← Back to Skills Marketplace
Multi Agent Workflow
by
dxie48892-jpg
· GitHub ↗
· v1.0.3
· MIT-0
316
Downloads
0
Stars
5
Active Installs
4
Versions
Install in OpenClaw
/install multi-agent-workflow
Description
多Agent协作工作流 v1.0.3。让多个AI Agent组成团队,协同完成复杂任务。支持任务拆分、角色分配、结果汇总、任务管理。
README (SKILL.md)
Multi Agent Workflow - 多Agent协作工作流
快速开始
cd scripts
python workflow.py --help
目录结构
multi-agent-workflow/
├── SKILL.md
├── README.md
├── scripts/
│ └── workflow.py
工作流程
- 接收任务
- 拆分任务
- 分配角色
- 并行执行
- 汇总结果
更新日志
v1.0.3 (2026-03-22)
- 修复:Windows控制台UTF-8编码输出问题
v1.0.2 (2026-03-21)
- 新增:TaskManager任务管理器
- 新增:split_task任务拆分
- 新增:自动角色分配
Usage Guidance
This skill appears to be a simple, coherent task-splitting and role-assignment helper implemented as a local Python script. It does not access the network, request credentials, or perform installs. Before installing or running: 1) Inspect the script (you already have it) — it's small and readable. 2) Note that claims about 'parallel execution' and 'sessions_spawn' are not implemented; if you expect agent orchestration, additional integration code is required. 3) If you will run it on sensitive systems, run it in an isolated environment (e.g., container/VM) as a general best practice for any third‑party script. Overall risk is low, but only run it if you understand how you'll integrate it with your agent framework.
Capability Analysis
Type: OpenClaw Skill
Name: multi-agent-workflow
Version: 1.0.3
The skill bundle provides a legitimate framework for managing multi-agent workflows by categorizing tasks and assigning roles. The core logic in `scripts/workflow.py` uses simple keyword matching and task management structures to output JSON configurations, with no evidence of data exfiltration, unauthorized execution, or malicious prompt injection.
Capability Assessment
Purpose & Capability
Name/description match the delivered artifacts: SKILL.md, README, and scripts/workflow.py implement task splitting, role assignment, a TaskManager, and result aggregation. The 'model': 'iflow' fields are just descriptive strings and do not trigger network or credential use.
Instruction Scope
Runtime instructions are limited to running the included Python CLI. The SKILL.md and code do not read system files or environment variables. Minor mismatch: meta/README/description refer to '并行执行' (parallel execution) and '可用于调用OpenClaw的sessions_spawn执行', but the provided script does not implement parallel execution or any auto-spawning of agent sessions — it only prints JSON and manages in-memory tasks.
Install Mechanism
No install spec is provided and no external packages are fetched; the skill is instruction + a small local Python script only, which is low risk from an installation standpoint.
Credentials
The skill requests no environment variables, credentials, or config paths. The code does not access secrets or external credentials.
Persistence & Privilege
Flags show normal privileges (always: false, user-invocable: true). The skill does not persist or modify other skills or system configuration.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install multi-agent-workflow - After installation, invoke the skill by name or use
/multi-agent-workflow - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
v1.0.3: 修复Windows控制台UTF-8编码输出问题
v1.0.2
v1.0.2: 新增TaskManager任务管理器、split_task任务拆分、自动角色分配
v1.0.1
修复:补充Agent调度代码
v1.0.0
多Agent协作工作流 - 任务拆分、角色分配、结果汇总
Metadata
Frequently Asked Questions
What is Multi Agent Workflow?
多Agent协作工作流 v1.0.3。让多个AI Agent组成团队,协同完成复杂任务。支持任务拆分、角色分配、结果汇总、任务管理。 It is an AI Agent Skill for Claude Code / OpenClaw, with 316 downloads so far.
How do I install Multi Agent Workflow?
Run "/install multi-agent-workflow" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Multi Agent Workflow free?
Yes, Multi Agent Workflow is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Multi Agent Workflow support?
Multi Agent Workflow is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Multi Agent Workflow?
It is built and maintained by dxie48892-jpg (@dxie48892-jpg); the current version is v1.0.3.
More Skills