OpenSkillIndex← back to search
claude-codeautomation

Claude-skill-registry ai-gateway

Build AI gateway services for routing and managing LLM requests. Use when implementing API proxies, rate limiting, or multi-provider AI services.

install
source · Clone the upstream repo
git clone https://github.com/majiayu000/claude-skill-registry
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/ai-gateway" ~/.claude/skills/majiayu000-claude-skill-registry-ai-gateway && rm -rf "$T"
manifest: skills/data/ai-gateway/SKILL.md
tags
#api-gateway#llm-routing#provider-switching#ai-integration#rate-limiting
safety · automated scan (low risk)
This is a pattern-based risk scan, not a security review. Our crawler flagged:
  • makes HTTP requests (curl)
  • references .env files
Always read a skill's source content before installing. Patterns alone don't mean the skill is malicious — but they warrant attention.
source content

AI Gateway Provider Switching Skill

Multi-provider AI configuration for Cloodle platform.

Trigger

  • AI provider configuration
  • Model switching requests
  • API key setup

Supported Providers

Local (Ollama/LM Studio)

AI_PROVIDER=ollama
OLLAMA_BASE_URL=http://localhost:11434
OLLAMA_MODEL=llama3.2

Anthropic (Sonnet/Haiku)

AI_PROVIDER=anthropic
ANTHROPIC_API_KEY=sk-ant-...
ANTHROPIC_MODEL=claude-sonnet-4-20250514

HuggingFace (GPT-OSS)

AI_PROVIDER=huggingface
HF_API_KEY=hf_...
HF_MODEL=gpt-oss-20b

Provider Switching Logic

def get_llm():
    provider = os.getenv("AI_PROVIDER", "ollama")

    if provider == "ollama":
        from langchain_ollama import ChatOllama
        return ChatOllama(
            base_url=os.getenv("OLLAMA_BASE_URL"),
            model=os.getenv("OLLAMA_MODEL", "llama3.2")
        )
    elif provider == "anthropic":
        from langchain_anthropic import ChatAnthropic
        return ChatAnthropic(
            model=os.getenv("ANTHROPIC_MODEL")
        )
    elif provider == "huggingface":
        from langchain_huggingface import HuggingFaceEndpoint
        return HuggingFaceEndpoint(
            repo_id=os.getenv("HF_MODEL")
        )

Model Recommendations

Use CaseProviderModel
DevelopmentOllamallama3.2
Production ChatAnthropicclaude-sonnet
Cost SensitiveHuggingFacegpt-oss-20b
High QualityAnthropicclaude-opus

Environment File Location

/opt/cloodle/tools/ai/multi_agent_rag_system/.env

Test Provider

curl http://localhost:11434/api/tags  # Ollama