Back to Details

memory-discipline

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
Memory only pays off when reads happen before the work and writes happen at decision points. This loop is the skill; every tool call in it is mechanical.
只有在工作前读取记忆、在决策节点写入记忆时，记忆才能发挥价值。这个循环就是一项技能；其中的每个工具调用都是机械性操作。

Quick start

快速开始

json
memory_smart_search { "query": "auth refresh flow", "project": "myrepo", "limit": 5 }
at task start, then at each settled decision:
json
memory_save { "content": "Chose cursor pagination over offset; offset scans broke past 100k rows in db/list.ts.", "concepts": "cursor-pagination, offset-scan-limit", "files": "src/db/list.ts" }
json
memory_smart_search { "query": "auth refresh flow", "project": "myrepo", "limit": 5 }
在任务开始时执行上述操作，然后在每个决策确定后执行：
json
memory_save { "content": "Chose cursor pagination over offset; offset scans broke past 100k rows in db/list.ts.", "concepts": "cursor-pagination, offset-scan-limit", "files": "src/db/list.ts" }

Why

核心原因

Hooks capture what happened automatically. What they cannot capture is judgment: which fact mattered, which decision was settled, which correction should change future behavior. That judgment applied at the right moments is this discipline.
钩子会自动记录已发生的事件，但它们无法捕捉判断：哪些事实至关重要，哪些决策已确定，哪些修正应改变未来行为。在恰当的时刻运用这种判断，就是这套方法的关键。

Workflow

工作流程

  1. Task start, before reading code for any nontrivial task: 
    memory_smart_search
    with the task topic and the project name. Spend the first tool call here; a hit saves rediscovery, a miss costs one call.
  2. Mid-task, the moment a decision settles or a gotcha resolves: 
    memory_save
    with the decision AND the reason, 2-5 specific concepts, real file paths. Save at the moment of resolution; end-of-session batch saves lose the reasons.
  3. On user correction of your approach: save a lesson instead of a memory (the 
    lesson
    skill). Lessons carry confidence and resurface before similar work; memories carry facts.
  4. Before repeating a task type you have been corrected on: 
    memory_lesson_recall
    with the task type as query.
  5. Session end: stop. Hooks summarize and consolidate; a manual recap save duplicates them.
  1. 任务启动时，在处理任何重要任务的代码前：使用任务主题和项目名称调用
    memory_smart_search
    。将第一个工具调用用于此处；如果检索到相关内容，可避免重复探索；如果没有，也仅消耗一次调用。
  2. 任务进行中，当决策确定或问题解决的那一刻：调用
    memory_save
    ，传入决策内容及原因、2-5个具体概念、真实文件路径。要在问题解决的当下保存；会话结束后批量保存会丢失决策原因。
  3. 当用户修正你的方法时：保存为经验教训（使用
    lesson
    技能）而非普通记忆。经验教训带有可信度，会在类似工作前重新浮现；普通记忆仅存储事实。
  4. 在重复执行曾被修正过的任务类型前：以任务类型为查询词调用
    memory_lesson_recall
    。
  5. 会话结束：停止操作。钩子会自动总结和整合记忆；手动保存总结会造成重复。

What qualifies

可保存的内容

Save: settled decisions with reasons, non-obvious constraints discovered by debugging, environment facts not derivable from the repo. Skip: anything readable from the code, transient state, secrets, and step-by-step narration (hooks already captured it).
可保存：带有原因的确定决策、调试发现的非显而易见的约束条件、无法从代码库推导的环境信息。需跳过：任何可从代码中读取的内容、临时状态、机密信息，以及分步操作叙述（钩子已自动记录这些内容）。

Anti-patterns

反模式

WRONG: finish implementing, then search memory to double-check, and batch-save a summary of everything done.
RIGHT: search first, save each decision as it settles, let hooks own the summary.
错误做法：完成实现后，再检索记忆进行双重检查，然后批量保存所有操作的总结。
正确做法：先检索记忆，在每个决策确定时立即保存，让钩子负责总结工作。

Checklist

检查清单

  • First tool call on a nontrivial task was a project-scoped search.
  • Every save carries the reason, not just the conclusion.
  • Corrections became lessons, not memories.
  • Nothing saved that the repo or hooks already record.
  • 重要任务的第一个工具调用是针对项目范围的检索。
  • 每次保存都包含决策原因，而非仅结论。
  • 修正内容被保存为经验教训，而非普通记忆。
  • 未保存代码库或钩子已记录的内容。

See also

相关技能

  • recall
    , 
    remember
    : the user-invoked forms of the read and write sides.
  • lesson
    : the correction loop this discipline hands off to.
  • recall
    、
    remember
    ：由用户触发的记忆读取和写入操作。
  • lesson
    ：这套方法所衔接的修正循环技能。

Troubleshooting

问题排查

See ../_shared/TROUBLESHOOTING.md if 
memory_smart_search
or 
memory_save
is not available.
如果
memory_smart_search
或
memory_save
无法使用，请查看../_shared/TROUBLESHOOTING.md。