clawclau

异步 Claude Code 任务调度工具集(ClawClau)。基于 tmux 派发后台 Claude Code 任务,含进度汇报、完成通知、状态查询、中途纠偏。触发场景:让乌萨奇做xxx、派发任务给Claude Code、查看后台任务状态、终止后台任务、batch任务派发。

3,891 stars

Best use case

clawclau is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

异步 Claude Code 任务调度工具集(ClawClau)。基于 tmux 派发后台 Claude Code 任务,含进度汇报、完成通知、状态查询、中途纠偏。触发场景:让乌萨奇做xxx、派发任务给Claude Code、查看后台任务状态、终止后台任务、batch任务派发。

Teams using clawclau should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/clawclau/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/barryyjj/clawclau/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/clawclau/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How clawclau Compares

Feature / AgentclawclauStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

异步 Claude Code 任务调度工具集(ClawClau)。基于 tmux 派发后台 Claude Code 任务,含进度汇报、完成通知、状态查询、中途纠偏。触发场景:让乌萨奇做xxx、派发任务给Claude Code、查看后台任务状态、终止后台任务、batch任务派发。

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# ClawClau v2.0.0 — Claude Code 任务调度系统

小八(OpenClaw)派发异步 Claude Code 任务的工具集。基于 Elvis Sun 的 Agent Swarm 架构设计。

## 核心文件

```
<skills-dir>/clawclau/scripts/          # 安装后脚本位置
├── clawclau-lib.sh        # 共享库(所有脚本 source 此文件)
├── claude-spawn.sh        # 派发任务(含内嵌完成检测器和进度汇报器)
├── claude-check.sh        # 查询状态(确定性,不耗 token)
├── claude-result.sh       # 获取结果
├── claude-monitor.sh      # 批量监控安全兜底(cron 用)
├── claude-kill.sh         # 终止任务
└── claude-steer.sh        # 中途纠偏

~/.clawclau/
├── active-tasks.json      # 任务注册表(source of truth)
├── config                 # 本地配置(notify_chat 等)
├── logs/
│   ├── task-id.json       # stream-json 格式日志(print 模式)
│   └── task-id.txt        # 纯文本日志(steerable 模式)
└── prompts/
    ├── task-id.txt        # prompt 备份
    └── task-id-wrapper.sh # 自动生成的 wrapper 脚本
```

## 安装与配置

```bash
# 依赖
brew install tmux jq && which claude

# 初始化
mkdir -p ~/.clawclau/logs ~/.clawclau/prompts

# 配置通知(可选)
echo "notify_chat = oc_xxxxxxxx" >> ~/.clawclau/config

# shell profile(可选)
export CC_SCRIPTS=~/.openclaw/workspace/skills/clawclau/scripts
```

## 快速开始

```bash
SCRIPTS=~/.openclaw/workspace/skills/clawclau/scripts

# 1. 派发任务
$SCRIPTS/claude-spawn.sh my-task "请整理这份文档..." /path/to/workdir

# 2. 查看所有任务
$SCRIPTS/claude-check.sh

# 3. 查看单个任务详情
$SCRIPTS/claude-check.sh my-task

# 4. 获取完整结果
$SCRIPTS/claude-result.sh my-task

# 5. 终止任务
$SCRIPTS/claude-kill.sh my-task
```

## 脚本接口

### claude-spawn.sh — 派发任务

```bash
claude-spawn.sh [OPTIONS] <task-id> "<prompt>" [workdir]

--steerable        交互式模式(支持 claude-steer.sh 纠偏)
--timeout <sec>    超时秒数(默认 600)
--interval <sec>   进度汇报间隔,0=关闭(默认 180)
--max-retries <n>  最大重试次数记录(默认 3)
--model <name>     Claude 模型名称
--parent <id>      父任务 ID(重试时使用)
--retry-count <n>  当前重试计数(内部使用)
```

示例:

```bash
# 带进度汇报(每 60s 通知一次)
$SCRIPTS/claude-spawn.sh research-task "调研XXX行业趋势" ~/.openclaw/workspace \
  --interval 60 --timeout 1200

# 交互式模式(可中途纠偏)
$SCRIPTS/claude-spawn.sh explore-task "探索代码库,找出主要问题" ~/myproject \
  --steerable --interval 120

# 指定模型
$SCRIPTS/claude-spawn.sh heavy-task "复杂分析任务..." . \
  --model claude-opus-4-6 --timeout 1800
```

spawn 内嵌双重 fork 后台完成检测器,任务结束时自动调用 `cc_notify` 通知小八。

### claude-check.sh — 查询状态

```bash
claude-check.sh              # 列出所有任务(表格)
claude-check.sh <task-id>    # 单任务详情(含结果预览)
```

以 tmux session 是否存活为 running 的最终判据,不调用 AI,不消耗 token。

### claude-result.sh — 获取结果

```bash
claude-result.sh <task-id>        # 从 stream-json 提取可读文本
claude-result.sh <task-id> --raw  # 输出原始 stream-json 日志
```

### claude-monitor.sh — 批量监控(cron 用)

```bash
# 设置 cron(每 10 分钟)
*/10 * * * * $SCRIPTS/claude-monitor.sh >> /tmp/clawclau-monitor.log 2>&1
```

### claude-kill.sh — 终止任务

```bash
claude-kill.sh <task-id>    # 终止 session,状态更新为 killed
```

### claude-steer.sh — 中途纠偏

```bash
claude-steer.sh <task-id> "请聚焦在 X 方面"    # 仅支持 --steerable 模式
```

## 参考文档

- 注册表字段、状态流转、环境变量:[references/schema.md](references/schema.md)
- 设计原则、通知机制、重试流程、运行模式:[references/design.md](references/design.md)

Related Skills

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation