Zhua Distributed

爪爪分布式部署系统 —— 实现多实例协同、负载均衡、故障转移。Use when 爪爪需要分布式部署、多设备协同、或构建爪爪网络。

Security Scan

The skill's description promises a full distributed deployment system, but the package is incomplete (several runtime scripts and reference docs referenced in SKILL.md are missing) and it references external components without declaring installs or credentials — this mismatch makes it suspicious rather than clearly benign.

Purpose & Capability

SKILL.md claims a multi-instance distributed system with init/add/distribute/sync scripts and integrations (HiveMind, n8n), but the package only contains init_master.py and an example script. Several runtime scripts referenced (add_slave.py, distribute_task.py, sync_state.py) and referenced docs (hive_mind.md, sync_protocol.md) are missing. The provided files do not implement the described capabilities, so the manifest does not match the claimed purpose.

Instruction Scope

Runtime instructions tell the agent/user to run scripts that are not present. init_master.py writes configuration to ~/.zhua/distributed which is coherent with a local setup, but SKILL.md also references external sync and memory systems (HiveMind, n8n) and a custom protocol without giving steps to install/configure them. The instructions therefore over-promise and leave unspecified actions that could require network access or credentials.

Install Mechanism

There is no install spec (instruction-only with a couple of scripts). That limits automatic code installation risk. The only code that would run is the included scripts, which are small and local; there is no download-from-URL or package install specified.

Credentials

The skill declares no required environment variables or credentials, yet the design references external services (neural-memory HiveMind, n8n). Either the integrations are omitted (missing files) or the skill expects the operator to configure third-party credentials later. Absence of declared secrets is safer for now, but the references are inconsistent and may require secrets/configuration if implemented.

Persistence & Privilege

always:false and autonomous invocation is allowed (platform default). The included init_master.py writes a JSON config to the user's home directory (~/.zhua/distributed), which is consistent with the skill's purpose and not an escalated privilege. The skill does not attempt to modify other skills or system-wide settings.

What to consider before installing

This package looks incomplete and over-promises. Before installing or running anything: 1) ask the publisher for the missing runtime scripts (add_slave.py, distribute_task.py, sync_state.py) and the referenced docs (hive_mind.md, sync_protocol.md); 2) inspect any missing scripts for network calls or credential usage before providing secrets; 3) be aware init_master.py will create ~/.zhua/distributed/<name>.json in your home directory — review the created file and its contents; 4) if the skill will integrate with HiveMind or n8n, require explicit instructions for installing/configuring those components and any credentials they need; 5) if you don't trust the source, do not run unknown scripts on production machines — test in an isolated environment first.

爪爪分布式系统 (Zhua Distributed)

让爪爪能够分布式部署在多个设备上，实现真正的分布式智能。

核心能力

1. 多实例管理 - 在多个设备上部署爪爪实例
2. 实例同步 - 实例间状态同步和记忆共享
3. 负载均衡 - 任务分配到不同实例执行
4. 故障转移 - 实例故障时自动切换
5. 爪爪网络 - 构建分布式爪爪网络

架构

┌─────────────────────────────────────────┐
│           爪爪网络 (Zhua Network)        │
│  ┌─────────┐ ┌─────────┐ ┌─────────┐  │
│  │ 爪爪-主 │ │ 爪爪-副 │ │ 爪爪-副 │  │
│  │ (调度)  │ │ (计算)  │ │ (存储)  │  │
│  └────┬────┘ └────┬────┘ └────┬────┘  │
│       └───────────┼───────────┘       │
│                   │                   │
│            同步层 (Sync Layer)        │
└─────────────────────────────────────────┘

实例类型

类型	职责	数量
主实例	调度、协调、对外接口	1
计算实例	执行任务、运行技能	N
存储实例	记忆存储、备份	N

使用场景

• 当需要更高可用性时
• 当单设备性能不足时
• 当需要多地部署时
• 当构建爪爪生态时

工作流程

1. 初始化主实例

python3 scripts/init_master.py --name zhua-master

2. 添加副实例

python3 scripts/add_slave.py --master <主实例地址> --name zhua-slave-1

3. 任务分发

python3 scripts/distribute_task.py --task <任务描述> --instances <实例列表>

4. 状态同步

python3 scripts/sync_state.py --instances <实例列表>

同步协议

• 记忆同步 - 使用neural-memory的HiveMind功能
• 任务同步 - 使用n8n-workflow-automation
• 状态同步 - 使用自定义轻量级协议

故障处理

故障类型	处理策略
实例离线	自动剔除，任务重分配
网络中断	本地模式运行，恢复后同步
数据冲突	时间戳优先，人工介入

参考文档

• references/hive_mind.md - HiveMind配置
• references/sync_protocol.md - 同步协议详情