Back to Details

mlflow-agent

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

MLflow Agent

MLflow Agent

Master dispatcher for MLflow workflows. Reads user intent and invokes the right sub-skill.

MLflow工作流的主调度器，读取用户意图并调用对应的子技能。

Trigger

触发条件

Use when the user wants to do anything with MLflow but hasn't specified which skill to use.

当用户想要执行任何与MLflow相关的操作，但未指定使用哪个技能时使用。

Process

处理流程

Read the user's request and identify intent
Map to the appropriate skill:
- Tracing / instrumentation →
```
instrumenting-with-mlflow-tracing
```
- Evaluation / scoring →
```
agent-evaluation
```
- Debug a trace →
```
analyze-mlflow-trace
```
- Debug a chat session →
```
analyze-mlflow-chat-session
```
- Search traces →
```
retrieving-mlflow-traces
```
- Metrics / costs →
```
querying-mlflow-metrics
```
- Getting started →
```
mlflow-onboarding
```
- Docs / API questions →
```
searching-mlflow-docs
```
If intent is unclear, ask ONE clarifying question, then dispatch
Invoke the matched skill using the Skill tool

读取用户请求并识别意图

匹配到对应的技能：

追踪/埋点 →
```
instrumenting-with-mlflow-tracing
```
评估/打分 →
```
agent-evaluation
```
调试追踪记录 →
```
analyze-mlflow-trace
```
调试聊天会话 →
```
analyze-mlflow-chat-session
```
搜索追踪记录 →
```
retrieving-mlflow-traces
```
指标/成本 →
```
querying-mlflow-metrics
```
入门使用 →
```
mlflow-onboarding
```
文档/API问题 →
```
searching-mlflow-docs
```

如果意图不明确，最多提出1个澄清问题，之后再进行调度
使用Skill工具调用匹配到的技能

Key Rules

核心规则

Never do the work yourself — always dispatch to the appropriate sub-skill
One clarifying question maximum before dispatching
If the user says "evaluate AND trace", dispatch tracing first, then evaluation
If the user's request spans multiple skills, handle them in logical order (setup → instrument → evaluate)

不要自行处理任务，始终调度到对应的子技能
调度前最多提出1个澄清问题
如果用户要求"评估且追踪"，先调度追踪，再调度评估
如果用户请求涉及多个技能，按逻辑顺序处理（设置→埋点→评估）