Back to Details

temper

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

MANDATORY PREPARATION

必备准备工作

Invoke {{command_prefix}}agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run {{command_prefix}}teach-maestro first. Consult the agent-architecture reference in the agent-workflow skill for topology patterns and when multi-agent is justified.
Pull back from over-engineering. The most common mistake isn't building too little — it's building too much.
调用 {{command_prefix}}agent-workflow —— 它包含工作流原则、反模式，以及Context Gathering Protocol。继续操作前请遵循该协议——如果还不存在任何工作流上下文，你必须先运行 {{command_prefix}}teach-maestro。 参考 agent-workflow skill 中的 agent-architecture 参考文档了解拓扑模式，以及多Agent适用的场景。
避免过度工程化。最常见的错误不是构建的内容太少——而是构建得太多。

Over-Engineering Detection

过度工程化检测

Signs you've over-engineered:
  • Multi-agent for a single-agent problem
  • Premature optimization before you have performance data
  • Abstraction layers with one implementation
  • Configuration for things that never change
  • Evaluation loops on non-critical outputs
  • Framework before features
你出现过度工程化的迹象：
  • 为单Agent问题使用多Agent方案
  • 在获取性能数据之前就进行过早优化
  • 仅有一种实现的抽象层
  • 为永远不会变更的内容做配置
  • 对非关键输出设置评估循环
  • 先搭框架再做功能

The Complexity Test

复杂度测试

For each component:
  1. Is this solving a problem we actually have? (not "might have")
  2. Is this the simplest solution that works?
  3. Would removing this break anything? (if not, remove it)
  4. Can someone new understand this in 5 minutes? (if not, simplify)
针对每个组件：
  1. 它是否解决了我们当下实际存在的问题？（不是“可能存在”的问题）
  2. 这是否是能生效的最简单方案？
  3. 移除它是否会导致任何功能异常？（如果不会，就移除）
  4. 新接触的人能否在5分钟内理解它？（如果不能，就简化）

Tempering Strategies

优化精简策略

Collapse Unnecessary Agents
text
OVER-ENGINEERED: User → Classifier → Router → Specialist → Formatter → Checker (6 components)
TEMPERED: User → Single Agent with good prompt (1 component, same quality)
Remove Premature Abstraction
text
OVER-ENGINEERED: class AgentOrchestrator with 5 strategy interfaces
TEMPERED: async function runWorkflow(input) — direct, readable
Simplify Configuration
text
OVER-ENGINEERED: config.yaml (200 lines, 47 params, 3 inheritance levels)
TEMPERED: config.yaml (20 lines, essential params only, sensible defaults)
合并不必要的Agent
text
OVER-ENGINEERED: User → Classifier → Router → Specialist → Formatter → Checker (6 components)
TEMPERED: User → Single Agent with good prompt (1 component, same quality)
移除过早的抽象
text
OVER-ENGINEERED: class AgentOrchestrator with 5 strategy interfaces
TEMPERED: async function runWorkflow(input) — direct, readable
简化配置
text
OVER-ENGINEERED: config.yaml (200 lines, 47 params, 3 inheritance levels)
TEMPERED: config.yaml (20 lines, essential params only, sensible defaults)

What NOT to Temper

禁止精简的内容

  • Error handling — essential, not overhead
  • Logging — saves you when things go wrong
  • Input validation — prevents cascading failures
  • Core guardrails — safety is non-negotiable
  • The golden test set — how you know it still works
  • 错误处理——核心必备，不是冗余开销
  • 日志——出问题时能帮你排查定位
  • 输入校验——避免级联故障
  • 核心护栏——安全性是不可妥协的
  • 黄金测试集——用于验证功能是否正常运行

Recommended Next Step

推荐后续步骤

After tempering, run 
{{command_prefix}}evaluate
to confirm quality is preserved, or 
{{command_prefix}}diagnose
for a full health check.
NEVER:
  • Temper without measuring output quality before and after
  • Remove error handling in the name of simplicity
  • Simplify below the level of correctness
  • Remove features users actively rely on
精简后，运行 
{{command_prefix}}evaluate
确认质量不受影响，或者运行 
{{command_prefix}}diagnose
进行完整健康检查。
绝对不要：
  • 精简前后没有度量输出质量
  • 为了简化而移除错误处理
  • 过度简化导致正确性受影响
  • 移除用户正在使用的功能