How do I install the Teamclaw skill?

Run npx skillmds@latest add modbender/teamclaw in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Teamclaw skill do?

A high-performance Agent subsystem designed for complex multi-agent orchestration (OASIS),automated computer use tasks, and real-time visual monitoring via a dedicated Web UI. It is listed under AI & ML on SkillMD.

Is Teamclaw safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: CAUTION, Skill Scanner: PASS. Capability flags: executes scripts, makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Teamclaw?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Teamclaw free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Teamclaw?

modbender (@modbender) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Teamclaw by modbender — Agent Skill

Name: Teamclaw
Rating: 4.2 (5 reviews)
Author: modbender

Language: English | 中文

Teamclaw — Agent Subsystem Skill (English)

Overview

Teamclaw is a multifunctional AI Agent service providing:

Conversational Agent: A multi-tool AI assistant based on LangGraph that supports streaming/non-streaming conversations
OASIS Forum: A multi-expert parallel discussion/execution engine that orchestrates collaboration among multiple Agents
Scheduled Tasks: A task scheduling center based on APScheduler
Bark Push: Mobile push notifications
Web UI Frontend: A complete chat interface

Skill Scripts

All scripts are located in selfskill/scripts/ and are called uniformly through the run.sh entry point. All are non-interactive.

selfskill/scripts/
├── run.sh          # Main entry (start/stop/status/setup/add-user/configure)
├── adduser.py      # Non-interactive user creation
└── configure.py    # Non-interactive .env configuration management

Quick Start

All commands are executed from the project root directory.

1. Initial Deployment

# Install dependencies
bash selfskill/scripts/run.sh setup

# Initialize configuration file
bash selfskill/scripts/run.sh configure --init

# Configure LLM (required)
bash selfskill/scripts/run.sh configure --batch \
  LLM_API_KEY=sk-your-key \
  LLM_BASE_URL=https://api.deepseek.com \
  LLM_MODEL=deepseek-chat

# Create user
bash selfskill/scripts/run.sh add-user system MySecurePass123

2. Start/Stop/Status

bash selfskill/scripts/run.sh start     # Start background service
bash selfskill/scripts/run.sh status    # Check status
bash selfskill/scripts/run.sh stop      # Stop service

3. Configuration Management

# View current configuration (sensitive values masked)
bash selfskill/scripts/run.sh configure --show

# Set single item
bash selfskill/scripts/run.sh configure PORT_AGENT 51200

# Batch set
bash selfskill/scripts/run.sh configure --batch TTS_MODEL=gemini-2.5-flash-preview-tts TTS_VOICE=charon

Configurable Items

Configuration Item	Description	Default Value
`LLM_API_KEY`	LLM API key (required)	—
`LLM_BASE_URL`	LLM API address	`https://api.deepseek.com`
`LLM_MODEL`	Model name	`deepseek-chat`
`LLM_PROVIDER`	Provider (google/anthropic/deepseek/openai, auto-inferred)	Auto
`LLM_VISION_SUPPORT`	Image support (auto-inferred)	Auto
`PORT_AGENT`	Main Agent service port	`51200`
`PORT_SCHEDULER`	Scheduling port	`51201`
`PORT_OASIS`	OASIS forum port	`51202`
`PORT_FRONTEND`	Web UI port	`51209`
`PORT_BARK`	Bark push port	`58010`
`TTS_MODEL`	TTS model (optional)	—
`TTS_VOICE`	TTS voice (optional)	—
`INTERNAL_TOKEN`	Internal communication key (auto-generated)	Auto

Ports and Services

Port	Service
51200	AI Agent main service
51201	Scheduled tasks
51202	OASIS forum
51209	Web UI

API Authentication

Method 1: User Authentication

Authorization: Bearer <user_id>:<password>

Method 2: Internal Token (inter-service calls, recommended)

Authorization: Bearer <INTERNAL_TOKEN>:<user_id>

INTERNAL_TOKEN is auto-generated on the first startup and can be viewed via configure --show-raw.

Core APIs

Base URL: http://127.0.0.1:51200

Chat (OpenAI Compatible)

POST /v1/chat/completions
Authorization: Bearer <token>

{"model":"mini-timebot","messages":[{"role":"user","content":"Hello"}],"stream":true,"session_id":"my-session"}

System Trigger (Internal Call)

POST /system_trigger
X-Internal-Token: <INTERNAL_TOKEN>

{"user_id":"system","text":"Execute task","session_id":"task-001"}

Cancel Session

POST /cancel

{"user_id":"<user_id>","session_id":"<session_id>"}

OASIS Discussion/Execution

POST http://127.0.0.1:51202/topics

{"question":"Discussion topic","user_id":"system","max_rounds":3,"discussion":true,"schedule_yaml":"...","callback_url":"http://127.0.0.1:51200/system_trigger","callback_session_id":"my-session"}

Example Configuration Reference

Below is a sample configuration from an actual running instance (sensitive information masked):

bash selfskill/scripts/run.sh configure --init
bash selfskill/scripts/run.sh configure --batch \
  LLM_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxx4c74 \
  LLM_BASE_URL=https://deepseek.com \
  LLM_MODEL=deepseek-chat \
  LLM_VISION_SUPPORT=true \
  TTS_MODEL=gemini-2.5-flash-preview-tts \
  TTS_VOICE=charon \
  PORT_AGENT=51200 \
  PORT_SCHEDULER=51201 \
  PORT_OASIS=51202 \
  PORT_FRONTEND=51209 \
  PORT_BARK=58010 \
  OPENAI_STANDARD_MODE=false
bash selfskill/scripts/run.sh add-user system <your-password>

Output of configure --show after configuration:

  PORT_SCHEDULER=51201
  PORT_AGENT=51200
  PORT_FRONTEND=51209
  PORT_OASIS=51202
  OASIS_BASE_URL=http://127.0.0.1:51202
  PORT_BARK=58010
  INTERNAL_TOKEN=f1aa****57e7          # Auto-generated, do not leak
  LLM_API_KEY=sk-7****4c74
  LLM_BASE_URL=https://deepseek.com
  LLM_MODEL=deepseek-chat
  LLM_VISION_SUPPORT=true
  TTS_MODEL=gemini-2.5-flash-preview-tts
  TTS_VOICE=charon
  OPENAI_STANDARD_MODE=false

Note: INTERNAL_TOKEN is auto-generated on first startup, PUBLIC_DOMAIN / BARK_PUBLIC_URL are auto-written by tunnel, no manual configuration needed.

Typical Usage Workflow

cd /home/avalon/Teamclaw

# Initial configuration
bash selfskill/scripts/run.sh setup
bash selfskill/scripts/run.sh configure --init
bash selfskill/scripts/run.sh configure --batch LLM_API_KEY=sk-xxx LLM_BASE_URL=https://api.deepseek.com LLM_MODEL=deepseek-chat
bash selfskill/scripts/run.sh add-user system MyPass123

# Start service
bash selfskill/scripts/run.sh start

# Access Web UI
# Open browser and navigate to: http://127.0.0.1:51209
# Log in with username: system and password: MyPass123

# Call API
curl -X POST http://127.0.0.1:51200/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer system:MyPass123" \
  -d '{"model":"mini-timebot","messages":[{"role":"user","content":"Hello"}],"stream":false,"session_id":"default"}'

# Stop service
bash selfskill/scripts/run.sh stop

Important Notes

All skill scripts are located in selfskill/scripts/ and do not affect the original project functionality
Process management via PID files; start supports idempotent calls
Do not leak INTERNAL_TOKEN
Log path: logs/launcher.log
How to Enable Visualization & Login:
- After starting the service, open your browser and navigate to http://127.0.0.1:51209
- Use the credentials you created with add-user command (default: username system, password MySecurePass123)
- You can now access the chat interface and participate in OASIS forum discussions

Teamclaw — Agent 子系统 Skill (中文)

简介

Teamclaw 是一个多功能 AI Agent 服务，提供：

对话 Agent：基于 LangGraph 的多工具 AI 助手，支持流式/非流式对话
OASIS 论坛：多专家并行讨论/执行引擎，可编排多个 Agent 协作
定时调度：基于 APScheduler 的任务调度中心
Bark 推送：移动端推送通知
前端 Web UI：完整的聊天界面

Skill 脚本

所有脚本位于 selfskill/scripts/，统一通过 run.sh 入口调用，全部非交互式。

selfskill/scripts/
├── run.sh          # 主入口（start/stop/status/setup/add-user/configure）
├── adduser.py      # 非交互式用户创建
└── configure.py    # 非交互式 .env 配置管理

快速启动

所有命令在项目根目录下执行。

1. 首次部署

# 安装依赖
bash selfskill/scripts/run.sh setup

# 初始化配置文件
bash selfskill/scripts/run.sh configure --init

# 配置 LLM（必填）
bash selfskill/scripts/run.sh configure --batch \
  LLM_API_KEY=sk-your-key \
  LLM_BASE_URL=https://api.deepseek.com \
  LLM_MODEL=deepseek-chat

# 创建用户
bash selfskill/scripts/run.sh add-user system MySecurePass123

2. 启动/停止/状态

bash selfskill/scripts/run.sh start     # 后台启动
bash selfskill/scripts/run.sh status    # 检查状态
bash selfskill/scripts/run.sh stop      # 停止服务

3. 配置管理

# 查看当前配置（敏感值脱敏）
bash selfskill/scripts/run.sh configure --show

# 设置单项
bash selfskill/scripts/run.sh configure PORT_AGENT 51200

# 批量设置
bash selfskill/scripts/run.sh configure --batch TTS_MODEL=gemini-2.5-flash-preview-tts TTS_VOICE=charon

可配置项

配置项	说明	默认值
`LLM_API_KEY`	LLM API 密钥（必填）	—
`LLM_BASE_URL`	LLM API 地址	`https://api.deepseek.com`
`LLM_MODEL`	模型名称	`deepseek-chat`
`LLM_PROVIDER`	厂商（google/anthropic/deepseek/openai，可自动推断）	自动
`LLM_VISION_SUPPORT`	是否支持图片（可自动推断）	自动
`PORT_AGENT`	Agent 主服务端口	`51200`
`PORT_SCHEDULER`	定时调度端口	`51201`
`PORT_OASIS`	OASIS 论坛端口	`51202`
`PORT_FRONTEND`	Web UI 端口	`51209`
`PORT_BARK`	Bark 推送端口	`58010`
`TTS_MODEL`	TTS 模型（可选）	—
`TTS_VOICE`	TTS 声音（可选）	—
`INTERNAL_TOKEN`	内部通信密钥（自动生成）	自动

端口与服务

端口	服务
51200	AI Agent 主服务
51201	定时调度
51202	OASIS 论坛
51209	Web UI

API 认证

方式 1：用户认证

Authorization: Bearer <user_id>:<password>

方式 2：内部 Token（服务间调用，推荐）

Authorization: Bearer <INTERNAL_TOKEN>:<user_id>

INTERNAL_TOKEN 首次启动自动生成，可通过 configure --show-raw 查看。

核心 API