memory

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Memory - Read & Access Operations

内存 - 读取与访问操作

Unified read-side memory skill with subcommands for searching, loading, syncing, history, and visualization.

统一的读侧内存技能，包含搜索、加载、同步、历史记录与可视化子命令。

Usage

使用方法

bash

/ork:memory search <query>  # Search knowledge graph
/ork:memory load             # Load context at session start
/ork:memory history          # View decision timeline
/ork:memory viz              # Visualize knowledge graph
/ork:memory status           # Show memory system health

bash

/ork:memory search <query>  # 搜索知识图谱
/ork:memory load             # 会话启动时加载上下文
/ork:memory history          # 查看决策时间线
/ork:memory viz              # 可视化知识图谱
/ork:memory status           # 查看内存系统健康状态

CRITICAL: Use AskUserQuestion When No Subcommand

重要提示：无自命令时调用AskUserQuestion

If invoked without a subcommand, ask the user what they want:

python

AskUserQuestion(
  questions=[{
    "question": "What memory operation do you need?",
    "header": "Operation",
    "options": [
      {"label": "search", "description": "Search decisions and patterns in knowledge graph"},
      {"label": "load", "description": "Load relevant context for this session"},
      {"label": "history", "description": "View decision timeline"},
      {"label": "viz", "description": "Visualize knowledge graph as Mermaid"},
      {"label": "status", "description": "Check memory system health"}
    ],
    "multiSelect": false
  }]
)

如果调用时未指定子命令，请询问用户需求：

python

AskUserQuestion(
  questions=[{
    "question": "你需要执行哪种内存操作？",
    "header": "操作类型",
    "options": [
      {"label": "search", "description": "搜索知识图谱中的决策与模式"},
      {"label": "load", "description": "加载当前会话的相关上下文"},
      {"label": "history", "description": "查看决策时间线"},
      {"label": "viz", "description": "将知识图谱生成为Mermaid可视化图"},
      {"label": "status", "description": "检查内存系统健康状态"}
    ],
    "multiSelect": false
  }]
)

Subcommands

子命令

search

- Search Knowledge Graph

search

- 搜索知识图谱

Search past decisions, patterns, and entities from the knowledge graph.

Usage:

bash

/ork:memory search <query>                    # Search knowledge graph
/ork:memory search --category <cat> <query>   # Filter by category
/ork:memory search --limit <n> <query>        # Limit results (default: 10)
/ork:memory search --agent <agent-id> <query> # Filter by agent scope
/ork:memory search --global <query>           # Search cross-project best practices

Flags:

Flag	Behavior
(default)	Search graph
`--limit <n>`	Max results (default: 10)
`--category <cat>`	Filter by category
`--agent <agent-id>`	Filter results to a specific agent's memories
`--global`	Search cross-project best practices

Context-Aware Result Limits:

Result limits automatically adjust based on

context_window.used_percentage

Context Usage	Default Limit	Behavior
0-70%	10 results	Full results with details
70-85%	5 results	Reduced, summarized results
>85%	3 results	Minimal with "more available" hint

Search Workflow:

Parse flags (--category, --limit, --agent, --global)

Build filters from flags:

Check for --category <cat> flag → metadata.category: "<cat>"
Check for --agent <agent-id> flag → agent_id: "ork:{agent-id}"
Check for --global flag → user_id: "orchestkit-global-best-practices"

Search knowledge graph via

mcp__memory__search_nodes

json

{ "query": "user's search query" }

Entity Types to Look For:

```
Technology
```
: Tools, frameworks, databases (pgvector, PostgreSQL, React)
```
Agent
```
: OrchestKit agents (database-engineer, backend-system-architect)
```
Pattern
```
: Named patterns (cursor-pagination, connection-pooling)
```
Decision
```
: Architectural decisions
```
Project
```
: Project-specific context
```
AntiPattern
```
: Failed patterns

Result Formats:

Found {count} results matching "{query}":

[GRAPH] {entity_name} ({entity_type})
   -> {relation1} -> {target1}
   Observations: {observation1}, {observation2}

No results:

No results found matching "{query}"

Try:
- Broader search terms
- /ork:remember to store new decisions
- --global flag to search cross-project best practices

从知识图谱中搜索过往决策、模式与实体。

使用方式：

bash

/ork:memory search <query>                    # 搜索知识图谱
/ork:memory search --category <cat> <query>   # 按分类筛选
/ork:memory search --limit <n> <query>        # 限制结果数量（默认：10）
/ork:memory search --agent <agent-id> <query> # 按Agent范围筛选
/ork:memory search --global <query>           # 跨项目搜索最佳实践

参数说明：

参数	作用
(默认)	搜索图谱
`--limit <n>`	最大结果数（默认：10）
`--category <cat>`	按分类筛选
`--agent <agent-id>`	筛选特定Agent的内存数据
`--global`	跨项目搜索最佳实践

上下文感知的结果限制：

结果数量会根据

context_window.used_percentage

自动调整：

上下文使用率	默认结果数	行为
0-70%	10条结果	返回完整详情结果
70-85%	5条结果	返回精简的摘要结果
>85%	3条结果	返回极简结果并提示"更多结果可用"

搜索工作流：

解析参数（--category, --limit, --agent, --global）

根据参数构建筛选条件：

检查--category <cat>参数 → metadata.category: "<cat>"
检查--agent <agent-id>参数 → agent_id: "ork:{agent-id}"
检查--global参数 → user_id: "orchestkit-global-best-practices"

通过

mcp__memory__search_nodes

搜索知识图谱：

json

{ "query": "用户的搜索查询" }

需查找的实体类型：

```
Technology
```
: 工具、框架、数据库（pgvector, PostgreSQL, React）
```
Agent
```
: OrchestKit Agent（database-engineer, backend-system-architect）
```
Pattern
```
: 命名模式（cursor-pagination, connection-pooling）
```
Decision
```
: 架构决策
```
Project
```
: 项目特定上下文
```
AntiPattern
```
: 失败模式

结果格式：

找到 {count} 条匹配"{query}"的结果：

[图谱] {entity_name} ({entity_type})
   -> {relation1} -> {target1}
   观测结果: {observation1}, {observation2}

无结果时：

未找到匹配"{query}"的结果

建议尝试：
- 使用更宽泛的搜索词
- 执行/ork:remember存储新决策
- 添加--global参数搜索跨项目最佳实践

load

- Load Session Context

load

- 加载会话上下文

Auto-load relevant memories at session start from knowledge graph.

Usage:

bash

/ork:memory load              # Load all relevant context
/ork:memory load --project    # Project-specific only
/ork:memory load --global     # Include global best practices

What it loads:

Recent decisions from
```
.claude/memory/decisions.jsonl
```
Active project context
Agent-specific memories (if in agent context)
Global best practices (if --global)

在会话启动时从知识图谱自动加载相关内存数据。

使用方式：

bash

/ork:memory load              # 加载所有相关上下文
/ork:memory load --project    # 仅加载项目特定上下文
/ork:memory load --global     # 包含全局最佳实践

加载内容：

来自
```
.claude/memory/decisions.jsonl
```
的近期决策
活跃项目上下文
Agent特定内存数据（若处于Agent上下文）
全局最佳实践（若使用--global参数）

history

- Decision Timeline

history

- 决策时间线

Visualize architecture decisions over time, tracking evolution and rationale.

Usage:

bash

/ork:memory history                    # Show recent decisions
/ork:memory history --category <cat>   # Filter by category
/ork:memory history --since 7d         # Last 7 days
/ork:memory history --mermaid          # Output as Mermaid timeline

Output formats:

Table view (default)
Mermaid timeline diagram (--mermaid)
JSON (--json)

可视化架构决策随时间的演变，追踪演进过程与决策依据。

使用方式：

bash

/ork:memory history                    # 显示近期决策
/ork:memory history --category <cat>   # 按分类筛选
/ork:memory history --since 7d         # 显示近7天记录
/ork:memory history --mermaid          # 输出为Mermaid时间线

输出格式：

表格视图（默认）
Mermaid时间线图（--mermaid参数）
JSON格式（--json参数）

viz

- Knowledge Graph Visualization

viz

- 知识图谱可视化

Render the local knowledge graph as a Mermaid diagram.

Usage:

bash

/ork:memory viz                  # Full graph
/ork:memory viz --entity <name>  # Focus on specific entity
/ork:memory viz --depth 2        # Limit relationship depth
/ork:memory viz --type <type>    # Filter by entity type

Entity types:

Technology, Agent, Pattern, Decision, Project, AntiPattern, Constraint, Preference

Relation types:

USES, RECOMMENDS, REQUIRES, ENABLES, PREFERS, CHOSE_OVER, USED_FOR, CONFLICTS_WITH

将本地知识图谱渲染为Mermaid图。

使用方式：

bash

/ork:memory viz                  # 完整图谱
/ork:memory viz --entity <name>  # 聚焦特定实体
/ork:memory viz --depth 2        # 限制关系深度
/ork:memory viz --type <type>    # 按实体类型筛选

实体类型：

Technology, Agent, Pattern, Decision, Project, AntiPattern, Constraint, Preference

关系类型：

USES, RECOMMENDS, REQUIRES, ENABLES, PREFERS, CHOSE_OVER, USED_FOR, CONFLICTS_WITH

status

- Memory Health Check

status

- 内存健康检查

Show memory system status and health.

Usage:

bash

/ork:memory status

Output:

Memory System Status:
  Graph Memory:  healthy (42 decisions, 0 corrupt)
  Queue Depth:   3 pending

显示内存系统状态与健康情况。

使用方式：

bash

/ork:memory status

输出示例：

内存系统状态:
  图谱内存: 健康（42条决策，0条损坏）
  队列深度: 3条待处理

Workflow

工作流

1. Parse Subcommand

1. 解析子命令

Extract first argument as subcommand
If no subcommand -> AskUserQuestion
Validate subcommand is one of: search, load, history, viz, status
Parse remaining flags

提取第一个参数作为子命令
若无自命令 → 调用AskUserQuestion
验证子命令是否为以下之一：search, load, history, viz, status
解析剩余参数

2. Execute Subcommand

2. 执行子命令

Route to appropriate handler based on subcommand.

根据子命令路由至对应的处理逻辑。

3. Report Results

3. 报告结果

Format output appropriate to the operation.

根据操作类型格式化输出结果。

Related Skills

CC 2.1.31 Session Resume Hints

CC 2.1.31 会话恢复提示

At session end, Claude shows resume hints. To maximize resume effectiveness:

会话结束时，Claude会显示恢复提示。为最大化恢复效率：

Capture Context Before Ending

结束前捕获上下文

bash

undefined

bash

undefined

Store key decisions and context

存储关键决策与上下文

/ork:remember Key decisions for next session:

Decision 1: [brief]
Decision 2: [brief]
Next steps: [what remains]

undefined

/ork:remember 下会话关键决策:

决策1: [简要描述]
决策2: [简要描述]
下一步: [待完成事项]

undefined

Resume Patterns

恢复模式

bash

undefined

bash

undefined

For PR work: Use --from-pr (CC 2.1.27)

针对PR工作：使用--from-pr（CC 2.1.27）

/ork:create-pr

Later: claude --from-pr 123

后续恢复: claude --from-pr 123

For issue fixing: Use memory load

针对问题修复：使用memory load

/ork:fix-issue 456

Later: /ork:memory load # Reloads investigation context

后续恢复: /ork:memory load # 重新加载调查上下文

For implementation: Use memory search

针对开发实现：使用memory search

/ork:implement user-auth

Later: /ork:memory search "user-auth implementation"

后续恢复: /ork:memory search "user-auth implementation"

undefined

undefined

Best Practice

最佳实践

Always store investigation findings before session end:

bash

/ork:remember Session summary for {task}:
  Completed: [what was done]
  Findings: [key discoveries]
  Next steps: [what remains]
  Blockers: [if any]

会话结束前务必存储调查结果：

bash

/ork:remember {任务}会话摘要:
  已完成: [完成事项]
  发现: [关键结论]
  下一步: [待完成事项]
  阻塞点: [若有]

Error Handling

错误处理

If graph empty for viz: Show helpful message about using /ork:remember
If subcommand invalid: Show usage help
If memory files corrupt: Report and offer repair
If search query empty: Show recent entities instead
If no search results: Suggest alternatives

若可视化时图谱为空：显示使用/ork:remember的提示信息
若子命令无效：显示使用帮助
若内存文件损坏：报告问题并提供修复选项
若搜索查询为空：显示近期实体
若无搜索结果：建议替代方案

memory

Original

Translation

Memory - Read & Access Operations

内存 - 读取与访问操作

Usage

使用方法

CRITICAL: Use AskUserQuestion When No Subcommand

重要提示：无自命令时调用AskUserQuestion

Subcommands

子命令

search - Search Knowledge Graph

search - 搜索知识图谱

load - Load Session Context

load - 加载会话上下文

history - Decision Timeline

history - 决策时间线

viz - Knowledge Graph Visualization

viz - 知识图谱可视化

status - Memory Health Check

status - 内存健康检查

Workflow

工作流

1. Parse Subcommand

1. 解析子命令

2. Execute Subcommand

2. 执行子命令

3. Report Results

3. 报告结果

Related Skills

相关技能

CC 2.1.31 Session Resume Hints

CC 2.1.31 会话恢复提示

Capture Context Before Ending

结束前捕获上下文

Store key decisions and context

存储关键决策与上下文

Resume Patterns

恢复模式

For PR work: Use --from-pr (CC 2.1.27)

针对PR工作：使用--from-pr（CC 2.1.27）

Later: claude --from-pr 123

后续恢复: claude --from-pr 123

For issue fixing: Use memory load

针对问题修复：使用memory load

Later: /ork:memory load # Reloads investigation context

后续恢复: /ork:memory load # 重新加载调查上下文

For implementation: Use memory search

针对开发实现：使用memory search

Later: /ork:memory search "user-auth implementation"

后续恢复: /ork:memory search "user-auth implementation"

Best Practice

最佳实践

Error Handling

错误处理

`search`
- Search Knowledge Graph

`search`
- 搜索知识图谱

`load`
- Load Session Context

`load`
- 加载会话上下文

`history`
- Decision Timeline

`history`
- 决策时间线

`viz`
- Knowledge Graph Visualization

`viz`
- 知识图谱可视化

`status`
- Memory Health Check

`status`
- 内存健康检查