ai-ml

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

AI/ML Workflow Bundle

AI/ML工作流合集

Overview

概述

Comprehensive AI/ML workflow for building LLM applications, implementing RAG systems, creating AI agents, and developing machine learning pipelines. This bundle orchestrates skills for production AI development.

用于构建LLM应用、实现RAG系统、创建AI Agent以及开发机器学习流水线的综合性AI/ML工作流。该合集编排了生产级AI开发所需的各项技能。

When to Use This Workflow

何时使用此工作流

Use this workflow when:

Building LLM-powered applications
Implementing RAG (Retrieval-Augmented Generation)
Creating AI agents
Developing ML pipelines
Adding AI features to applications
Setting up AI observability

在以下场景使用此工作流：

构建基于LLM的应用
实现RAG（检索增强生成）
创建AI Agent
开发ML流水线
为应用添加AI功能
搭建AI可观测性体系

Workflow Phases

工作流阶段

Phase 1: AI Application Design

阶段1：AI应用设计

Skills to Invoke

需调用的技能

```
ai-product
```
- AI product development
```
ai-engineer
```
- AI engineering
```
ai-agents-architect
```
- Agent architecture
```
llm-app-patterns
```
- LLM patterns

```
ai-product
```
- AI产品开发
```
ai-engineer
```
- AI工程
```
ai-agents-architect
```
- Agent架构设计
```
llm-app-patterns
```
- LLM应用模式

Actions

操作步骤

Define AI use cases
Choose appropriate models
Design system architecture
Plan data flows
Define success metrics

定义AI用例
选择合适的模型
设计系统架构
规划数据流
定义成功指标

Copy-Paste Prompts

可复制粘贴的提示词

Use @ai-product to design AI-powered features

Use @ai-agents-architect to design multi-agent system

Use @ai-product to design AI-powered features

Use @ai-agents-architect to design multi-agent system

Phase 2: LLM Integration

阶段2：LLM集成

Skills to Invoke

需调用的技能

```
llm-application-dev-ai-assistant
```
- AI assistant development
```
llm-application-dev-langchain-agent
```
- LangChain agents
```
llm-application-dev-prompt-optimize
```
- Prompt engineering
```
gemini-api-dev
```
- Gemini API

```
llm-application-dev-ai-assistant
```
- AI助手开发
```
llm-application-dev-langchain-agent
```
- LangChain Agent
```
llm-application-dev-prompt-optimize
```
- 提示词工程
```
gemini-api-dev
```
- Gemini API开发

Actions

操作步骤

Select LLM provider
Set up API access
Implement prompt templates
Configure model parameters
Add streaming support
Implement error handling

选择LLM提供商
配置API访问权限
实现提示词模板
配置模型参数
添加流式支持
实现错误处理

Copy-Paste Prompts

可复制粘贴的提示词

Use @llm-application-dev-ai-assistant to build conversational AI

Use @llm-application-dev-langchain-agent to create LangChain agents

Use @llm-application-dev-prompt-optimize to optimize prompts

Use @llm-application-dev-ai-assistant to build conversational AI

Use @llm-application-dev-langchain-agent to create LangChain agents

Use @llm-application-dev-prompt-optimize to optimize prompts

Phase 3: RAG Implementation

阶段3：RAG实现

Skills to Invoke

需调用的技能

```
rag-engineer
```
- RAG engineering
```
rag-implementation
```
- RAG implementation
```
embedding-strategies
```
- Embedding selection
```
vector-database-engineer
```
- Vector databases
```
similarity-search-patterns
```
- Similarity search
```
hybrid-search-implementation
```
- Hybrid search

```
rag-engineer
```
- RAG工程
```
rag-implementation
```
- RAG实现
```
embedding-strategies
```
- 嵌入策略选择
```
vector-database-engineer
```
- 向量数据库
```
similarity-search-patterns
```
- 相似度搜索
```
hybrid-search-implementation
```
- 混合搜索实现

Actions

操作步骤

Design data pipeline
Choose embedding model
Set up vector database
Implement chunking strategy
Configure retrieval
Add reranking
Implement caching

设计数据流水线
选择嵌入模型
搭建向量数据库
实现分块策略
配置检索逻辑
添加重排序机制
实现缓存功能

Copy-Paste Prompts

可复制粘贴的提示词

Use @rag-engineer to design RAG pipeline

Use @vector-database-engineer to set up vector search

Use @embedding-strategies to select optimal embeddings

Use @rag-engineer to design RAG pipeline

Use @vector-database-engineer to set up vector search

Use @embedding-strategies to select optimal embeddings

Phase 4: AI Agent Development

阶段4：AI Agent开发

Skills to Invoke

需调用的技能

```
autonomous-agents
```
- Autonomous agent patterns
```
autonomous-agent-patterns
```
- Agent patterns
```
crewai
```
- CrewAI framework
```
langgraph
```
- LangGraph
```
multi-agent-patterns
```
- Multi-agent systems
```
computer-use-agents
```
- Computer use agents

```
autonomous-agents
```
- 自主Agent模式
```
autonomous-agent-patterns
```
- Agent模式
```
crewai
```
- CrewAI框架
```
langgraph
```
- LangGraph
```
multi-agent-patterns
```
- 多Agent系统
```
computer-use-agents
```
- 计算机操作Agent

Actions

操作步骤

Design agent architecture
Define agent roles
Implement tool integration
Set up memory systems
Configure orchestration
Add human-in-the-loop

设计Agent架构
定义Agent角色
实现工具集成
搭建记忆系统
配置编排逻辑
添加人在环机制

Copy-Paste Prompts

可复制粘贴的提示词

Use @crewai to build role-based multi-agent system

Use @langgraph to create stateful AI workflows

Use @autonomous-agents to design autonomous agent

Use @crewai to build role-based multi-agent system

Use @langgraph to create stateful AI workflows

Use @autonomous-agents to design autonomous agent

Phase 5: ML Pipeline Development

阶段5：ML流水线开发

Skills to Invoke

需调用的技能

```
ml-engineer
```
- ML engineering
```
mlops-engineer
```
- MLOps
```
machine-learning-ops-ml-pipeline
```
- ML pipelines
```
ml-pipeline-workflow
```
- ML workflows
```
data-engineer
```
- Data engineering

```
ml-engineer
```
- ML工程
```
mlops-engineer
```
- MLOps
```
machine-learning-ops-ml-pipeline
```
- ML流水线
```
ml-pipeline-workflow
```
- ML工作流
```
data-engineer
```
- 数据工程

Actions

操作步骤

Design ML pipeline
Set up data processing
Implement model training
Configure evaluation
Set up model registry
Deploy models

设计ML流水线
搭建数据处理流程
实现模型训练
配置评估机制
搭建模型仓库
部署模型

Copy-Paste Prompts

可复制粘贴的提示词

Use @ml-engineer to build machine learning pipeline

Use @mlops-engineer to set up MLOps infrastructure

Use @ml-engineer to build machine learning pipeline

Use @mlops-engineer to set up MLOps infrastructure

Phase 6: AI Observability

阶段6：AI可观测性

Skills to Invoke

需调用的技能

```
langfuse
```
- Langfuse observability
```
manifest
```
- Manifest telemetry
```
evaluation
```
- AI evaluation
```
llm-evaluation
```
- LLM evaluation

```
langfuse
```
- Langfuse可观测性
```
manifest
```
- Manifest遥测
```
evaluation
```
- AI评估
```
llm-evaluation
```
- LLM评估

Actions

操作步骤

Set up tracing
Configure logging
Implement evaluation
Monitor performance
Track costs
Set up alerts

搭建追踪系统
配置日志记录
实现评估逻辑
监控性能指标
追踪成本开销
配置告警机制

Copy-Paste Prompts

可复制粘贴的提示词

Use @langfuse to set up LLM observability

Use @evaluation to create evaluation framework

Use @langfuse to set up LLM observability

Use @evaluation to create evaluation framework

Phase 7: AI Security

阶段7：AI安全

Skills to Invoke

需调用的技能

```
prompt-engineering
```
- Prompt security
```
security-scanning-security-sast
```
- Security scanning

```
prompt-engineering
```
- 提示词安全
```
security-scanning-security-sast
```
- 安全扫描

Actions

操作步骤

Implement input validation
Add output filtering
Configure rate limiting
Set up access controls
Monitor for abuse
Implement audit logging

实现输入验证
添加输出过滤
配置速率限制
搭建访问控制
监控滥用行为
实现审计日志

ai-ml

Original

Translation

AI/ML Workflow Bundle

AI/ML工作流合集

Overview

概述

When to Use This Workflow

何时使用此工作流

Workflow Phases

工作流阶段

Phase 1: AI Application Design

阶段1：AI应用设计

Skills to Invoke

需调用的技能

Actions

操作步骤

Copy-Paste Prompts

可复制粘贴的提示词

Phase 2: LLM Integration

阶段2：LLM集成

Skills to Invoke

需调用的技能

Actions

操作步骤

Copy-Paste Prompts

可复制粘贴的提示词

Phase 3: RAG Implementation

阶段3：RAG实现

Skills to Invoke

需调用的技能

Actions

操作步骤

Copy-Paste Prompts

可复制粘贴的提示词

Phase 4: AI Agent Development

阶段4：AI Agent开发

Skills to Invoke

需调用的技能

Actions

操作步骤

Copy-Paste Prompts

可复制粘贴的提示词

Phase 5: ML Pipeline Development

阶段5：ML流水线开发

Skills to Invoke

需调用的技能

Actions

操作步骤

Copy-Paste Prompts

可复制粘贴的提示词

Phase 6: AI Observability

阶段6：AI可观测性

Skills to Invoke

需调用的技能

Actions

操作步骤

Copy-Paste Prompts

可复制粘贴的提示词

Phase 7: AI Security

阶段7：AI安全

Skills to Invoke

需调用的技能

Actions

操作步骤

AI Development Checklist

AI开发检查清单

LLM Integration

LLM集成

RAG System

RAG系统

AI Agents

AI Agent

Observability

可观测性

Quality Gates

质量门禁

Related Workflow Bundles

相关工作流合集