A high-performance multi-agent orchestration subsystem featuring the OASIS collaboration engine, automated computer use, and social platform integrations.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install teamclawtest
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install teamclawtest using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is TeamClaw?
TeamClaw is an advanced agent subsystem designed for complex multi-agent orchestration (OASIS) and visual workflow management. It operates as a versatile extension within the Openclaw Skills ecosystem, providing a built-in lightweight agent capable of automated computer use tasks and real-time visual monitoring via a dedicated Web UI.
By supporting multi-vendor LLM backends like DeepSeek, OpenAI, Gemini, and Claude, TeamClaw allows developers to run independent agent processes without blocking the main agent. It also facilitates remote access through Cloudflare Tunnels, enabling mobile-friendly multi-agent programming and real-time social platform bot integrations for Telegram and QQ.
TeamClaw Use Cases
- Orchestrating parallel multi-expert discussions for technical route selection and decision-making.
- Automating complex computer use tasks via a dedicated agent subsystem.
- Building and managing social platform bots for Telegram or QQ with AI backends.
- Setting up scheduled AI tasks using the built-in APScheduler center.
- Remote visual workflow programming via public HTTPS access using Cloudflare Tunnels.
How TeamClaw Works
- The user initiates the TeamClaw environment using the provided shell scripts in the Openclaw Skills structure.
- LLM providers and API keys are configured to power the conversational and orchestration engines.
- The OASIS platform categorizes agents into four types (Direct LLM, Oasis Session, Regular Agent, or External API) based on YAML configuration.
- Workflows are executed in either Discussion Mode for consensus or Execution Mode for direct deliverables.
- Real-time updates are pushed via SSE (Server-Sent Events) to the Web UI or via Bark push notifications to mobile devices.
TeamClaw Setup
Prerequisites
Ensure you are in the project root directory before running commands.
Installation & Initialization
# Install dependencies
bash selfskill/scripts/run.sh setup
# Initialize configuration
bash selfskill/scripts/run.sh configure --init
# Configure LLM credentials
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 a system user
bash selfskill/scripts/run.sh add-user system MySecurePass123
Service Control
# Start all services (Agent, OASIS, Frontend)
bash selfskill/scripts/run.sh start
TeamClaw Data Schema & Taxonomy
TeamClaw organizes its data through a structured file system and SQLite databases for persistence.
| Data Type | Storage Location |
|---|---|
| Agent Memory | data/agent_memory.db (SQLite) |
| Workflows | data/user_files/{user}/oasis/yaml/{file}.yaml |
| Custom Experts | data/oasis_user_experts/{user}.json |
| Discussion Records | data/oasis_topics/{user}/{topic_id}.json |
| Logs | logs/launcher.log |
TeamClaw Advanced Features
- OASIS Detach Mode: Run long-running multi-round discussions in the background without blocking sessions.
- External API Integration: Connect Openclaw Skills agents directly to the OASIS server as external experts.
- Automated Tunneling: Integrated Cloudflare Tunnel support for secure, auto-configured public HTTPS domains.
- Multi-Engine Support: Seamlessly mix and match different LLM providers within a single parallel orchestration plan.
- Stateful Sessions: Persistent memory layers for agents across multiple rounds of discussion.
SKILL.md
Loading
Related Openclaw Skills
Memphis CLI
A local-first brain management CLI for capturing, querying, and synchronizing immutable memory chains across AI agents.
Teamclaw
A high-performance Agent subsystem designed for complex multi-agent orchestration, automated scheduling, and real-time visual monitoring.
Debug Checklist
A systematic debugging framework that automates error detection to drastically reduce bug recurrence and troubleshooting time.
birdx
A high-performance X/Twitter CLI that bypasses API requirements by reading Chrome cookies directly from disk for seamless data extraction.
Oura API Complete Export
A professional-grade data extraction tool that automates Oura Ring OAuth2 authentication and exports all available v2 user collection datasets to raw JSON.
Claw Janitor
A platform-aware, zero-dependency system cleanup utility designed to safely reclaim disk space for AI agents.
Featured*
