refine

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

MANDATORY PREPARATION

必做准备

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.

This is the final quality pass. The workflow works — now make it excellent.
调用 {{command_prefix}}agent-workflow —— 它包含工作流原则、反模式,以及上下文收集协议。在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。

这是最终质量校验环节。工作流已经可以正常运行——现在要将其打磨得更加完善。

Refinement Checklist

优化检查清单

Prompts
  • Every prompt follows the 4-zone pattern (role, context, instructions, output)
  • Output schemas are explicit and validated
  • Negative instructions clarify what NOT to do
  • No contradictory instructions
  • Few-shot examples included for ambiguous tasks
  • Chain-of-thought used for multi-step reasoning tasks
Tool Descriptions
  • Every tool has a multi-line description: what, when to use, when NOT to use, returns
  • Input parameters have descriptions and types
  • Error responses are documented
  • At least one example input/output in the description
Error Messages
  • Error messages are specific (not "an error occurred")
  • Error messages suggest corrective action
  • Errors include context (what was being attempted)
  • Errors are structured (code + message + details)
Logging
  • Every model call is logged (input tokens, output tokens, latency, cost)
  • Tool calls are logged with inputs and outputs
  • Errors are logged with full context
  • PII is redacted from logs
  • Workflow ID traces through all log entries
Configuration
  • All magic numbers are named constants
  • Environment-specific values are in config, not code
  • Defaults are sensible — config is for overrides
  • Cost ceilings are set
  • Timeout values are set for all external calls
Prompts
  • 所有提示词都遵循4区模式(角色、上下文、指令、输出要求)
  • 输出模式明确且经过校验
  • 包含否定指令,明确说明禁止执行的操作
  • 不存在互相矛盾的指令
  • 针对模糊任务包含了少样本示例
  • 多步推理任务使用了Chain-of-thought提示
工具描述
  • 每个工具都有多行描述:功能说明、适用场景、不适用场景、返回值说明
  • 输入参数包含描述和类型说明
  • 错误响应有完整文档
  • 描述中至少包含一个输入/输出示例
错误信息
  • 错误信息具体明确(不能仅显示“发生了错误”)
  • 错误信息给出修正建议
  • 错误包含上下文说明(当时正在尝试执行什么操作)
  • 错误是结构化的(错误码 + 信息 + 详情)
日志
  • 所有模型调用都有日志记录(输入token数、输出token数、延迟、成本)
  • 工具调用的输入和输出都被记录
  • 错误记录包含完整上下文
  • PII已从日志中脱敏移除
  • 工作流ID贯穿所有日志条目可追溯
配置
  • 所有魔法数字都定义为命名常量
  • 环境相关的配置值存放在配置文件中,而非硬编码在代码里
  • 默认值合理——配置仅用于覆盖默认值
  • 已设置成本上限
  • 所有外部调用都设置了超时时间

Output

输出

For each checklist item that fails, provide:
  1. What's wrong (specific finding)
  2. Where it is (file, line, or component)
  3. How to fix it (concrete suggestion)
  4. Priority (critical / important / nice-to-have)
对于每一项未通过检查的清单条目,请提供:
  1. 问题描述(具体发现的问题)
  2. 问题位置(文件、行号或组件)
  3. 修复方案(具体建议)
  4. 优先级(critical / important / nice-to-have)

Priority Matrix

优先级矩阵

PriorityCriteriaMaestro Action
CriticalAffects correctness or safety
{{command_prefix}}fortify
or
{{command_prefix}}guard
before shipping
ImportantAffects quality or maintainability
{{command_prefix}}calibrate
in current cycle
Nice-to-haveCosmetic or minor inconsistencyNote for next
{{command_prefix}}refine
pass
优先级判断标准Maestro 操作
Critical影响正确性或安全性上线前执行
{{command_prefix}}fortify
{{command_prefix}}guard
Important影响质量或可维护性当前迭代执行
{{command_prefix}}calibrate
Nice-to-have外观问题或微小不一致记录下来,留到下一次
{{command_prefix}}refine
环节处理

Recommended Next Step

推荐下一步

After refinement is complete, run
{{command_prefix}}evaluate
to verify the polished workflow against realistic scenarios.
NEVER:
  • Skip the checklist — go through every item
  • Mark items as passing without checking
  • Suggest changes that alter behavior (this is polish, not redesign)
  • Refine before the workflow is functionally correct (fix first, refine last)
优化完成后,运行
{{command_prefix}}evaluate
,用真实场景验证打磨后的工作流。
绝对禁止
  • 跳过检查清单——必须逐条目检查
  • 未实际检查就标记条目为通过
  • 提出会改变原有行为的修改建议(本环节是优化,不是重新设计)
  • 在工作流功能未正确实现前就进行优化(先修复功能,最后做优化)