ai-engineer

SKILL.md

Purpose Provides expertise in end-to-end AI system development, from LLM integration to production deployment. Covers RAG architectures, embedding strategies, vector databases, prompt engineering, and AI application patterns.

| Prompt in code | Hard to iterate and test | Use prompt templates with versioning | | No evaluation | Unknown quality in production | Implement eval pipelines | | Synchronous LLM calls | Slow user experience | Use streaming responses | | Unbounded context | Token limits and cost | Implement context windowing |

| No fallbacks | System fails on API errors | Add retry logic and alternatives |

构建综合人工智能系统、将法学硕士、RAG 架构和自主代理集成到生产应用程序中的专家。在构建 AI 支持的功能、实施 LLM 集成、设计 RAG 管道或部署 AI 系统时使用。 来源：404kidwiz/claude-supercode-skills。

查看原文