Back to Details

reflect

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Reflect

反思

Review the conversation and persist learnings — to 
brain/
, to skill files, or as structural enforcement.
回顾对话并沉淀所学内容——保存至
brain/
目录、Skill文件，或作为结构性强制规则。

Process

流程

Use Tasks to track progress (TaskCreate per step, TaskUpdate to in_progress/completed).
  1. Read 
    brain/index.md
     to understand what notes already exist
  2. Scan the conversation for:
    • Mistakes made and corrections received
    • User preferences and workflow patterns
    • Codebase knowledge gained (architecture, gotchas, patterns)
    • Tool/library quirks discovered
    • Decisions made and their rationale
    • Friction in skill execution, orchestration, or delegation
    • Repeated manual steps that could be automated or encoded
  3. Skip anything trivial or already captured in existing brain files
  4. Route each learning to the right destination (see Routing below)
  5. Update 
    brain/index.md
     if any brain files were added or removed
使用Tasks跟踪进度（每一步执行TaskCreate，通过TaskUpdate更新为进行中/已完成状态）。
  1. 读取
    brain/index.md
    ，了解现有笔记内容
  2. 梳理对话，查找以下内容：
    • 犯下的错误及收到的纠正
    • 用户偏好与工作流模式
    • 习得的代码库知识（架构、坑点、模式）
    • 发现的工具/库特殊特性
    • 做出的决策及其背后逻辑
    • Skill执行、编排或委派过程中的摩擦点
    • 可自动化或编码化的重复手动步骤
  3. 跳过任何琐碎内容或已记录在现有brain文件中的内容
  4. 将每条所学内容分派到合适的位置（见下方“分派规则”）
  5. 若新增或删除了任何brain文件，更新
    brain/index.md

Routing

分派规则

Not everything belongs in the brain. Route each learning to where it will have the most impact.
并非所有内容都适合放入brain。需将每条所学内容放到最能发挥价值的位置。

Structural enforcement check

结构性强制检查

Before routing a learning to 
brain/
, ask: can this be a lint rule, script, metadata flag, or runtime check? If yes, encode it structurally and skip the brain note. See 
brain/principles/encode-lessons-in-structure.md
.
在将学习内容分派到
brain/
之前，先自问：这能不能做成lint规则、脚本、元数据标记或运行时检查？如果可以，就将其结构化编码，无需写入brain笔记。参见
brain/principles/encode-lessons-in-structure.md
。

Brain files (
brain/
)

Brain文件（
brain/
）

Codebase knowledge, delegation principles, gotchas — anything that informs future sessions. This is the default destination. Use the 
brain
skill for writing conventions.
  • One topic per file. File name = topic slug.
  • Group in directories with index files using 
    [[wikilinks]]
    .
  • No inlined content in index files.
代码库知识、委派原则、坑点——任何对未来会话有帮助的内容。这是默认归档位置。书写规范请遵循
brain
Skill的约定。
  • 每个文件对应一个主题，文件名=主题slug
  • 按目录分组，目录下配备索引文件，使用
    [[wikilinks]]
    语法
  • 索引文件中不放置内联内容

Skill improvements (
.agents/skills/<skill>/
)

Skill改进（
.agents/skills/<skill>/
）

If a learning is about how a specific skill works — its process, prompts, or edge cases — update the skill directly. Use the 
skill-creator
skill for guidelines on effective skill content.
如果学习内容与某个特定Skill的运行方式相关——比如其流程、提示词或边界情况——直接更新该Skill。关于高效Skill内容的编写指南，请使用
skill-creator
Skill。

Orchestration workflow improvements

编排工作流改进

If the session revealed systemic orchestration issues, route to:
  • Brain principle (new delegation heuristic) → 
    brain/delegation/
  • Skill mechanics change (monitoring loop, review step) → relevant skill file
  • New skill opportunity (recurring workflow that could be encoded) → note in summary for the user
如果本次会话暴露了系统性的编排问题，分派到以下位置：
  • Brain原则（新的委派启发式规则）→ 
    brain/delegation/
  • Skill机制变更（监控循环、审查步骤）→ 对应的Skill文件
  • 新Skill机会（可被编码的重复工作流）→ 在给用户的总结中注明

Backlog items (
brain/todos.md
)

待办事项（
brain/todos.md
）

Follow-up work that can't be done during reflection — bugs, non-trivial rewrites, tooling gaps. Use the 
todo
skill to file.
反思期间无法完成的后续工作——bug、非平凡重写、工具缺口。使用
todo
Skill来归档。

Summary

总结

undefined
undefined

Reflect Summary

Reflect Summary

  • Brain: [files created/updated, one-line each]
  • Skills: [skill files modified, one-line each]
  • Structural: [rules/scripts/checks added]
  • Todos: [follow-up items filed]
undefined
  • Brain: [files created/updated, one-line each]
  • Skills: [skill files modified, one-line each]
  • Structural: [rules/scripts/checks added]
  • Todos: [follow-up items filed]
undefined