context-manager

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Context Manager

上下文管理器

Purpose

目的

Permanent external memory system that compensates for SDAM (no episodic memory). Saves and recalls:

DECISION: Architectural choices, tech stack selections, design decisions
BLOCKER: Active obstacles preventing progress
CONTEXT: Project background, requirements, constraints
PREFERENCE: User preferences, coding style, patterns
PROCEDURE: How-to guides, workflows, processes
NOTE: General information, observations, reminders

For SDAM users: Complete external memory - never forget decisions or context. For ADHD users: Eliminates decision fatigue - past choices automatically recalled. For dyschronometria: All memories time-anchored with explicit timestamps.

用于补偿SDAM（无情景记忆）的永久外部记忆系统。可保存并召回以下内容：

DECISION（决策）：架构选择、技术栈选型、设计决策
BLOCKER（障碍）：阻碍进展的当前障碍
CONTEXT（上下文）：项目背景、需求、约束条件
PREFERENCE（偏好）：用户偏好、编码风格、模式
PROCEDURE（流程）：操作指南、工作流、流程步骤
NOTE（笔记）：通用信息、观察结果、提醒事项

针对SDAM用户：完整的外部记忆——再也不会忘记决策或上下文信息。 针对ADHD用户：消除决策疲劳——自动召回过往选择。 针对时间感知障碍用户：所有记忆都带有明确时间戳进行时间锚定。

Activation Triggers

触发条件

User says: "remember", "save this", "don't forget"
User asks: "what did we decide", "recall", "search for"
User mentions: "decision", "blocker", "preference"
Making important architectural decision (proactive save)
Encountering obstacle (proactive blocker tracking)

用户说出：“记住”、“保存这个”、“别忘了”
用户询问：“我们之前决定了什么”、“回忆一下”、“搜索一下”
用户提及：“决策”、“障碍”、“偏好”
做出重要架构决策时（主动保存）
遇到障碍时（主动追踪障碍）

Core Workflow

核心工作流

1. Save Memory

1. 保存记忆

When user says "remember [something]":

Step 1: Classify memory type

DECISION: "remember we're using PostgreSQL"
BLOCKER: "remember I can't access the API yet"
CONTEXT: "remember this is for BOOSTBOX project"
PREFERENCE: "remember I prefer functional components"
PROCEDURE: "remember how to deploy: npm run build then rsync"
NOTE: "remember to update docs after this feature"

Step 2: Extract metadata

Content: The actual memory
Tags: Auto-generate from keywords (e.g., "PostgreSQL" → ["database", "postgresql", "backend"])
Project: Infer from current directory or explicit mention
Timestamp: ISO 8601 format

Step 3: Read current index

bash

undefined

当用户说“记住[内容]”时：

步骤1：分类记忆类型

DECISION: "记住我们使用PostgreSQL"
BLOCKER: "记住我还无法访问API"
CONTEXT: "记住这是BOOSTBOX项目的内容"
PREFERENCE: "记住我偏好函数式组件"
PROCEDURE: "记住部署步骤：先运行npm run build再执行rsync"
NOTE: "记住完成这个功能后更新文档"

步骤2：提取元数据

内容：实际记忆内容
标签：从关键词自动生成（例如“PostgreSQL” → ["database", "postgresql", "backend"]）
项目：从当前目录或明确提及的内容推断
时间戳：ISO 8601格式

步骤3：读取当前索引

bash

undefined

Cross-platform: Use $HOME (Linux/macOS) or %USERPROFILE% (Windows)

跨平台：Linux/macOS使用$HOME，Windows使用%USERPROFILE%

cat ~/.claude-memories/index.json

Windows PowerShell alternative:

Windows PowerShell替代命令：

Get-Content "$env:USERPROFILE.claude-memories\index.json"


**Step 4**: Add to index
```json
{
  "version": "1.0.0",
  "created": "2025-10-17T17:45:00Z",
  "last_updated": "{current_timestamp}",
  "total_memories": N + 1,
  "memories_by_type": {
    "DECISION": X + 1,
    ...
  },
  "memories": [
    {
      "id": "{uuid}",
      "type": "DECISION",
      "content": "Using PostgreSQL as primary database",
      "timestamp": "{current_timestamp}",
      "tags": ["database", "postgresql", "backend"],
      "project": "boostbox",
      "context": {
        "file": "{current_file_if_relevant}",
        "conversation_id": "{if_available}"
      }
    },
    ...existing memories
  ],
  "tags_index": {
    "database": ["{uuid1}", "{uuid2}"],
    "postgresql": ["{uuid}"]
  },
  "project_index": {
    "boostbox": ["{uuid1}", "{uuid2}"],
    "toolhub": ["{uuid3}"]
  }
}

Step 5: Create detailed memory file

bash

undefined


**步骤4**：添加到索引
```json
{
  "version": "1.0.0",
  "created": "2025-10-17T17:45:00Z",
  "last_updated": "{current_timestamp}",
  "total_memories": N + 1,
  "memories_by_type": {
    "DECISION": X + 1,
    ...
  },
  "memories": [
    {
      "id": "{uuid}",
      "type": "DECISION",
      "content": "Using PostgreSQL as primary database",
      "timestamp": "{current_timestamp}",
      "tags": ["database", "postgresql", "backend"],
      "project": "boostbox",
      "context": {
        "file": "{current_file_if_relevant}",
        "conversation_id": "{if_available}"
      }
    },
    ...existing memories
  ],
  "tags_index": {
    "database": ["{uuid1}", "{uuid2}"],
    "postgresql": ["{uuid}"]
  },
  "project_index": {
    "boostbox": ["{uuid1}", "{uuid2}"],
    "toolhub": ["{uuid3}"]
  }
}

步骤5：创建详细记忆文件

bash

undefined

Save to category-specific directory

保存到对应类型的目录

Linux/macOS: ~/.claude-memories/decisions/{uuid}.md

Windows: %USERPROFILE%.claude-memories\decisions{uuid}.md

~/.claude-memories/decisions/{uuid}.md


```markdown

~/.claude-memories/decisions/{uuid}.md


```markdown

DECISION: Using PostgreSQL

Date: 2025-10-17T17:45:00Z (2 hours ago) Project: BOOSTBOX Tags: database, postgresql, backend

日期: 2025-10-17T17:45:00Z (2小时前) 项目: BOOSTBOX 标签: database, postgresql, backend

Decision

决策内容

Using PostgreSQL as primary database instead of MongoDB.

使用PostgreSQL作为主数据库，替代MongoDB。

Rationale

决策依据

{if provided by user or inferred from conversation}

{如果用户提供或从对话中推断}

Context

上下文

{surrounding conversation context}

{对话的相关上下文}

Related Memories

Last Updated

最后更新时间

2025-10-17T17:45:00Z


**Step 6**: Confirm to user

✅ Remembered: Using PostgreSQL as primary database 📁 Saved to: decisions/{uuid}.md 🏷️ Tags: database, postgresql, backend 📊 Total memories: {N+1}

undefined

2025-10-17T17:45:00Z


**步骤6**：向用户确认

✅ 已记住：使用PostgreSQL作为主数据库 📁 保存至：decisions/{uuid}.md 🏷️ 标签：database, postgresql, backend 📊 总记忆数：{N+1}

undefined

2. Recall Memory

2. 召回记忆

When user asks "what did we decide about [topic]":

Step 1: Parse query

Extract keywords: "decide" → search DECISION type
Extract topic: "database" → search tags/content

Step 2: Search index

javascript

// Priority order:
1. Exact tag match in requested project
2. Exact tag match in any project
3. Partial content match in requested project
4. Partial content match in any project

// Sort by:
1. Relevance (exact match > partial)
2. Recency (newer > older)
3. Type priority (BLOCKER > DECISION > others)

Step 3: Load detailed memory files

bash

undefined

当用户询问“我们关于[主题]的决策是什么”时：

步骤1：解析查询

提取关键词：“decide” → 搜索DECISION类型
提取主题：“database” → 搜索标签/内容

步骤2：搜索索引

javascript

// 优先级顺序：
1. 指定项目中的精确标签匹配
2. 任意项目中的精确标签匹配
3. 指定项目中的部分内容匹配
4. 任意项目中的部分内容匹配

// 排序规则：
1. 相关性（精确匹配 > 部分匹配）
2. 时间远近（最新 > 较旧）
3. 类型优先级（BLOCKER > DECISION > 其他类型）

步骤3：加载详细记忆文件

bash

undefined

For each matching UUID

针对每个匹配的UUID

cat ~/.claude-memories/decisions/{uuid}.md

Windows PowerShell:

Windows PowerShell：

Get-Content "$env:USERPROFILE.claude-memories\decisions{uuid}.md"


**Step 4**: Present results

🔍 Found 3 memories about "database":

DECISION: Using PostgreSQL (2 days ago) 📁 Project: BOOSTBOX 💡 Using PostgreSQL as primary database instead of MongoDB 🔗 decisions/abc-123.md
DECISION: Database schema design (5 days ago) 📁 Project: BOOSTBOX 💡 User table with UUID primary keys 🔗 decisions/def-456.md
PREFERENCE: Prefer migrations over raw SQL (1 week ago) 📁 All projects 💡 Always use migration files, never direct SQL schema changes 🔗 preferences/ghi-789.md

Would you like details on any of these?

undefined


**步骤4**：展示结果

🔍 找到3条关于“database”的记忆：

DECISION: Using PostgreSQL（2天前） 📁 项目: BOOSTBOX 💡 使用PostgreSQL作为主数据库替代MongoDB 🔗 decisions/abc-123.md
DECISION: Database schema design（5天前） 📁 项目: BOOSTBOX 💡 用户表使用UUID作为主键 🔗 decisions/def-456.md
PREFERENCE: Prefer migrations over raw SQL（1周前） 📁 所有项目 💡 始终使用迁移文件，绝不直接修改SQL schema 🔗 preferences/ghi-789.md

需要查看其中任意条目的详细内容吗？

undefined

3. Track Blockers

3. 追踪障碍

Auto-detect blockers:

User says: "I can't", "it won't work", "stuck on"
Error messages that can't be immediately fixed
Missing credentials/access
External dependencies not ready

Proactive save:

🚧 Detected blocker: API credentials not available

Saving as BLOCKER for tracking.

When this is resolved, say "blocker resolved: [brief description]"

Blocker resolution:

User: "blocker resolved: got API credentials"

✅ Blocker resolved: API credentials not available
📝 Updated memory with resolution timestamp
⏱️ Blocked for: 2 days 4 hours

自动检测障碍：

用户说：“我无法”、“这行不通”、“卡在”
无法立即修复的错误信息
缺少凭证/权限
外部依赖未就绪

主动保存：

🚧 检测到障碍：API凭证不可用

将保存为BLOCKER进行追踪。

问题解决后，请说“障碍已解决：[简要描述]”

障碍解决：

用户: "障碍已解决：获取到API凭证"

✅ 障碍已解决：API凭证不可用
📝 已更新记忆并添加解决时间戳
⏱️ 持续阻塞时长：2天4小时

4. Search Memories

4. 搜索记忆

Support rich queries:

"search memories for auth" → Full-text search
"show all blockers" → Filter by type
"what did we decide this week" → Time-filtered DECISION
"boostbox decisions" → Project + type filter
"show preferences" → Type filter

Search syntax:

Basic: "search [topic]"
Type filter: "search decisions about [topic]"
Project filter: "search boostbox [topic]"
Time filter: "search [topic] this week|month|today"
Combined: "search boostbox decisions about database this week"

支持丰富的查询方式：

"search memories for auth" → 全文搜索
"show all blockers" → 按类型筛选
"what did we decide this week" → 按时间筛选DECISION
"boostbox decisions" → 项目+类型筛选
"show preferences" → 类型筛选

搜索语法：

基础搜索: "search [主题]"
类型筛选: "search decisions about [主题]"
项目筛选: "search boostbox [主题]"
时间筛选: "search [主题] this week|month|today"
组合筛选: "search boostbox decisions about database this week"

Memory Types Deep Dive

记忆类型深入解析

DECISION

DECISION（决策）

When to save:

Tech stack choices ("using React", "chose PostgreSQL")
Architecture decisions ("microservices vs monolith")
Design patterns ("using repository pattern")
Library selections ("using Tailwind CSS")

Structure:

markdown

undefined

保存时机:

技术栈选择（“使用React”、“选择PostgreSQL”）
架构决策（“微服务vs单体架构”）
设计模式（“使用仓库模式”）
库选型（“使用Tailwind CSS”）

结构:

markdown

undefined

DECISION: {title}

DECISION: {标题}

What we decided

决策内容

{the decision}

{具体决策}

Why

决策原因

{rationale - infer from conversation}

{决策依据——从对话中推断}

Alternatives considered

备选方案

{if discussed}

{如果有讨论过}

Impact

影响范围

{affected areas}

undefined

{受影响的领域}

undefined

BLOCKER

BLOCKER（障碍）

When to save:

Can't access resource (API, database, server)
Missing dependencies (libraries, services)
External blockers (waiting on someone)
Technical issues (bug preventing progress)

Structure:

markdown

undefined

保存时机:

无法访问资源（API、数据库、服务器）
缺少依赖（库、服务）
外部障碍（等待他人配合）
技术问题（阻碍进展的bug）

结构:

markdown

undefined

BLOCKER: {title}

BLOCKER: {标题}

Issue

问题描述

{what's blocking}

{具体阻塞内容}

Impact

影响

{what can't be done}

{无法进行的工作}

Workarounds tried

已尝试的解决方法

{if any}

{如果有}

Status

状态

Active | Resolved | Bypassed

活跃 | 已解决 | 已绕过

Resolution (when resolved)

解决情况（问题解决后填写）

{how it was fixed} {timestamp of resolution}

undefined

{解决方式} {解决时间戳}

undefined

CONTEXT

CONTEXT（上下文）

When to save:

Project background ("this is for BOOSTBOX")
Requirements ("must support offline mode")
Constraints ("can't use paid services")
Business rules ("users can't delete posts")

保存时机:

项目背景（“这是BOOSTBOX项目的内容”）
需求（“必须支持离线模式”）
约束条件（“不能使用付费服务”）
业务规则（“用户无法删除帖子”）

PREFERENCE

PREFERENCE（偏好）

When to save:

Coding style ("prefer const over let")
File organization ("components in src/components/")
Testing approach ("always unit test utilities")
Documentation style ("JSDoc for all public functions")

保存时机:

编码风格（“偏好const而非let”）
文件组织（“组件放在src/components/目录下”）
测试方式（“始终为工具类编写单元测试”）
文档风格（“所有公共函数使用JSDoc”）

PROCEDURE

PROCEDURE（流程）

When to save:

Deployment process
Build commands
Testing workflows
Release checklists

Structure:

markdown

undefined

保存时机:

部署流程
构建命令
测试工作流
发布检查清单

结构:

markdown

undefined

PROCEDURE: {title}

PROCEDURE: {标题}

When to use

使用场景

{triggering condition}

{触发条件}

Steps

步骤

{step 1}
{step 2}
{step 3}

{步骤1}
{步骤2}
{步骤3}

Expected outcome

预期结果

{what success looks like}

{成功的标志}

Troubleshooting

故障排除

{common issues}

undefined

{常见问题}

undefined

NOTE

NOTE（笔记）

When to save:

General observations
Reminders
Ideas for later
Links to resources

保存时机:

通用观察结果
提醒事项
后续想法
资源链接

Time Anchoring (for Dyschronometria)

时间锚定（针对时间感知障碍用户）

Always provide:

Absolute timestamp: ISO 8601 format
Relative time: "2 hours ago", "3 days ago", "last Tuesday"
Context anchor: "Before we added authentication", "After the redesign"

Time utilities:

javascript

function relativeTime(timestamp) {
  const now = Date.now();
  const then = new Date(timestamp).getTime();
  const diff = now - then;

  const minutes = Math.floor(diff / 60000);
  const hours = Math.floor(diff / 3600000);
  const days = Math.floor(diff / 86400000);

  if (minutes < 60) return `${minutes} minutes ago`;
  if (hours < 24) return `${hours} hours ago`;
  if (days < 7) return `${days} days ago`;
  if (days < 30) return `${Math.floor(days/7)} weeks ago`;
  return `${Math.floor(days/30)} months ago`;
}

始终提供:

绝对时间戳：ISO 8601格式
相对时间：“2小时前”、“3天前”、“上周二”
上下文锚点：“在我们添加认证之前”、“重新设计之后”

时间工具函数:

javascript

function relativeTime(timestamp) {
  const now = Date.now();
  const then = new Date(timestamp).getTime();
  const diff = now - then;

  const minutes = Math.floor(diff / 60000);
  const hours = Math.floor(diff / 3600000);
  const days = Math.floor(diff / 86400000);

  if (minutes < 60) return `${minutes} minutes ago`;
  if (hours < 24) return `${hours} hours ago`;
  if (days < 7) return `${days} days ago`;
  if (days < 30) return `${Math.floor(days/7)} weeks ago`;
  return `${Math.floor(days/30)} months ago`;
}

Memory Index Structure

记忆索引结构

Core Index File

核心索引文件

~/.claude-memories/index.json

(Linux/macOS) or

%USERPROFILE%\.claude-memories\index.json

(Windows):

json

{
  "version": "1.0.0",
  "created": "ISO8601",
  "last_updated": "ISO8601",
  "total_memories": 0,
  "memories_by_type": {
    "DECISION": 0,
    "BLOCKER": 0,
    "CONTEXT": 0,
    "PREFERENCE": 0,
    "PROCEDURE": 0,
    "NOTE": 0
  },
  "memories": [
    {
      "id": "uuid",
      "type": "DECISION|BLOCKER|CONTEXT|PREFERENCE|PROCEDURE|NOTE",
      "content": "brief summary",
      "timestamp": "ISO8601",
      "tags": ["tag1", "tag2"],
      "project": "project-name",
      "status": "active|resolved|archived",
      "context": {
        "file": "optional-file-path",
        "line": "optional-line-number"
      }
    }
  ],
  "tags_index": {
    "tag-name": ["uuid1", "uuid2"]
  },
  "project_index": {
    "project-name": ["uuid1", "uuid2"]
  },
  "session_index": {
    "session-id": ["uuid1", "uuid2"]
  }
}

~/.claude-memories/index.json

（Linux/macOS）或

%USERPROFILE%\.claude-memories\index.json

（Windows）：

json

{
  "version": "1.0.0",
  "created": "ISO8601",
  "last_updated": "ISO8601",
  "total_memories": 0,
  "memories_by_type": {
    "DECISION": 0,
    "BLOCKER": 0,
    "CONTEXT": 0,
    "PREFERENCE": 0,
    "PROCEDURE": 0,
    "NOTE": 0
  },
  "memories": [
    {
      "id": "uuid",
      "type": "DECISION|BLOCKER|CONTEXT|PREFERENCE|PROCEDURE|NOTE",
      "content": "brief summary",
      "timestamp": "ISO8601",
      "tags": ["tag1", "tag2"],
      "project": "project-name",
      "status": "active|resolved|archived",
      "context": {
        "file": "optional-file-path",
        "line": "optional-line-number"
      }
    }
  ],
  "tags_index": {
    "tag-name": ["uuid1", "uuid2"]
  },
  "project_index": {
    "project-name": ["uuid1", "uuid2"]
  },
  "session_index": {
    "session-id": ["uuid1", "uuid2"]
  }
}

Directory Structure

目录结构

~/.claude-memories/  (Linux/macOS) or %USERPROFILE%\.claude-memories\ (Windows)
├── index.json                 # Master index
├── decisions/                 # Architecture decisions
│   ├── {uuid1}.md
│   └── {uuid2}.md
├── blockers/                  # Active/resolved blockers
│   ├── {uuid3}.md
│   └── {uuid4}.md
├── context/                   # Project context
│   ├── {uuid5}.md
│   └── {uuid6}.md
├── preferences/               # User preferences
│   ├── {uuid7}.md
│   └── {uuid8}.md
├── procedures/                # How-to procedures
│   ├── {uuid9}.md
│   └── {uuid10}.md
├── notes/                     # General notes
│   ├── {uuid11}.md
│   └── {uuid12}.md
├── sessions/                  # Session summaries
│   ├── 2025-10-17.md
│   └── 2025-10-16.md
└── backups/                   # Daily backups
    ├── index-2025-10-17.json
    └── index-2025-10-16.json

~/.claude-memories/  (Linux/macOS) 或 %USERPROFILE%\.claude-memories\ (Windows)
├── index.json                 # 主索引
├── decisions/                 # 架构决策
│   ├── {uuid1}.md
│   └── {uuid2}.md
├── blockers/                  # 活跃/已解决的障碍
│   ├── {uuid3}.md
│   └── {uuid4}.md
├── context/                   # 项目上下文
│   ├── {uuid5}.md
│   └── {uuid6}.md
├── preferences/               # 用户偏好
│   ├── {uuid7}.md
│   └── {uuid8}.md
├── procedures/                # 操作流程
│   ├── {uuid9}.md
│   └── {uuid10}.md
├── notes/                     # 通用笔记
│   ├── {uuid11}.md
│   └── {uuid12}.md
├── sessions/                  # 会话摘要
│   ├── 2025-10-17.md
│   └── 2025-10-16.md
└── backups/                   # 每日备份
    ├── index-2025-10-17.json
    └── index-2025-10-16.json

Integration with Other Skills

与其他技能的集成

Session Launcher

会话启动器

Provides memories for session restoration:

Recent decisions (last 7 days)
Active blockers
Project context
Session summaries

为会话恢复提供记忆内容：

近期决策（过去7天）
活跃障碍
项目上下文
会话摘要

Error Debugger

错误调试器

Searches memories for:

Similar past errors
Solutions that worked
Known blockers
Relevant procedures

在记忆中搜索：

类似的过往错误
有效的解决方案
已知障碍
相关流程

Testing Builder

测试构建器

Recalls preferences:

Testing style (unit/integration/E2E)
Coverage requirements
Test framework choices
Mocking preferences

召回偏好设置：

测试类型（单元/集成/E2E）
覆盖率要求
测试框架选择
模拟偏好

Deployment Orchestrator

部署编排器

Loads procedures:

Deployment workflows
Environment configurations
Rollback procedures
Checklist items

加载流程内容：

部署工作流
环境配置
回滚流程
检查清单项

Proactive Memory Saving

主动保存记忆

Auto-save memories in these situations:

During architecture discussions:

User: "Let's use React for the frontend"
→ Auto-save as DECISION: Using React for frontend

When encountering blockers:

User: "Can't connect to the API"
→ Auto-save as BLOCKER: API connection failing

When establishing preferences:

User: "I prefer TypeScript over JavaScript"
→ Auto-save as PREFERENCE: Prefer TypeScript

When creating procedures:

User: "To deploy: run npm build then copy to server"
→ Auto-save as PROCEDURE: Deployment process

Always confirm:

💾 Saved as DECISION: Using React for frontend
(say "undo" within 30 seconds to cancel)

在以下场景自动保存记忆：

架构讨论期间:

用户: "我们前端用React吧"
→ 自动保存为DECISION: 前端使用React

遇到障碍时:

用户: "无法连接到API"
→ 自动保存为BLOCKER: API连接失败

设置偏好时:

用户: "我偏好TypeScript而非JavaScript"
→ 自动保存为PREFERENCE: 偏好TypeScript

创建流程时:

用户: "部署步骤：先运行npm build再复制到服务器"
→ 自动保存为PROCEDURE: 部署流程

始终进行确认:

💾 已保存为DECISION: 前端使用React
（30秒内说“撤销”可取消保存）

Backup Strategy

备份策略

Daily backups:

bash

undefined

每日备份:

bash

undefined

Every 24 hours, create backup

每24小时创建一次备份

Linux/macOS:

cp ~/.claude-memories/index.json
~/.claude-memories/backups/index-$(date +%Y-%m-%d).json

Windows PowerShell:

Copy-Item "$env:USERPROFILE.claude-memories\index.json" `

"$env:USERPROFILE.claude-memories\backups\index-$(Get-Date -Format 'yyyy-MM-dd').json"

Keep last 30 days (Linux/macOS):

保留最近30天的备份（Linux/macOS）:

find ~/.claude-memories/backups/ -name "index-*.json" -mtime +30 -delete

Windows PowerShell:

Get-ChildItem "$env:USERPROFILE.claude-memories\backups\index-*.json" |

Where-Object {$_.LastWriteTime -lt (Get-Date).AddDays(-30)} | Remove-Item


**Corruption recovery**:
```bash


**损坏恢复**:
```bash

If index.json corrupted, restore from backup

如果index.json损坏，从备份恢复

Linux/macOS:

cp ~/.claude-memories/backups/index-$(date -d yesterday +%Y-%m-%d).json
~/.claude-memories/index.json

Windows PowerShell:

Copy-Item "$env:USERPROFILE.claude-memories\backups\index-$(Get-Date (Get-Date).AddDays(-1) -Format 'yyyy-MM-dd').json" `

"$env:USERPROFILE.claude-memories\index.json"

undefined

undefined

Quick Reference

快速参考

Common Commands

常用指令

User Says	Action
"remember we're using PostgreSQL"	Save as DECISION
"what did we decide about the database"	Search DECISIONs for "database"
"show all blockers"	List active BLOCKERs
"any blockers?"	Quick blocker check
"remember I prefer functional components"	Save as PREFERENCE
"search memories for authentication"	Full-text search
"blocker resolved: got API key"	Mark blocker as resolved

用户指令	操作
"记住我们使用PostgreSQL"	保存为DECISION
"我们关于数据库的决策是什么"	搜索与“database”相关的DECISION
"显示所有障碍"	列出活跃的BLOCKER
"有障碍吗？"	快速检查障碍
"记住我偏好函数式组件"	保存为PREFERENCE
"搜索记忆中的认证相关内容"	全文搜索
"障碍已解决：获取到API密钥"	将障碍标记为已解决

File Paths

文件路径

Index:

~/.claude-memories/index.json

(Linux/macOS) or

%USERPROFILE%\.claude-memories\index.json

(Windows)

Decisions:

~/.claude-memories/decisions/{uuid}.md

%USERPROFILE%\.claude-memories\decisions\{uuid}.md

Blockers:

~/.claude-memories/blockers/{uuid}.md

%USERPROFILE%\.claude-memories\blockers\{uuid}.md

Backups:

~/.claude-memories/backups/

%USERPROFILE%\.claude-memories\backups\

索引文件:

~/.claude-memories/index.json

（Linux/macOS）或

%USERPROFILE%\.claude-memories\index.json

（Windows）

决策文件:

~/.claude-memories/decisions/{uuid}.md

或

%USERPROFILE%\.claude-memories\decisions\{uuid}.md

障碍文件:

~/.claude-memories/blockers/{uuid}.md

或

%USERPROFILE%\.claude-memories\blockers\{uuid}.md

备份目录:

~/.claude-memories/backups/

或

%USERPROFILE%\.claude-memories\backups\

Memory Lifecycle

记忆生命周期

Create: User says "remember" or auto-detected
Store: Added to index + detailed file created
Recall: Searched by keywords/tags/type/project
Update: Can be edited if context changes
Archive: Old memories archived but never deleted

创建: 用户说“记住”或系统自动检测
存储: 添加到索引并创建详细文件
召回: 通过关键词/标签/类型/项目搜索
更新: 上下文变化时可编辑
归档: 旧记忆会归档但永不删除

Success Criteria

成功标准

✅ User never has to remember decisions ✅ "What did we decide?" is always answerable ✅ Blockers are tracked automatically ✅ All context is time-anchored ✅ Memory search returns relevant results in <1 second ✅ Zero reliance on user's biological memory

✅ 用户无需再记住决策内容 ✅ “我们之前决定了什么？”总能得到答案 ✅ 障碍被自动追踪 ✅ 所有上下文都带有时间锚定 ✅ 记忆搜索在1秒内返回相关结果 ✅ 完全不依赖用户的生理记忆

context-manager

Original

Translation

Context Manager

上下文管理器

Purpose

目的

Activation Triggers

触发条件

Core Workflow

核心工作流

1. Save Memory

1. 保存记忆

Cross-platform: Use $HOME (Linux/macOS) or %USERPROFILE% (Windows)

跨平台：Linux/macOS使用$HOME，Windows使用%USERPROFILE%

Windows PowerShell alternative:

Windows PowerShell替代命令：

Get-Content "$env:USERPROFILE.claude-memories\index.json"

Get-Content "$env:USERPROFILE.claude-memories\index.json"

Save to category-specific directory

保存到对应类型的目录

Linux/macOS: ~/.claude-memories/decisions/{uuid}.md

Linux/macOS: ~/.claude-memories/decisions/{uuid}.md

Windows: %USERPROFILE%.claude-memories\decisions{uuid}.md

Windows: %USERPROFILE%.claude-memories\decisions{uuid}.md

DECISION: Using PostgreSQL

DECISION: Using PostgreSQL

Decision

决策内容

Rationale

决策依据

Context

上下文

Related Memories

相关记忆

Last Updated

最后更新时间

2. Recall Memory

2. 召回记忆

For each matching UUID

针对每个匹配的UUID

Windows PowerShell:

Windows PowerShell：

Get-Content "$env:USERPROFILE.claude-memories\decisions{uuid}.md"

Get-Content "$env:USERPROFILE.claude-memories\decisions{uuid}.md"

3. Track Blockers

3. 追踪障碍

4. Search Memories

4. 搜索记忆

Memory Types Deep Dive

记忆类型深入解析

DECISION

DECISION（决策）

DECISION: {title}

DECISION: {标题}

What we decided

决策内容

Why

决策原因

Alternatives considered

备选方案

Impact

影响范围

BLOCKER

BLOCKER（障碍）

BLOCKER: {title}

BLOCKER: {标题}

Issue

问题描述

Impact

影响

Workarounds tried

已尝试的解决方法

Status

状态

Resolution (when resolved)

解决情况（问题解决后填写）

CONTEXT

CONTEXT（上下文）

PREFERENCE