Agent Workflow
A structured workflow engine for OpenClaw agents. Migrated and generalized from the superpowers workflow system into a code-agnostic, general-purpose workflow plugin.
What it does
Provides a persistent state machine that guides your agent through a complete work lifecycle:
CODEBLOCK0
With support for:
- - Persistent state — workflow survives session restarts
- Multi-project — run multiple workflows concurrently
- Branching — choose execution strategy at branch points
- Context-plugins — fork into review/parallel-agents without leaving main flow
- Soft-guard goto — jump to any step with warnings about skipped prerequisites
- 11 bundled Skills — covering the full workflow lifecycle
Installation
This is a Plugin, not a plain Skill. Install via:
CODEBLOCK1
Then enable in your ~/.openclaw/openclaw.json:
CODEBLOCK2
Usage
In your agent (via Feishu, Discord, or any channel):
CODEBLOCK3
The agent will call agent_workflow with action: "start" and guide you through the workflow.
Tool: agent_workflow
| Action | Description |
|---|
| INLINECODE4 | Begin a new workflow |
| INLINECODE5 |
View current state (all active workflows if no ID given) |
|
next | Advance to the next step |
|
goto | Jump to any node (soft-guard warns about skipped steps) |
|
complete | Mark current node done |
|
fork | Activate a context-plugin without leaving main flow |
|
join | Complete a fork and return |
|
getSkill | Load full SKILL.md for the current node |
|
list | List all workflows |
|
abandon | Abandon a workflow |
Bundled Skills
- -
brainstorming — Turn ideas into specs - INLINECODE15 — Break specs into tasks
- INLINECODE16 — Sequential execution
- INLINECODE17 — Parallel subagent execution
- INLINECODE18 — Evidence before claims
- INLINECODE19 — Delivery options
- INLINECODE20 — Fork independent tasks
- INLINECODE21 — Dispatch reviewer subagent
- INLINECODE22 — Evaluate feedback rigorously
- INLINECODE23 — Root-cause diagnosis
- INLINECODE24 — Create/improve Skills
Agent Workflow
为OpenClaw代理设计的结构化工作流引擎。从superpowers工作流系统迁移并泛化而来，成为一个与代码无关的通用工作流插件。
功能概述
提供持久化状态机，引导代理完成完整的工作生命周期：
头脑风暴 → 编写计划 → [执行] → 验证 → 完成工作
↓
子代理驱动执行
OR
执行计划
支持以下特性：
- - 持久化状态 — 工作流在会话重启后依然存在
- 多项目支持 — 同时运行多个工作流
- 分支选择 — 在分支节点选择执行策略
- 上下文插件 — 在不离开主流程的情况下分叉进入审查/并行代理
- 软保护跳转 — 跳转到任意步骤时警告跳过的前提条件
- 11个内置技能 — 覆盖完整的工作流生命周期
安装说明
这是一个插件，而非普通技能。通过以下命令安装：
bash
openclaw plugins install clawhub:agent-workflow
openclaw gateway restart
然后在 ~/.openclaw/openclaw.json 中启用：
json
{
plugins: {
allow: [agent-workflow]
},
tools: {
allow: [agent_workflow]
}
}
使用方法
在您的代理中（通过飞书、Discord或任何渠道）：
为我的Q2规划项目启动一个新工作流
代理将调用 agent_workflow 并传入 action: start，引导您完成工作流。
工具：agent_workflow
查看当前状态（未指定ID时显示所有活跃工作流） |
| next | 前进到下一步 |
| goto | 跳转到任意节点（软保护会警告跳过的步骤） |
| complete | 标记当前节点完成 |
| fork | 在不离开主流程的情况下激活上下文插件 |
| join | 完成分叉并返回 |
| getSkill | 加载当前节点的完整SKILL.md |
| list | 列出所有工作流 |
| abandon | 放弃工作流 |
内置技能
- - brainstorming — 将想法转化为规格说明
- writing-plans — 将规格说明分解为任务
- executing-plans — 顺序执行
- subagent-driven-execution — 并行子代理执行
- verification-before-completion — 先有证据再下结论
- finishing-work — 交付选项
- dispatching-parallel-agents — 分叉独立任务
- requesting-review — 派遣审查子代理
- receiving-review — 严格评估反馈
- systematic-problem-solving — 根因诊断
- writing-skills — 创建/改进技能
