context-network

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Context Network Lifecycle

上下文网络生命周期

You help users build and maintain context networks—structured frameworks for organizing project knowledge that persist across sessions and support both human and agent work. Your role is to diagnose context network state, generate appropriate scaffolding, and coach users on content decisions.

你帮助用户构建和维护上下文网络——这是一种结构化框架，用于组织可跨会话留存的项目知识，为人类和Agent的工作提供支持。你的职责是诊断上下文网络状态、生成合适的架构模板，并指导用户进行内容决策。

Core Principle

核心原则

Context networks make relationships explicit. Implicit knowledge doesn't survive session boundaries. Structure enables discovery. The goal is not completeness but navigability.

上下文网络让关系显性化。 隐性知识无法跨会话留存，结构化的组织方式便于知识发现。我们的目标不是追求内容的完整性，而是确保可导航性。

Quick Reference

快速参考

Use this skill when:

Starting a new project that needs persistent context
Existing documentation feels scattered or hard to navigate
Agent effectiveness is degrading due to missing context
Context-retrospective identified gaps to address

Key states:

CN0: No Network - Project has no context network
CN1: Scattered Docs - Documentation exists but isn't organized as a network
CN2: Siloed Structure - Structure exists but connections missing
CN3: Navigation Broken - Connections exist but hard to traverse
CN4: Guidance Unclear - Structure works but agent instructions fail
CN5: Relationships Missing - Impacts/dependencies undocumented
CN6: Maintenance Failing - Network exists but drifts from reality

在以下场景中使用本技能：

启动需要持久上下文的新项目
现有文档杂乱无章或难以导航
因上下文缺失导致Agent效能下降
上下文回顾发现需要填补的知识缺口

关键状态：

CN0：无网络 - 项目尚未建立上下文网络
CN1：文档零散 - 存在文档但未以网络形式组织
CN2：结构孤立 - 有结构但缺少关联
CN3：导航失效 - 存在关联但难以遍历
CN4：指引模糊 - 结构可用但Agent指令失效
CN5：关系缺失 - 影响/依赖未被记录
CN6：维护失效 - 网络存在但与实际情况脱节

The States

各状态详情

State CN0: No Network

状态CN0：无网络

Symptoms: No

.context-network.md

file. No

context/

directory. Documentation scattered in README or absent entirely. Agent asks same questions each session.

Key Questions:

What type of project is this? (software, research, creative, personal knowledge)
Who will use this context? (solo, team, agents)
What's the expected lifespan?

Interventions:

Run Bootstrap Mode (see below)
Generate discovery file and initial structure
Coach on minimal viable content

症状： 不存在

.context-network.md

文件，无

context/

目录。文档零散分布在README中或完全缺失。Agent在每个会话中都会重复询问相同问题。

关键问题：

这是什么类型的项目？（软件、研究、创意、个人知识管理）
谁会使用该上下文？（个人、团队、Agent）
项目预期生命周期是多久？

干预措施：

运行初始化模式（见下文）
生成发现文件和初始结构
指导用户填充最小可行内容

State CN1: Scattered Docs

状态CN1：文档零散

Symptoms: README.md has grown unwieldy. docs/ folder exists but files aren't connected. Architecture decisions buried in comments or commit messages. Agent finds partial info but misses connections.

Key Questions:

What documentation already exists?
Which docs are still accurate?
What relationships exist between these documents?

Interventions:

Scan for existing documentation
Propose migration plan to context network structure
Generate relationship mappings for migrated content

症状： README.md过于冗长，docs/文件夹存在但文件之间无关联。架构决策隐藏在注释或提交信息中。Agent只能找到部分信息，无法获取关联内容。

关键问题：

现有哪些文档？
哪些文档仍然准确有效？
这些文档之间存在哪些关系？

干预措施：

扫描现有文档
提出迁移至上下文网络结构的方案
为迁移内容生成关系映射

State CN2: Siloed Structure

状态CN2：结构孤立

Symptoms: Context network exists with clear directory structure. Files are well-organized within domains. But cross-references are sparse. Agent finds info within domains but misses cross-domain implications.

Key Questions:

Which domains affect each other?
What changes in A typically require changes in B?
Are there shared concepts with different names in different domains?

Interventions:

Generate relationship templates
Coach on identifying cross-domain connections
Create hub documents that bridge domains

症状： 上下文网络已存在，目录结构清晰。文件在各领域内组织有序，但跨领域引用稀少。Agent能在单个领域内找到信息，但无法发现跨领域的影响。

关键问题：

哪些领域之间相互影响？
A领域的哪些变更通常需要同步修改B领域？
不同领域中是否存在名称不同但概念相同的内容？

干预措施：

生成关系模板
指导用户识别跨领域关联
创建连接各领域的枢纽文档

State CN3: Navigation Broken

状态CN3：导航失效

Symptoms: Information exists and is connected, but hard to find. status.md is stale. No clear entry points for common tasks. Agent reads many files to find what it needs.

Key Questions:

What are the most common tasks agents perform?
Which files get read most often? Least often?
Are there orphan documents no one accesses?

Interventions:

Create/update hub documents
Establish task-based navigation guides
Prune or consolidate orphan content

症状： 信息存在且有关联，但难以查找。status.md内容过时。没有针对常见任务的明确入口。Agent需要读取大量文件才能找到所需信息。

关键问题：

Agent最常执行的任务是什么？
哪些文件的访问频率最高？最低？
是否存在无人访问的孤立文档？

干预措施：

创建/更新枢纽文档
建立基于任务的导航指南
清理或合并孤立内容

State CN4: Guidance Unclear

状态CN4：指引模糊

Symptoms: Context network is well-structured. CLAUDE.md exists but agents still make wrong decisions. Instructions exist but aren't followed. Agent behavior inconsistent with documented patterns.

Key Questions:

Which agent behaviors are problematic?
Are instructions ambiguous or contradictory?
Is guidance too abstract to act on?

Interventions:

Refine CLAUDE.md with specific, actionable instructions
Add examples to abstract guidance
Create decision trees for common choices

症状： 上下文网络结构完善。存在CLAUDE.md，但Agent仍会做出错误决策。有相关指令但未被遵循。Agent行为与文档记录的模式不一致。

关键问题：

Agent的哪些行为存在问题？
指令是否存在歧义或矛盾？
指引是否过于抽象而无法执行？

干预措施：

优化CLAUDE.md，添加具体、可执行的指令
为抽象指引补充示例
为常见决策场景创建决策树

State CN5: Relationships Missing

状态CN5：关系缺失

Symptoms: Changes in one area unexpectedly break another. Dependencies discovered mid-task. Impact of decisions unclear until after implementation. Agent doesn't know what else to check.

Key Questions:

What recent changes had unexpected ripple effects?
Which components share data, state, or interfaces?
What implicit contracts exist between areas?

Interventions:

Document dependency maps
Create impact relationship documentation
Add "affects" and "affected-by" sections to key nodes

症状： 某一领域的变更意外导致其他领域出现问题。在任务执行过程中才发现依赖关系。决策的影响在实施后才显现。Agent不知道还需要检查哪些内容。

关键问题：

近期哪些变更产生了意外的连锁反应？
哪些组件共享数据、状态或接口？
各领域之间存在哪些隐性约定？

干预措施：

记录依赖关系图
创建影响关系文档
在关键节点添加“影响”和“受影响于”章节

State CN6: Maintenance Failing

状态CN6：维护失效

Symptoms: Context network was once useful but now drifts from reality. status.md describes old state. Decisions documented but not updated. Agent references outdated information.

Key Questions:

When was the network last meaningfully updated?
What triggers should cause updates?
Who/what is responsible for maintenance?

Interventions:

Establish maintenance cadence
Define update triggers
Integrate with context-retrospective skill for continuous improvement

症状： 上下文网络曾经有用，但现在已与实际情况脱节。status.md描述的是旧状态。决策已记录但未更新。Agent引用过时信息。

关键问题：

网络上次有意义的更新是什么时候？
哪些触发条件应触发更新？
谁/哪个角色负责维护？

干预措施：

建立维护周期
定义更新触发条件
与上下文回顾技能集成以实现持续改进

Operational Modes

操作模式

Bootstrap Mode (CN0/CN1 → CN2)

初始化模式（CN0/CN1 → CN2）

Use when starting fresh or organizing scattered documentation.

Process:

适用于从零开始或整理零散文档的场景。

流程：

1. Existing Documentation Scan

1. 现有文档扫描

Automatically scan for:

```
README.md
```
,
```
docs/
```
,
```
documentation/
```
Architecture decision records (ADRs,
```
adr/
```
,
```
decisions/
```
)
Design docs, planning files
Package files (
```
package.json
```
,
```
Cargo.toml
```
,
```
pyproject.toml
```
) for project metadata
Existing
```
.claude/
```
or memory bank structures

Report findings:

Found existing documentation:
- README.md (2.3kb) - Project overview, setup instructions
- docs/architecture.md (5.1kb) - System design
- docs/api.md (3.2kb) - API reference

Recommendation: Migrate architecture.md to context/architecture/,
keep README.md in place as user-facing doc.

自动扫描以下内容：

```
README.md
```
、
```
docs/
```
、
```
documentation/
```
架构决策记录（ADRs、
```
adr/
```
、
```
decisions/
```
）
设计文档、规划文件
包文件（
```
package.json
```
、
```
Cargo.toml
```
、
```
pyproject.toml
```
）以获取项目元数据
现有
```
.claude/
```
或记忆库结构

报告扫描结果：

发现现有文档：
- README.md (2.3kb) - 项目概述、安装说明
- docs/architecture.md (5.1kb) - 系统设计
- docs/api.md (3.2kb) - API参考

建议：将architecture.md迁移至context/architecture/,
保留README.md作为面向用户的文档。

2. Project Discovery Questions

2. 项目探索问题

Ask:

Project type? Software / Research / Creative / Personal Knowledge
Primary domains? (For software: frontend, backend, data, infra, etc.)
Stakeholders? Solo / Team / Agents / Mixed
Expected lifespan? Short-term / Long-term / Indefinite
Which discovered docs to incorporate vs. leave in place?

询问以下问题：

项目类型？ 软件 / 研究 / 创意 / 个人知识管理
核心领域？（软件项目：前端、后端、数据、基础设施等）
利益相关者？ 个人 / 团队 / Agent / 混合
预期生命周期？ 短期 / 长期 / 无限期
哪些已发现的文档需要整合，哪些保持原样？

3. Structure Generation

3. 结构生成

Generate based on project type:

For software projects:

context/
├── status.md           # Current state, active work
├── decisions.md        # Architecture decisions
├── glossary.md         # Domain vocabulary
├── architecture/       # System design docs
├── domains/            # Domain-specific context
│   ├── [domain-1]/
│   └── [domain-2]/
└── processes/          # Workflows, procedures

For research projects:

context/
├── status.md           # Current research state
├── decisions.md        # Methodology decisions
├── glossary.md         # Technical vocabulary
├── sources/            # Source tracking
├── findings/           # Research discoveries
└── questions/          # Open questions, hypotheses

For creative projects:

context/
├── status.md           # Current project state
├── decisions.md        # Creative decisions
├── glossary.md         # World/project vocabulary
├── world/              # Worldbuilding, setting
├── characters/         # Character information
└── structure/          # Plot, outline, structure

For personal knowledge:

context/
├── status.md           # Current focus areas
├── decisions.md        # System decisions
├── glossary.md         # Personal vocabulary
├── areas/              # Life areas (PARA-style)
├── projects/           # Active projects
└── resources/          # Reference material

Also generate:

```
.context-network.md
```
discovery file in project root
```
CLAUDE.md
```
with basic agent instructions (if not present)

根据项目类型生成结构：

软件项目：

context/
├── status.md           # 当前状态、正在进行的工作
├── decisions.md        # 架构决策
├── glossary.md         # 领域术语表
├── architecture/       # 系统设计文档
├── domains/            # 领域特定上下文
│   ├── [domain-1]/
│   └── [domain-2]/
└── processes/          # 工作流、流程规范

研究项目：

context/
├── status.md           # 当前研究状态
├── decisions.md        # 方法论决策
├── glossary.md         # 技术术语表
├── sources/            # 来源追踪
├── findings/           # 研究发现
└── questions/          # 待解决问题、假设

创意项目：

context/
├── status.md           # 当前项目状态
├── decisions.md        # 创意决策
├── glossary.md         # 项目/世界观术语表
├── world/              # 世界观构建、场景设定
├── characters/         # 角色信息
└── structure/          # 情节、大纲、结构

个人知识管理：

context/
├── status.md           # 当前关注领域
├── decisions.md        # 系统决策
├── glossary.md         # 个人术语表
├── areas/              # 生活领域（PARA风格）
├── projects/           # 进行中的项目
└── resources/          # 参考资料

同时生成：

项目根目录下的
```
.context-network.md
```
发现文件
基础Agent指令文件
```
CLAUDE.md
```
（如果不存在）

4. Migration Execution

4. 迁移执行

For docs user wants to incorporate:

Copy/move to appropriate context network location
Convert format if needed (e.g., flatten ADRs into decisions.md entries)
Update internal cross-references
Add relationship metadata

对于用户选择整合的文档：

复制/移动至上下文网络的对应位置
如有需要转换格式（例如，将ADRs整合到decisions.md中）
更新内部交叉引用
添加关系元数据

5. Content Coaching

5. 内容指导

Guide user to populate:

status.md: Current state, recent changes, active work
decisions.md: Key decisions made, rationale, date
glossary.md: Project-specific terms, abbreviations
Relationships between migrated content

引导用户填充以下内容：

status.md：当前状态、近期变更、正在进行的工作
decisions.md：已做出的关键决策、决策依据、日期
glossary.md：项目特定术语、缩写
已迁移内容之间的关系

Maintenance Mode (CN2-CN6 → improved state)

维护模式（CN2-CN6 → 状态优化）

Use when network exists but needs improvement.

Process:

适用于网络已存在但需要改进的场景。

流程：

1. State Diagnosis

1. 状态诊断

Analyze:

Structure completeness: Required files present? Domains covered?
Relationship density: Cross-references per document? Orphan files?
Navigation paths: Clear entry points? Task-based routes?
Guidance clarity: CLAUDE.md actionable? Instructions followed?
Freshness: Last update dates? Stale content?

Produce diagnosis:

Current State: CN3 (Navigation Broken)

Findings:
- 23 context files, 8 with no incoming links (orphans)
- status.md last updated 3 weeks ago
- No task-based entry points defined
- Cross-domain relationships sparse (avg 1.2 per file)

Priority Issues:
1. [Critical] status.md is stale - blocks agent orientation
2. [High] 8 orphan files - content exists but undiscoverable
3. [Medium] Missing hub for API-related context

分析以下方面：

结构完整性：必要文件是否存在？是否覆盖所有领域？
关系密度：每个文档的交叉引用数量？是否存在孤立文件？
导航路径：是否有明确的入口？是否有基于任务的导航路线？
指引清晰度：CLAUDE.md是否可执行？指令是否被遵循？
新鲜度：最后更新日期？是否存在过时内容？

生成诊断报告：

当前状态：CN3（导航失效）

发现：
- 23个上下文文件，其中8个无入站链接（孤立文件）
- status.md最后更新于3周前
- 未定义基于任务的入口点
- 跨领域关联稀少（平均每个文件1.2个）

优先级问题：
1. [关键] status.md过时 - 阻碍Agent定位
2. [高优先级] 8个孤立文件 - 内容存在但无法被发现
3. [中优先级] 缺少API相关上下文的枢纽文档

2. Gap Identification

2. 缺口识别

Prioritize:

Critical: Blocking agent effectiveness (can't find what it needs)
High: Requires real-time discovery (agent has to search)
Medium: Would improve efficiency (extra steps to navigate)
Low: Nice-to-have (marginal improvement)

按优先级排序：

关键：阻碍Agent效能（无法找到所需内容）
高优先级：需要实时发现（Agent必须搜索）
中优先级：可提升效率（导航需要额外步骤）
低优先级：锦上添花（边际改进）

3. Intervention

3. 干预措施

Based on diagnosed state:

State	Generate	Coach
CN2	Relationship templates	How to identify connections
CN3	Hub documents, navigation guides	Task-based organization
CN4	CLAUDE.md refinements	Writing actionable instructions
CN5	Dependency map templates	Impact analysis process
CN6	Maintenance cadence doc	Update triggers, responsibilities

根据诊断状态执行：

状态	生成内容	指导方向
CN2	关系模板	如何识别关联
CN3	枢纽文档、导航指南	基于任务的组织方式
CN4	CLAUDE.md优化方案	编写可执行指令
CN5	依赖关系图模板	影响分析流程
CN6	维护周期文档	更新触发条件、职责划分

Retrospective Integration

回顾集成

Accept output from context-retrospective skill:

Import findings: Knowledge gaps, navigation issues, guidance assessments
Map to states: Which CN state do these findings indicate?
Prioritize: Use retrospective priority levels (Critical/High/Medium/Low)
Execute: Run appropriate maintenance mode interventions

接收上下文回顾技能的输出：

导入发现结果：知识缺口、导航问题、指引评估
映射到状态：这些发现对应哪个CN状态？
优先级排序：使用回顾技能的优先级等级（关键/高/中/低）
执行干预：运行相应的维护模式干预措施

Anti-Patterns

反模式

The Empty Scaffold

空架构

Pattern: Generating full directory structure but leaving files empty or with placeholder content only. Problem: Structure without content is worse than no structure—it creates false confidence that context exists. Fix: Generate only structure user commits to populating. Start with status.md and one domain. Expand as content accumulates.

模式： 生成完整的目录结构，但文件为空或仅包含占位符内容。 问题： 只有结构没有内容比没有结构更糟，会让人误以为上下文已存在。 解决方法： 仅生成用户承诺会填充内容的结构。从status.md和一个领域开始，随着内容积累逐步扩展。

The Kitchen Sink

大杂烩

Pattern: Initial network tries to anticipate every possible need. Complex taxonomies, deep hierarchies, elaborate metadata. Problem: Maintenance burden exceeds value. Network becomes intimidating. Users avoid updating it. Fix: Start minimal. Add structure only when pain emerges from its absence. Two levels of hierarchy maximum initially.

模式： 初始网络试图覆盖所有可能需求，包含复杂的分类、深层层级和繁琐的元数据。 问题： 维护成本超过价值，网络变得令人望而生畏，用户不愿更新。 解决方法： 从最小化结构开始，仅在因缺少结构而产生痛点时再添加。初始层级最多不超过两层。

The Orphan Network

孤立网络

Pattern: Creating network during initial enthusiasm, then never updating it. status.md frozen in time. Problem: Stale context is worse than no context—agents act on outdated information. Fix: Establish minimal maintenance triggers: update status.md at session start/end. Schedule periodic retrospectives.

模式： 在初始热情驱动下创建网络，之后从未更新。status.md内容停滞不前。 问题： 过时的上下文比没有上下文更糟——Agent会基于过时信息采取行动。 解决方法： 建立最小化维护触发条件：在会话开始/结束时更新status.md，定期安排回顾。

The Template Trap

模板陷阱

Pattern: Using templates without adaptation. Every file has same sections regardless of relevance. Problem: Boilerplate obscures actual content. Templates become noise to skip. Fix: Templates are starting points, not requirements. Delete irrelevant sections. Add project-specific ones.

模式： 不加调整地使用模板，每个文件都包含相同的章节，无论是否相关。 问题： 模板内容掩盖了实际信息，成为需要跳过的噪音。 解决方法： 模板只是起点而非要求。删除无关章节，添加项目特定的章节。

The Completeness Illusion

完整性幻觉

Pattern: Believing the network can/should capture everything. Adding more and more detail hoping to prevent all gaps. Problem: Signal-to-noise degrades. Navigation becomes impossible. Maintenance unsustainable. Fix: Focus on high-impact gaps. Document what agents actually need. Accept that some discovery will always be real-time.

模式： 认为网络能够/应该捕获所有信息，不断添加更多细节以试图消除所有缺口。 问题： 信号噪声比下降，导航变得不可能，维护无法持续。 解决方法： 专注于高影响的缺口，记录Agent实际需要的内容。接受部分知识发现必须实时进行的事实。

Verification (Oracle)

验证（校验机制）

What This Skill Can Verify

本技能可验证的内容

Structure completeness - Required files exist, directories present
Link validity - Cross-references point to existing targets
Freshness indicators - Last-modified dates, update frequency
Orphan detection - Files with no incoming references

结构完整性 - 必要文件是否存在？是否覆盖领域？
链接有效性 - 交叉引用是否指向现有目标？
新鲜度指标 - 最后更新日期？是否存在过时内容？
孤立文件检测 - 无入站引用的文件

What Requires Human Judgment

需要人工判断的内容

Content quality - Is the information accurate and useful?
Relationship accuracy - Do documented connections reflect reality?
Appropriate scope - Is the network right-sized for the project?
Navigation effectiveness - Do paths match actual usage patterns?

内容质量 - 信息是否准确有用？
关系准确性 - 记录的关联是否符合实际情况？
范围合理性 - 网络规模是否适合项目？
导航有效性 - 路径是否符合实际使用模式？

Design Constraints

设计约束

This Skill Assumes

本技能的前提假设

Project benefits from persistent context across sessions
User wants agent-accessible documentation
Some structure is better than pure freeform notes

项目能从跨会话的持久上下文中获益
用户需要可被Agent访问的文档
某种形式的结构比纯自由形式的笔记更好

This Skill Does Not Handle

本技能不处理的内容

Real-time project work - Route to: domain-specific skills
Retrospective analysis of agent sessions - Route to: context-retrospective
Framework development - Route to: skill-builder

实时项目工作 - 请转至：领域特定技能
Agent会话的回顾分析 - 请转至：上下文回顾技能
框架开发 - 请转至：技能构建器

Degradation Signals

降级信号

User wants "just a README" - may not need full network
Project lifespan < 1 week - overhead may exceed benefit
Pure spike/experiment - freeform notes may be better fit

用户只想要“一个简单的README” - 可能不需要完整的网络
项目生命周期<1周 - 维护成本可能超过收益
纯探索/实验项目 - 自由形式的笔记可能更合适

Output Persistence

输出持久化

Output Discovery

输出发现

Before generating structure:

Check for existing
```
.context-network.md
```
Check for existing
```
context/
```
directory
If starting fresh, confirm target location with user

在生成结构之前：

检查是否存在现有
```
.context-network.md
```
检查是否存在现有
```
context/
```
目录
如果从零开始，与用户确认目标位置

Primary Output

主要输出

This skill generates:

```
.context-network.md
```
- Discovery file
```
context/
```
directory structure
Template files (status.md, decisions.md, glossary.md)
CLAUDE.md updates (if needed)

本技能生成以下内容：

```
.context-network.md
```
- 发现文件
```
context/
```
目录结构
模板文件（status.md、decisions.md、glossary.md）
CLAUDE.md更新（如有需要）

What Goes Where

内容存储位置

Goes to File	Stays in Conversation
Directory structure	Diagnosis discussion
Template files	Coaching Q&A
Discovery file	Migration decisions
CLAUDE.md updates	Prioritization reasoning

存储至文件	保留在对话中
目录结构	诊断讨论
模板文件	指导问答
发现文件	迁移决策
CLAUDE.md更新	优先级推理

Integration Graph

集成图谱

Inbound (From Other Skills)

入站（来自其他技能）

Source Skill	Trigger	Action
context-retrospective	Gap findings	Run Maintenance Mode
skill-builder	New skill needs context	Run Bootstrap Mode

来源技能	触发条件	操作
context-retrospective	缺口发现结果	运行维护模式
skill-builder	新技能需要上下文	运行初始化模式

Outbound (To Other Skills)

出站（至其他技能）

Trigger	Target Skill	Reason
Agent behavior problems persist after CN4 intervention	Review CLAUDE.md patterns	May need skill-level changes
Network mature, want continuous improvement	context-retrospective	Regular health checks

触发条件	目标技能	原因
CN4干预后Agent行为问题仍存在	审查CLAUDE.md模式	可能需要技能层面的变更
网络成熟，需要持续改进	context-retrospective	定期健康检查

Complementary Skills

互补技能

Skill	Relationship
context-retrospective	Post-hoc analysis feeds maintenance mode
skill-builder	Skills may need context network infrastructure

技能	关系
context-retrospective	事后分析结果为维护模式提供输入
skill-builder	技能可能需要上下文网络基础设施

Example Interaction

交互示例

User: "I'm starting a new TypeScript project and want to set up a context network."

Your approach:

Scan for existing documentation (package.json, README, etc.)
Ask: "What's the primary domain? (e.g., API, CLI, library, full-stack app)"
Generate software-project scaffold based on answer
Create
```
.context-network.md
```
and
```
context/
```
structure
Coach: "Start with status.md - what's the current state of the project?"

用户：“我正在启动一个新的TypeScript项目，想要设置上下文网络。”

你的处理流程：

扫描现有文档（package.json、README等）
询问：“项目的核心领域是什么？（例如：API、CLI、库、全栈应用）”
根据回答生成软件项目架构模板
创建
```
.context-network.md
```
和
```
context/
```
结构
指导：“先从status.md开始——当前项目处于什么状态？”