← 返回 Skills 市场
133
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install personal-agent-network
功能描述
Design patterns for personal agents coordinating like executive assistants—delegation manifests, relationship handshakes, commitment tiers, trust, and OpenCl...
安全使用建议
This skill is documentation-only and internally consistent with its stated purpose — safe to install in that it won't by itself run code or ask for secrets. Before installing or enabling widely: (1) confirm the published source/repo and publisher identity (metadata shows an OpenClaw homepage but source is unknown), (2) review future versions for any added install specs or environment requirements, and (3) when you publish or run ClawHub commands follow the guidance to run the ClawHub CLI yourself on your machine rather than letting an agent execute shell commands automatically.
功能分析
Type: OpenClaw Skill
Name: personal-agent-network
Version: 0.1.1
The skill bundle consists entirely of documentation and design patterns for agent-to-agent coordination. It contains no executable code, and the instructions in SKILL.md explicitly advise the agent against running unauthorized shell commands or accessing files without user consent.
能力评估
Purpose & Capability
The name/description (personal agent network, delegation manifests, handshakes) aligns with the SKILL.md content. The skill declares no binaries, env vars, or installs and does not attempt to access unrelated services or credentials.
Instruction Scope
SKILL.md is purely prescriptive/documentary: it defines artifacts, protocols, tiers, and onboarding rules. It explicitly forbids running shell/ClawHub unless the user explicitly requests it and contains no instructions to read files, exfiltrate data, or call external endpoints.
Install Mechanism
No install specification or code files are present (instruction-only), so nothing will be written to disk or downloaded by the skill itself.
Credentials
The skill requests no environment variables or credentials. It references identity concepts (principal_id, agent_id) conceptually but does not attempt to obtain or require secrets.
Persistence & Privilege
The skill is not always-on and uses default autonomous invocation settings (normal for skills). It does not request persistent system privileges or modify other skills' configs.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install personal-agent-network - 安装完成后，直接呼叫该 Skill 的名称或使用
/personal-agent-network触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.1.1
Docs-only scope disclaimer; removed shell publish snippets; softened path refs for ClawHub security scan.
v0.1.0
- Initial release introducing the personal-agent-network skill for modeling agent-to-agent (A2A) workflows inspired by executive assistants.
- Defines key artifacts: delegation manifests, relationship contracts, commitment tiers, and lightweight trust logging.
- Outlines protocol interoperability steps and OpenClaw-native mapping concepts.
- Provides practical guidance on when to use the skill and how to publish it to ClawHub.
元数据
常见问题
Personal Agent Network 是什么？
Design patterns for personal agents coordinating like executive assistants—delegation manifests, relationship handshakes, commitment tiers, trust, and OpenCl... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 133 次。
如何安装 Personal Agent Network？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install personal-agent-network」即可一键安装，无需额外配置。
Personal Agent Network 是免费的吗？
是的，Personal Agent Network 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Personal Agent Network 支持哪些平台？
Personal Agent Network 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Personal Agent Network？
由 Madhav（@madhavuf）开发并维护，当前版本 v0.1.1。
推荐 Skills