Back to Details

knowledge-ops

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Knowledge Operations

知识运营

Manage a multi-layered knowledge system for ingesting, organizing, syncing, and retrieving knowledge across multiple stores.
Prefer the live workspace model:
  • code work lives in the real cloned repos
  • active execution context lives in GitHub, Linear, and repo-local working-context files
  • broader human-facing notes can live in a non-repo context/archive folder
  • durable cross-machine memory belongs in the knowledge base, not in a shadow repo workspace
管理多层级知识体系，实现跨多存储源的知识摄入、整理、同步与检索。
推荐使用实时工作区模式：
  • 代码工作内容存放在实际克隆的仓库中
  • 活跃执行上下文存放在 GitHub、Linear 和仓库本地工作上下文文件中
  • 面向用户的通用笔记可存放在非仓库上下文/归档文件夹中
  • 持久化跨设备内存属于知识库，而非影子仓库工作区

When to Activate

何时启用

  • User wants to save information to their knowledge base
  • Ingesting documents, conversations, or data into structured storage
  • Syncing knowledge across systems (local files, MCP memory, Supabase, Git repos)
  • Deduplicating or organizing existing knowledge
  • User says "save this to KB", "sync knowledge", "what do I know about X", "ingest this", "update the knowledge base"
  • Any knowledge management task beyond simple memory recall
  • 用户需要将信息保存到知识库
  • 将文档、对话或数据摄入到结构化存储中
  • 跨系统同步知识（本地文件、MCP memory、Supabase、Git 仓库）
  • 对现有知识进行去重或整理
  • 用户说「把这个保存到KB」、「同步知识」、「我有哪些关于X的信息」、「摄入这个内容」、「更新知识库」
  • 任何超出简单记忆召回的知识管理任务

Knowledge Architecture

知识架构

Layer 1: Active execution truth

第1层：活跃执行真实数据源

  • Sources: GitHub issues, PRs, discussions, release notes, Linear issues/projects/docs
  • Use for: the current operational state of the work
  • Rule: if something affects an active engineering plan, roadmap, rollout, or release, prefer putting it here first
  • 来源： GitHub issue、PR、讨论、发布说明、Linear issue/项目/文档
  • 适用场景： 工作的当前运营状态
  • 规则： 如果内容会影响活跃的工程计划、路线图、上线或发布，优先存放在这里

Layer 2: Claude Code Memory (Quick Access)

第2层：Claude Code Memory（快速访问）

  • Path: 
    ~/.claude/projects/*/memory/
  • Format: Markdown files with frontmatter
  • Types: user preferences, feedback, project context, reference
  • Use for: quick-access context that persists across conversations
  • Automatically loaded at session start
  • 路径： 
    ~/.claude/projects/*/memory/
  • 格式： 带frontmatter的Markdown文件
  • 类型： 用户偏好、反馈、项目上下文、参考资料
  • 适用场景： 跨会话持久化的快速访问上下文
  • 会话启动时自动加载

Layer 3: MCP Memory Server (Structured Knowledge Graph)

第3层：MCP Memory Server（结构化知识图谱）

  • Access: MCP memory tools (create_entities, create_relations, add_observations, search_nodes)
  • Use for: Semantic search across all stored memories, relationship mapping
  • Cross-session persistence with queryable graph structure
  • 访问方式： MCP memory工具（create_entities、create_relations、add_observations、search_nodes）
  • 适用场景： 所有存储记忆的语义搜索、关系映射
  • 带可查询图谱结构的跨会话持久化

Layer 4: Knowledge base repo / durable document store

第4层：知识库仓库/持久化文档存储

  • Use for: curated durable notes, session exports, synthesized research, operator memory, long-form docs
  • Rule: this is the preferred durable store for cross-machine context when the content is not repo-owned code
  • 适用场景： 经过整理的持久化笔记、会话导出、合成研究成果、运营记忆、长文档
  • 规则： 当内容不属于仓库所有的代码时，这里是跨设备上下文首选的持久化存储位置

Layer 5: External Data Store (Supabase, PostgreSQL, etc.)

第5层：外部数据存储（Supabase、PostgreSQL等）

  • Use for: Structured data, large document storage, full-text search
  • Good for: Documents too large for memory files, data needing SQL queries
  • 适用场景： 结构化数据、大型文档存储、全文搜索
  • 优势： 适合存储超出内存文件大小限制的文档、需要SQL查询的数据

Layer 6: Local context/archive folder

第6层：本地上下文/归档文件夹

  • Use for: human-facing notes, archived gameplans, local media organization, temporary non-code docs
  • Rule: writable for information storage, but not a shadow code workspace
  • Do not use for: active code changes or repo truth that should live upstream
  • 适用场景： 面向用户的笔记、已归档的方案、本地媒体整理、临时非代码文档
  • 规则： 可写入用于信息存储，但不作为影子代码工作区
  • 禁止用于： 应该存放在上游的活跃代码变更或仓库真实数据源

Ingestion Workflow

摄入工作流

When new knowledge needs to be captured:
当需要捕获新知识时：

1. Classify

1. 分类

What type of knowledge is it?
  • Business decision -> memory file (project type) + MCP memory
  • Active roadmap / release / implementation state -> GitHub + Linear first
  • Personal preference -> memory file (user/feedback type)
  • Reference info -> memory file (reference type) + MCP memory
  • Large document -> external data store + summary in memory
  • Conversation/session -> knowledge base repo + short summary in memory
判断知识类型：
  • 业务决策 -> 内存文件（项目类型） + MCP memory
  • 活跃路线图/发布/实现状态 -> 优先存放到GitHub + Linear
  • 个人偏好 -> 内存文件（用户/反馈类型）
  • 参考信息 -> 内存文件（参考类型） + MCP memory
  • 大型文档 -> 外部数据存储 + 内存中存放摘要
  • 对话/会话 -> 知识库仓库 + 内存中存放简短摘要

2. Deduplicate

2. 去重

Check if this knowledge already exists:
  • Search memory files for existing entries
  • Query MCP memory with relevant terms
  • Check whether the information already exists in GitHub or Linear before creating another local note
  • Do not create duplicates. Update existing entries instead.
检查该知识是否已存在：
  • 搜索内存文件中的现有条目
  • 使用相关关键词查询MCP memory
  • 创建新的本地笔记前，先检查GitHub或Linear中是否已有该信息
  • 不要创建重复内容，优先更新现有条目

3. Store

3. 存储

Write to appropriate layer(s):
  • Always update Claude Code memory for quick access
  • Use MCP memory for semantic searchability and relationship mapping
  • Update GitHub / Linear first when the information changes live project truth
  • Commit to the knowledge base repo for durable long-form additions
写入到合适的层级：
  • 始终更新Claude Code Memory以便快速访问
  • 使用MCP memory实现语义搜索能力和关系映射
  • 当信息会变更实时项目真实数据源时，优先更新GitHub / Linear
  • 持久化的长内容新增提交到知识库仓库

4. Index

4. 索引

Update any relevant indexes or summary files.
更新所有相关的索引或摘要文件

Sync Operations

同步操作

Conversation Sync

对话同步

Periodically sync conversation history into the knowledge base:
  • Sources: Claude session files, Codex sessions, other agent sessions
  • Destination: knowledge base repo
  • Generate a session index for quick browsing
  • Commit and push
定期将会话历史同步到知识库：
  • 来源：Claude会话文件、Codex会话、其他Agent会话
  • 目标：知识库仓库
  • 生成会话索引便于快速浏览
  • 提交并推送

Workspace State Sync

工作区状态同步

Mirror important workspace configuration and scripts to the knowledge base:
  • Generate directory maps
  • Redact sensitive config before committing
  • Track changes over time
  • Do not treat the knowledge base or archive folder as the live code workspace
将重要的工作区配置和脚本镜像到知识库：
  • 生成目录映射
  • 提交前脱敏敏感配置
  • 跟踪历史变更
  • 不要将知识库或归档文件夹当做实时代码工作区

GitHub / Linear Sync

GitHub / Linear同步

When the information affects active execution:
  • update the relevant GitHub issue, PR, discussion, release notes, or roadmap thread
  • attach supporting docs to Linear when the work needs durable planning context
  • only mirror a local note afterwards if it still adds value
当信息会影响活跃执行时：
  • 更新相关的GitHub issue、PR、讨论、发布说明或路线图线程
  • 当工作需要持久化规划上下文时，将支撑文档附加到Linear
  • 仅当本地笔记仍有额外价值时，再做镜像留存

Cross-Source Knowledge Sync

跨源知识同步

Pull knowledge from multiple sources into one place:
  • Claude/ChatGPT/Grok conversation exports
  • Browser bookmarks
  • GitHub activity events
  • Write status summary, commit and push
将多个来源的知识聚合到同一位置：
  • Claude/ChatGPT/Grok对话导出内容
  • 浏览器书签
  • GitHub活动事件
  • 编写状态摘要，提交并推送

Memory Patterns

记忆模式

undefined
undefined

Short-term: current session context

Short-term: current session context

Use TodoWrite for in-session task tracking
Use TodoWrite for in-session task tracking

Medium-term: project memory files

Medium-term: project memory files

Write to ~/.claude/projects/*/memory/ for cross-session recall
Write to ~/.claude/projects/*/memory/ for cross-session recall

Long-term: GitHub / Linear / KB

Long-term: GitHub / Linear / KB

Put active execution truth in GitHub + Linear Put durable synthesized context in the knowledge base repo
Put active execution truth in GitHub + Linear Put durable synthesized context in the knowledge base repo

Semantic layer: MCP knowledge graph

Semantic layer: MCP knowledge graph

Use mcp__memory__create_entities for permanent structured data Use mcp__memory__create_relations for relationship mapping Use mcp__memory__add_observations for new facts about known entities Use mcp__memory__search_nodes to find existing knowledge
undefined
Use mcp__memory__create_entities for permanent structured data Use mcp__memory__create_relations for relationship mapping Use mcp__memory__add_observations for new facts about known entities Use mcp__memory__search_nodes to find existing knowledge
undefined

Best Practices

最佳实践

  • Keep memory files concise. Archive old data rather than letting files grow unbounded.
  • Use frontmatter (YAML) for metadata on all knowledge files.
  • Deduplicate before storing. Search first, then create or update.
  • Prefer one canonical home per fact set. Avoid parallel copies of the same plan across local notes, repo files, and tracker docs.
  • Redact sensitive information (API keys, passwords) before committing to Git.
  • Use consistent naming conventions for knowledge files (lowercase-kebab-case).
  • Tag entries with topics/categories for easier retrieval.
  • 保持内存文件简洁，归档旧数据而不是让文件无限制增长
  • 所有知识文件使用frontmatter（YAML）存放元数据
  • 存储前先去重，先搜索，再创建或更新
  • 每组事实优先使用唯一规范存储位置，避免在本地笔记、仓库文件和跟踪器文档中同时存放同一计划的并行副本
  • 提交到Git前脱敏敏感信息（API密钥、密码）
  • 知识文件使用统一命名规范（小写短横线分隔命名）
  • 为条目添加主题/分类标签便于检索

Quality Gate

质量校验

Before completing any knowledge operation:
  • no duplicate entries created
  • sensitive data redacted from any Git-tracked files
  • indexes and summaries updated
  • appropriate storage layer chosen for the data type
  • cross-references added where relevant
完成任何知识操作前确认：
  • 未创建重复条目
  • 所有Git跟踪文件中的敏感数据已脱敏
  • 索引和摘要已更新
  • 为数据类型选择了合适的存储层
  • 相关位置已添加交叉引用