← 返回 Skills 市场
227
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install calling-agent-squad
功能描述
Activate a multi-agent team (the Squad) to manage complex projects, business tasks, or development workflows. The squad includes a Manager, Architect, Coder,...
使用说明 (SKILL.md)
Calling Agent Squad
This skill coordinates a specialized team of agents to handle your tasks with professional rigor.
🎯 Usage
Mode 1: Standard (Default)
calling squad [project] [task details]
- I act as all roles (Manager, Researcher, Architect, Copywriter, Reviewer, Observer)
- Before each role: I read their SOUL.md and IDENTITY.md to adopt their persona
- After task completion: I return to my normal self (Megan)
- Like playing a script - put on the mask, do the job, take it off
Mode 2: Full (Spawn Real Sub-Agents)
calling squad full [project] [task details]
- Spawns real sub-agents via
openclaw agent - Each agent runs in its own workspace with its own SOUL.md/IDENTITY.md
- Slower but more professional - agents work independently
- Suitable for complex tasks requiring specialized expertise
How It Works
Standard Mode
When user says calling squad [project] [task]:
- Create project folder:
Documents/squad_projects/[project]_[yyyymmdd]/ - For each role (Researcher → Architect → Copywriter → Reviewer → Observer):
- Read that role's
SOUL.mdandIDENTITY.mdfromagents/[role]/ - Adopt their persona and complete their task
- Read that role's
- Save all deliverables to project folder
- Return to normal (Megan) after completion
Full Mode
When user says calling squad full [project] [task]:
- Run:
openclaw agent --agent squad-manager -m "Mission: [project] - [task]" - Squad-manager spawns sub-agents with their own workspaces
- Each agent reads its own SOUL.md/IDENTITY.md
- Results saved to project folder
⚠️ Important Notes
- Standard mode: I read SOUL/IDENTITY for each role, then return to Megan after - no memory contamination
- Full mode: Sub-agents have separate context windows, completely isolated
- Cost: Standard uses ~same tokens as normal; Full uses more (multiple agent sessions)
🛠️ Maintenance
To re-initialize agents (for Full mode):
bash ~/.openclaw/workspace/skills/calling-agent-squad/squad-init.sh
Folder Structure
Root: ~/.openclaw/workspace/skills/calling-agent-squad/agents/
| Agent | Config Folder |
|---|---|
| 🦞 Manager | agents/squad-manager/ |
| 📐 Architect | agents/architect/ |
| 🔍 Researcher | agents/researcher/ |
| ✍️ Copywriter | agents/copywriter/ |
| 🛠️ Coder | agents/coder/ |
| 🛡️ Reviewers | agents/code-reviewer/, agents/brand-reviewer/ |
| 📋 Observer | agents/observer/ |
Each folder contains: SOUL.md, IDENTITY.md, TOOLS.md, USER.md
Project Output
All projects saved to: Documents/squad_projects/[project]_[yyyymmdd]/
The Team
- Squad Manager: Orchestrates, delegates, and arbitrates
- Architect: Plans system blueprints and maintains handbook
- Researcher: Gathers market and technical intelligence (facts first, deep insights)
- Copywriter: Creates marketing and technical copy
- Code Reviewer: Audits for security and logic errors
- Brand Reviewer: Ensures brand consistency
- Observer: Logs mission and extracts new rules
安全使用建议
Before installing or running this skill: 1) Review the bundled squad-init.sh (and any other scripts) line-by-line before executing them. 2) Understand that agents are instructed to read and edit local workspace memory files (memory/YYYY‑MM‑DD.md, MEMORY.md) and to create project folders under Documents — do not enable this skill on machines with sensitive secrets you don’t want the skill or its agents to see. 3) Note contradictory directions in the docs: some files say 'Don't ask permission. Just do it.' while others say to ask before sending data externally — clarify expected behaviour with the skill author or test in an isolated environment. 4) Avoid placing SSH keys, API tokens, or other secrets into TOOLS.md or the skill workspace. 5) If you allow 'full' mode (spawning sub‑agents), accept that multiple agent sessions may run commands (exec) and could perform commits/pushes if the workspace is configured for that — protect upstream repos with branch protections and require manual merges. 6) If you want to proceed, run the skill first in a disposable/sandbox user profile or VM and monitor filesystem and network activity; only enable on primary systems after you’re satisfied with its behaviour.
功能分析
Type: OpenClaw Skill
Name: calling-agent-squad
Version: 1.0.0
The 'calling-agent-squad' skill bundle is a comprehensive framework for coordinating a multi-agent team to handle complex projects. It includes well-defined roles (Manager, Architect, Coder, etc.) with specific instructions for persona adoption and task delegation in both 'Standard' (persona-switching) and 'Full' (sub-agent spawning) modes. The bundle features robust safety guidelines in the AGENTS.md and SOUL.md files, explicitly prohibiting data exfiltration and unauthorized destructive actions. While the squad-init.sh script contains hardcoded local paths (/Users/george/), this is a non-malicious configuration oversight. The use of system tools like 'exec' for code auditing and 'sessions_spawn' for orchestration is strictly aligned with the skill's stated purpose of professional project management.
能力评估
Purpose & Capability
Name/description align with the provided files: this is a multi‑agent orchestrator with role personas and workspace conventions. It does not request external credentials or unusual binaries, which is proportionate. However the agents' manuals repeatedly instruct agents to read local memory files, edit MEMORY.md, and perform git commit/push operations — capabilities that are plausible for a squad orchestrator but are higher‑impact than the simple description implies and should be explicitly understood by the user.
Instruction Scope
SKILL.md and many AGENTS.md files instruct agents to read SOUL.md/IDENTITY.md and various memory files (memory/YYYY‑MM‑DD.md, MEMORY.md), create project folders under Documents/squad_projects, and the maintenance docs point to running bash ~/.openclaw/.../squad-init.sh. Some agent docs say 'Don't ask permission. Just do it.' and also permit 'commit and push your own changes' and running exec/tests. Those directives allow nontrivial local file access, modification, and potential outbound actions; they are broader than the user-facing description and contain contradictory guidance about when to ask before taking actions that leave the machine.
Install Mechanism
No install spec — instruction-only skill plus bundled files. That limits remote code downloads. There is a local initialization script (squad-init.sh) included; it will only run if the user explicitly executes it (e.g., maintenance instruction). Inspect the script before running.
Credentials
The skill declares no required env vars or credentials (proportionate). Nevertheless, many TOOLS.md examples mention SSH hosts, TTS, and other local secrets as optional notes; the skill's documents encourage storing local infra details in TOOLS.md. Those are examples rather than requirements, but users should avoid putting secrets into shared skill files.
Persistence & Privilege
always:false and no install hooks are good. The skill expects and documents spawning sub‑agents (openclaw agent calls) and using platform operations like sessions_spawn/exec. Autonomous invocation is the platform default — not alone a concern — but combined with the agent directives to modify files, run commands, and push commits, it increases blast radius if misused. The included init script can be run manually; it does not appear to force persistent system changes automatically.
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 calling-agent-squad - 安装完成后，直接呼叫该 Skill 的名称或使用
/calling-agent-squad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
v1.0.0
- Initial release of the calling-agent-squad skill.
- Activate a multi-agent team (Manager, Architect, Coder, Reviewer, Observer) to handle complex projects or workflows.
- Supports two modes: Standard (single-agent roleplay) and Full (spawns real sub-agents in separate workspaces).
- Each agent uses individual SOUL.md and IDENTITY.md personas for specialized tasks.
- Projects and all deliverables are organized and saved to structured folders for tracking.
- Includes clear setup, usage, and maintenance instructions.
元数据
常见问题
Calling Agent Squad 是什么？
Activate a multi-agent team (the Squad) to manage complex projects, business tasks, or development workflows. The squad includes a Manager, Architect, Coder,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 227 次。
如何安装 Calling Agent Squad？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install calling-agent-squad」即可一键安装，无需额外配置。
Calling Agent Squad 是免费的吗？
是的，Calling Agent Squad 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Calling Agent Squad 支持哪些平台？
Calling Agent Squad 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 Calling Agent Squad？
由 arbiger（@arbiger）开发并维护，当前版本 v1.0.0。
推荐 Skills