Updated 3d ago
by geniusjia666
agent-system-design-cn
单 Agent / 多 Agent 系统设计 Skill:7 步设计流程、交接契约、21 种模式与 21 维自检,产出可评审的架构方案。完整中文版。
53 GitHub stars (53)
+53 in 3 days
| Period | New stars |
|---|---|
| Nov 13 | +11 |
- 1 skill (1 skills found in its SKILL.md files)
- 0 forks (0 forks)
- 3d ago last update (Last updated 3d ago)
Install
Skills CLI
npx skills add geniusjia666/agent-system-design-cn
Asks which agents to install it for. Add -g to install it for every project.
Claude Code
git clone https://github.com/geniusjia666/agent-system-design-cncp -r "agent-system-design-cn/skills/agent-system-design-cn" ~/.claude/skills/
Copies the agent-system-design-cn skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project).
Plugin
/plugin marketplace add geniusjia666/agent-system-design-cn
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
agent-system-design-cn
单 Agent 与多 Agent 系统设计方法(中文)。从需求出发判断是否需要 Agent、选择架构档位(提示词、工作流、单 Agent、多 Agent),完成角色、任务契约、工具、上下文与记忆、编排模式、Agent 间交接、人类介入、可靠性与安全、评测的设计,产出结构固定的设计文档并按 21 个维度自检评分。融合 21 种 Agentic 设计模式。当用户需要:(1) 从零设计 Agent 或多智能体系统、智能体工作流、Agent 流水线;(2) 选择或组合设计模式(提示链、路由、并行、反思、编排者-工作者、规划等);(3) 设计 Agent 之间如何交接数据、拆分角色;(4) 评审、诊断、打分已有 Agent 设计;(5) 设计现有 LLM 应用的必要演进方案时使用。不负责运行时编排、业务代码重构、仓库 Harness 化、部署或发布。
skills/agent-system-design-cn/ on GitHub (opens in a new tab)SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.