Analytics and history

⚠️ Critical: Model Format

NEVER use bare model names. Format is ALWAYS

provider:

provider:model

❌ Wrong	✅ Correct	Why
`gemini-2.5-pro`	`geminicli:gemini-2.5-pro`	Needs provider prefix
`claude-3-5-sonnet`	`claudecli:`	`claudecli:` uses default
`llama3`	`ollama:llama3`	Needs provider prefix

🏗️ Provider Reference

1. CLI Providers (FREE!)

Uses your human's CLI subscriptions. Best for agents.

Prefix	CLI	Subscription Required
`geminicli:`	`gemini`	Google AI Premium/Pro
`claudecli:`	`claude`	Claude Pro/Max
`codex:`	`codex`	OpenAI Plus
`vibe:`	`vibe`	Mistral Le Chat

2. Local & Cloud

Prefix	Source	Cost
`ollama:`	Local Ollama	FREE
`auto`	Local Cortex	FREE (Requires plugin)
`switchai:`	Traylinx Cloud	Per-token
`groq:`	Groq Cloud	Per-token

🚀 Core Features

CLI Attachments & Flags

Pass local context and control autonomy via CLI extensions.

{
  "model": "geminicli:",
  "messages": [{"role": "user", "content": "Fix this code"}],
  "extra_body": {
    "cli": {
      "attachments": [{"type": "folder", "path": "./src"}],
      "flags": {"auto_approve": true, "yolo": true}
    }
  }
}

Streaming

Add

"stream": true

to any request for SSE token streaming.

🌲 Decision Tree

What do you need?
├─ FREE + Powerful + Files
│   └─ CLI Providers (geminicli:, claudecli:)
├─ FREE + Private + Fast
│   └─ Local Ollama (ollama:llama3.2)
├─ Ultra-Fast Production
│   └─ Groq Cloud (groq:llama-3.3-70b)
└─ I don't know, you pick
    └─ Intelligent Routing (auto)

🛠️ Troubleshooting & Best Practices

Problem	Fix
Connection error	Check if server is running on port 18080
Model not found	Ensure you used the `provider:` prefix
401 Unauthorized	Check API key in `config.yaml`

Best Practices

Prefer CLI Providers: They are free and support file attachments.
Check Status: Use
```
GET /v1/providers
```
to see what is active.
Use
auto
: For simple tasks, let the router pick the best model.
Local for Privacy: Use
```
ollama:
```
for confidential data.

Route wisely. Save tokens. Use CLI. 🚀