Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/agent-patterns-catalog
AI Agent 架构模式目录。提供 ReAct、Multi-Agent Conversation、Multi-Agent Workflow、 RAG Agent、Tool-Use Agent、Autonomous Agent 六种核心模式的参考架构、组件拓扑、 数据流、设计决策和框架无关的最佳实践。供 agent-dev-workshop Phase 2 调用。
Passed 22 of 22 test cases with the skill, and 14 of 22 without it.
and 7 more in the full report
8 fixed14 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
在按照规范查阅参考文档时，ReAct Agent 架构模式的详细设计规范对应目录下的哪一个 Markdown 文件？
| Checked | Without skill | With skill |
|---|---|---|
| The response specifies `references/react-agent.md`. | Missed | Passed |
The instructions your model reads when the skill loads.
AI Agent 架构模式目录，为 Agent 设计提供框架无关的参考架构。
agent-dev-workshop Phase 2 自动调用| 模式 | 核心思想 | 适用场景 | Reference |
|---|---|---|---|
| ReAct Agent | 思考→行动→观察循环 | 通用任务、搜索+操作 | references/react-agent.md |
| Multi-Agent Conversation | 多角色自由对话 | 辩论、评审、头脑风暴 | references/multi-agent-conversation.md |
| Multi-Agent Workflow | DAG/Pipeline 编排 | 阶段式处理、内容生产 | references/multi-agent-workflow.md |
| RAG Agent | 检索增强生成 | 知识问答、文档分析 | references/rag-agent.md |
| Tool-Use Agent | 工具调用链 | API 集成、数据处理 | references/tool-use-agent.md |
| Autonomous Agent | 自主规划+执行+反思 | 开放式任务、自主研究 | references/autonomous-agent.md |
Q1: Agent 需要自主分解复杂任务吗？
├─ Yes → Autonomous Agent
└─ No → Q2
Q2: 涉及多个不同角色协作吗？
├─ Yes → Q3
└─ No → Q4
Q3: 角色之间需要自由对话还是固定流程？
├─ 自由对话 → Multi-Agent Conversation
└─ 固定流程 → Multi-Agent Workflow
Q4: 核心能力是知识检索吗？
├─ Yes → RAG Agent
└─ No → Q5
test cases passed, vs 14 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.