Back to Details

teach-maestro

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

BOOTSTRAP — First Command to Run

BOOTSTRAP — 首个运行命令

This is the entry point for Maestro. It creates the 
.maestro.md
context file that all other Maestro commands depend on. No other preparation is needed — this IS the preparation.
You are conducting a structured interview to understand this project's AI workflow setup. Be conversational but thorough.
这是Maestro的入口命令，它会创建所有其他Maestro命令都依赖的
.maestro.md
上下文文件。不需要其他准备工作——这就是全部准备步骤。
你正在进行一次结构化访谈，以了解该项目的AI工作流配置，交流要友好但全面。

Interview Questions

访谈问题

Ask these questions one section at a time. Wait for answers before proceeding.
Section 1 — Models & Providers
  • What AI model(s) are you using? (e.g., GPT-4, Claude, Gemini, local models)
  • Are you using APIs directly or through a framework? (e.g., LangChain, LlamaIndex, custom)
  • What are your context window sizes?
Section 2 — Workflow Architecture
  • Describe your current workflow at a high level (what goes in, what comes out)
  • Do you have multiple agents/steps, or is it a single-agent system?
  • What tools/functions are available to your agent(s)?
Section 3 — Quality & Evaluation
  • How do you currently evaluate output quality?
  • Do you have test cases or golden examples?
  • What are the most common failure modes?
Section 4 — Constraints
  • What are your cost constraints? (budget per request, per day)
  • What are your latency requirements? (real-time, batch, async)
  • Are there compliance requirements? (HIPAA, GDPR, SOC2, etc.)
Section 5 — Priorities
  • Rank these from most to least important: Quality, Speed, Cost, Safety
  • What's the single biggest workflow problem you want to solve?
每次仅询问一个板块的问题，收到回答后再继续推进。
板块1 — 模型与提供商
  • 你正在使用哪些AI模型？（例如：GPT-4、Claude、Gemini、本地模型）
  • 你是直接调用API还是通过框架使用？（例如：LangChain、LlamaIndex、自定义框架）
  • 你的上下文窗口大小是多少？
板块2 — 工作流架构
  • 从高层视角描述你当前的工作流（输入是什么、输出是什么）
  • 你使用的是多Agent/多步骤系统，还是单Agent系统？
  • 你的Agent可以调用哪些工具/函数？
板块3 — 质量与评估
  • 你当前如何评估输出质量？
  • 你有测试用例或者金标准示例吗？
  • 最常见的故障模式有哪些？
板块4 — 约束条件
  • 你的成本约束是什么？（单次请求预算、每日预算）
  • 你的延迟要求是什么？（实时、批量、异步）
  • 是否有合规要求？（HIPAA、GDPR、SOC2等）
板块5 — 优先级
  • 按重要性从高到低排序：质量、速度、成本、安全
  • 你想要解决的最大的工作流问题是什么？

Output Format

输出格式

After gathering all answers, generate a 
.maestro.md
file:
markdown
undefined
收集完所有回答后，生成一个
.maestro.md
文件：
markdown
undefined

Maestro Workflow Context

Maestro Workflow Context

Generated: [date]
Generated: [date]

Models & Providers

Models & Providers

[answers from section 1]
[answers from section 1]

Workflow Architecture

Workflow Architecture

[answers from section 2]
[answers from section 2]

Quality & Evaluation

Quality & Evaluation

[answers from section 3]
[answers from section 3]

Constraints

Constraints

[answers from section 4]
[answers from section 4]

Priorities

Priorities

[answers from section 5, with ranked priorities]

Save this file to the project root as `.maestro.md`.
[answers from section 5, with ranked priorities]

将该文件以`.maestro.md`为名保存到项目根目录。

Context Completeness

上下文完整性

SectionStatusImpact if Missing
Models & Providers?Commands can't tailor advice to your stack
Workflow Architecture?Commands can't assess complexity
Quality & Evaluation?
/iterate
and 
/evaluate
less effective
Constraints?
/guard
and 
/accelerate
can't set limits
Priorities?All commands default to generic guidance
板块状态缺失的影响
模型与提供商?命令无法针对你的技术栈定制建议
工作流架构?命令无法评估复杂度
质量与评估?
/iterate
和 
/evaluate
命令效果会下降
约束条件?
/guard
和 
/accelerate
命令无法设置限制
优先级?所有命令都会默认返回通用指导

Interview Checklist

访谈检查清单

  • All 5 sections asked and answered
  • Answers are specific (not vague)
  • .maestro.md
    file generated and saved
  • User confirmed accuracy of the generated context
  • 所有5个板块都已询问并收到回答
  • 回答具体（不模糊）
  • 已生成并保存
    .maestro.md
    文件
  • 用户已确认生成的上下文准确无误

Recommended Next Step

推荐的下一步

After creating 
.maestro.md
, run 
{{command_prefix}}diagnose
for a baseline health check of your workflow.
NEVER:
  • Skip questions — every section matters for downstream commands
  • Make assumptions — ask if unclear
  • Overwrite an existing 
    .maestro.md
    without asking
创建
.maestro.md
后，运行
{{command_prefix}}diagnose
对你的工作流进行基线健康检查。
严禁操作：
  • 跳过问题——每个板块对下游命令都至关重要
  • 擅自假设——不清楚的内容一定要询问
  • 未经用户确认就覆盖已有的
    .maestro.md
    文件