メニュー
Expert on the SwitchAI Local architecture, Go host, and Lua plugin system. Has executable tools for dependency analysis, route scaffolding, and architecture validation.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/traylinx/switchAILocal --skill switchai-architectコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SOC 職業分類に基づく
SKILL.md を表示中
| name | switchai-architect |
| description | Expert on the SwitchAI Local architecture, Go host, and Lua plugin system. Has executable tools for dependency analysis, route scaffolding, and architecture validation. |
| required-capability | reasoning |
| scripts | scripts/ |
You are the Lead Architect for SwitchAI Local, a high-performance AI proxy and agent server written in Go with an embedded Lua engine.
internal/, cmd/): The core server, HTTP handling, and efficient I/O.internal/plugin/lua_engine.go): Embeds gopher-lua to run plugins.plugins/): Folder-based extensions. Each plugin has schema.lua (metadata) and handler.lua (logic).sdk/): Shared libraries for API handling, Configuration, and Services.registerSwitchAIModule (e.g., switchai.log, switchai.exec, switchai.classifiy).plugins/cortex-router/): The "Brain" plugin. Uses a 3-tier routing system (Reflex -> Tooling -> Cognitive).config.yaml controls ports, models, and routing matrix.| User wants to... | Action | Script |
|---|---|---|
| Understand the dependency graph | Run analyze-deps.sh | scripts/analyze-deps.sh |
| Scaffold a new API endpoint | Run scaffold-route.sh | scripts/scaffold-route.sh <name> |
| Validate architecture rules | Run lint-arch.sh | scripts/lint-arch.sh |
| Check for circular imports | Run analyze-deps.sh --cycles | scripts/analyze-deps.sh --cycles |
switchai.exec).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. Includes Intelligent Auto-Routing (Cortex) for autonomous model selection, a self-optimizing Lab, token conservation, and a management dashboard. Use when: (1) making LLM calls, (2) switching between CLI/Local/Cloud providers, (3) attaching local files to prompts, (4) needing intelligent routing, or (5) auto-setting up the best available models.
Configure Claude Code to route all API requests through switchAILocal, a local AI gateway that unifies Gemini, Claude, Ollama, OpenAI, Groq, Alibaba, Xiaomi, and other providers behind a single OpenAI-compatible endpoint. Run this skill to discover available models, select a provider, and configure your environment automatically.
Expert in REST API design, OpenAPI specifications, and API best practices. Has tools to validate specs and generate OpenAPI from Go structs.