Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From ai-engineer
Scaffolds AI backend services from reference templates for common shapes like simple LLM endpoints. Triggers on phrases about building LLM APIs or chat endpoints.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-engineer:ai-app-templatesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
When starting a new AI backend, check the catalog first for a matching shape.
references/simple-llm-api/README.mdreferences/simple-llm-api/app/__init__.pyreferences/simple-llm-api/app/main.pyreferences/simple-llm-api/app/providers/__init__.pyreferences/simple-llm-api/app/providers/anthropic_client.pyreferences/simple-llm-api/app/providers/gemini_client.pyreferences/simple-llm-api/app/providers/openrouter_client.pyreferences/simple-llm-api/pyproject.tomlWhen starting a new AI backend, check the catalog first for a matching shape.
| Template | Use when |
|---|---|
| simple-llm-api | Minimal FastAPI service with one POST /chat endpoint. Single prompt in, plain text out. Provider is chosen at scaffold time (Anthropic / Gemini / OpenRouter). |
→ Read references/<template>/README.md for architecture and the consumption
workflow, then copy files from references/<template>/ into the new project.
README.md (architecture, provider choice, version notes).Note: allowed-tools: Read, Glob reflects what this skill itself needs
(browse the catalog and read referenced files). The file-copy and
scaffolding steps are performed by the calling agent using its own tool
permissions — they do not need to be listed here.
ai-engineer:ai-engineering — broader AI system design and provider tradeoffs.ai-engineer:langgraph — when the shape needs to become a multi-step graph workflow.npx claudepluginhub p/hanamizuki-ai-engineer-plugins-ai-engineerCreates production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling.
Generates production-ready FastAPI projects with async patterns, dependency injection, middleware, and best practices for high-performance APIs.
Creates production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.