memory-manage

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

memory-manage

内存管理

Unified management of the ai-context/ memory layer. Three modes: init, update, maintain.

Triggers:

/memory-init

/memory-update

/memory-maintain

, initialize memory, update memory, maintain memory, memory housekeeping, clean ai-context

统一管理ai-context/内存层。包含三种模式：初始化（init）、更新（update）、维护（maintain）。

触发指令：

/memory-init

/memory-update

/memory-maintain

, initialize memory, update memory, maintain memory, memory housekeeping, clean ai-context

Mode Detection

模式检测

Determine the mode from the invocation:

```
/memory-init
```
or "initialize memory" or "generate ai-context" → init mode
```
/memory-update
```
or "update memory" or "sync memory" or "record session" → update mode
```
/memory-maintain
```
or "maintain memory" or "memory housekeeping" or "clean ai-context" → maintain mode

根据调用指令判断模式：

```
/memory-init
```
或 "initialize memory" 或 "generate ai-context" → 初始化模式（init mode）
```
/memory-update
```
或 "update memory" 或 "sync memory" 或 "record session" → 更新模式（update mode）
```
/memory-maintain
```
或 "maintain memory" 或 "memory housekeeping" 或 "clean ai-context" → 维护模式（maintain mode）

Mode: init

模式：初始化（init）

Creates the 5 core ai-context/ files from scratch by reading the project.

Use when: Project has no

ai-context/

yet, or you want to regenerate from scratch.

通过读取项目内容，从头创建5个核心ai-context/文件。

适用场景：项目尚未创建

ai-context/

Process

执行流程

Project inventory: Read configuration files, folder structure, README, representative source files, tests, CI/CD configs.
Generate files:
- ```
ai-context/stack.md
```
  — tech stack, versions, key tools
- ```
ai-context/architecture.md
```
  — architectural decisions and rationale
- ```
ai-context/conventions.md
```
  — naming patterns, code conventions
- ```
ai-context/known-issues.md
```
  — known bugs, tech debt, gotchas
- ```
ai-context/changelog-ai.md
```
  — empty, ready for session entries
Feature stubs: Scan for bounded contexts (directories with domain logic). Create
```
ai-context/features/_template.md
```
and stub files for discovered domains.
Report: List files created and coverage summary.

项目盘点：读取配置文件、文件夹结构、README、代表性源码文件、测试文件、CI/CD配置文件。
生成文件：
- ```
ai-context/stack.md
```
  — 技术栈、版本信息、核心工具
- ```
ai-context/architecture.md
```
  — 架构决策及理由
- ```
ai-context/conventions.md
```
  — 命名规范、代码约定
- ```
ai-context/known-issues.md
```
  — 已知Bug、技术债务、注意事项
- ```
ai-context/changelog-ai.md
```
  — 空文件，用于记录会话内容
功能存根生成：扫描有界上下文（包含领域逻辑的目录）。创建
```
ai-context/features/_template.md
```
模板文件，并为发现的领域生成存根文件。
生成报告：列出已创建的文件及覆盖范围总结。

Mode: update

模式：更新（update）

Incrementally updates ai-context/ with work done in the current session.

Use when: After completing significant work (SDD cycles, architecture changes, bug fixes).

根据当前会话完成的工作，增量更新ai-context/目录下的文件。

适用场景：完成重要工作后（如SDD周期迭代、架构变更、Bug修复）。

Process

执行流程

Analyze session: Review what changed — files created/modified, decisions made, bugs fixed, conventions established.
Update relevant files:
- ```
ai-context/stack.md
```
  — new dependencies, version changes
- ```
ai-context/architecture.md
```
  — new decisions, pattern changes
- ```
ai-context/conventions.md
```
  — new naming patterns, style changes
- ```
ai-context/known-issues.md
```
  — new issues found, resolved issues marked
- ```
ai-context/changelog-ai.md
```
  — append entry with date, summary, files affected
- ```
ai-context/features/<domain>.md
```
  — update if relevant domain was touched
Preserve: Never overwrite
```
[manual]
```
sections. Only update
```
[auto-updated]
```
markers.

会话分析：回顾会话中的变更内容——创建/修改的文件、做出的决策、修复的Bug、确立的规范。
更新相关文件：
- ```
ai-context/stack.md
```
  — 添加新依赖、更新版本信息
- ```
ai-context/architecture.md
```
  — 记录新决策、架构模式变更
- ```
ai-context/conventions.md
```
  — 更新命名规范、代码风格变更
- ```
ai-context/known-issues.md
```
  — 添加新发现的问题、标记已解决的问题
- ```
ai-context/changelog-ai.md
```
  — 追加条目，包含日期、内容摘要、受影响的文件
- ```
ai-context/features/<domain>.md
```
  — 若相关领域有变更则进行更新
保留规则：绝不覆盖
```
[manual]
```
标记的手动维护部分。仅更新
```
[auto-updated]
```
标记的自动更新区域。

Mode: maintain

模式：维护（maintain）

Periodic housekeeping: archive old entries, separate resolved issues, detect gaps.

Use when: changelog-ai.md is long (30+ entries), known-issues has resolved items, or at the start of a new project phase.

定期整理工作：归档旧条目、分离已解决的问题、检测文件缺失。

适用场景：

changelog-ai.md

条目过多（超过30条）、

known-issues.md

中有已解决的问题，或进入项目新阶段时。

Process

执行流程

Changelog archival: If
```
changelog-ai.md
```
has more than 30 entries, move older entries to
```
changelog-ai-archive.md
```
.
Known-issues cleanup: Move resolved items from
```
known-issues.md
```
to
```
known-issues-archive.md
```
.
Index generation: Create/update
```
ai-context/index.md
```
listing all ai-context/ files with one-line descriptions.
Gap detection: Check if CLAUDE.md references ai-context/ files that don't exist. Report gaps.
Dry-run first: Present all proposed changes, require user confirmation before applying.

变更日志归档：若
```
changelog-ai.md
```
条目超过30条，将旧条目迁移至
```
changelog-ai-archive.md
```
。
已知问题清理：将
```
known-issues.md
```
中已解决的问题迁移至
```
known-issues-archive.md
```
。
生成索引：创建/更新
```
ai-context/index.md
```
，列出所有ai-context/文件并添加一行描述。
缺失检测：检查CLAUDE.md中引用的ai-context/文件是否存在，报告缺失情况。
先执行预演：展示所有拟执行的变更，需用户确认后再应用。

Rules

规则

Init mode MUST NOT run if ai-context/ already exists — warn and suggest update mode instead
Update mode MUST NOT create new core files — only modify existing ones
Maintain mode MUST present dry-run before any destructive action (archival, moves)
All modes are read-heavy, write-light — the goal is accurate, concise documentation
Never overwrite
```
[manual]
```
sections in any file
Feature file updates follow the format defined in
```
skills/feature-domain-expert/SKILL.md
```

若
```
ai-context/
```
目录已存在，禁止运行初始化模式（init mode）——需发出警告并建议使用更新模式
更新模式（update mode）禁止创建新的核心文件——仅可修改现有文件
维护模式（maintain mode）在执行任何破坏性操作（归档、迁移）前必须先进行预演
所有模式均为“多读少写”——目标是生成准确、简洁的文档
绝不覆盖任何文件中
```
[manual]
```
标记的手动维护部分
功能文件的更新需遵循
```
skills/feature-domain-expert/SKILL.md
```
中定义的格式