ai-system-engineer

仓库创建 2026年7月6日最近提交 22 天前SkillHot 收录 22 天前

▸ 精选理由

面向工程化落地的全栈AI系统设计与改造指南

这个 Skill 做什么

协助设计与改进AI原生系统的架构、流程与评估

帮你把散乱的 AI 原型、prompt 系统或 agent 工作流重新架构成可维护、可验证的生产级系统。遇到要设计意图、上下文管理、工具接入、评估循环、可观测性或发布就绪性时会派上用场。特点是兼顾架构与实验：既做高层流程、guardrails 和 observability，也落地 evals、反馈循环和知识工程。

▸ 展开 SKILL.md 英文原文

Use when engineering or evolving AI-native systems: shaping intent, context, agent/workflow architecture, knowledge, tools, evals, feedback loops, observability, guardrails, release readiness, or re-architecting messy AI prototypes, prompt systems, skills/plugins, agent workflows, and legacy AI apps.

开发编程系统工程代理架构观测发布就绪通用

Stars

Forks

仓库内 Skill

7 日增星

安装 / 使用

给你的 Agent 一句话（通用）

帮我安装这个 skill：https://raw.githubusercontent.com/Odinary-AI/ai-system-engineer-skill/main/skills/ai-system-engineer/SKILL.md

或 curl 直取 SKILL.md

curl -fsSL "https://raw.githubusercontent.com/Odinary-AI/ai-system-engineer-skill/main/skills/ai-system-engineer/SKILL.md"

SKILL.MD 节选查看完整文件 ↗

# AI-Native Systems Engineering

This skill supports the engineering discipline around AI-native systems. Rearchitecture is one operating mode, alongside quality evolution, domain knowledge engineering, evaluation-loop design, agent blind-spot audits, gap analysis, and release hardening.

## Overview

Use this skill to build or evolve an AI-native project into a cleaner, maintainable, validated, domain-aware, quality-improving system. This is not a normal code refactor: handle product intent, architecture, existing assets, domain knowledge, AI workflow behavior, user interaction behavior, evaluation loops, runtime package boundaries, documentation, skill boundaries, references, templates, va

via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有