A universal orchestration framework for managing 5-agent teams to execute complex, multi-step workflows across software, research, and business domains.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install claude-agent-team-workflows
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 claude-agent-team-workflows 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 Agent Team Workflows?
Agent Team Workflows provide a standardized architecture for multi-agent collaboration, utilizing a Lead orchestrator and four specialized teammates. This framework allows users to scale their operations by remapping generic agent roles—Planner, Builder, Validator, and Critic—into domain-specific experts. By implementing these Openclaw Skills, you can move beyond single-prompt interactions into sophisticated, high-quality production pipelines.
The skill focuses on strict coordination protocols and defined handoff patterns, ensuring that every artifact produced is validated and reviewed before reaching the final synthesis. Whether you are building software or conducting market research, this skill provides the structural discipline needed for reliable AI-driven results.
Agent Team Workflows Use Cases
- Managing complex software engineering tasks that require separate architecture, coding, testing, and review phases.
- Creating high-quality long-form content using an iterative-review loop between writers and editors.
- Conducting deep-dive research projects that benefit from parallel data gathering and a centralized synthesis.
- Executing business strategy analysis where independent financial modeling and risk assessment are merged into a final report.
How Agent Team Workflows Works
- The Lead agent confirms the scope, including objective, domain, and preferred pipeline pattern.
- A detailed Workflow Instance Spec is generated to define role cards and artifact expectations.
- A team of four agents is initialized with specialized identities (e.g., Architect, Developer, Tester, Reviewer).
- The Lead decomposes the objective into specific tasks with clear dependencies and acceptance criteria.
- Specialized teammates are spawned with rich context, receiving the specific inputs and constraints required for their step.
- The Lead manages the handoff of artifacts between agents, ensuring each output meets the Definition of Done.
- The final results are synthesized into a comprehensive deliverable for the user.
Agent Team Workflows Setup
To use these agent orchestration features within your Openclaw Skills environment, you must enable experimental agent teams. Add the following to your ~/.claude/settings.json file:
{
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
}
}
Agent Team Workflows Data Schema & Taxonomy
The skill utilizes a structured taxonomy to manage data and communication between agents:
| Component | Description |
|---|---|
| Workflow Spec | A universal template defining the objective, pattern, and domain preset. |
| Role Cards | Specialized profiles for each teammate (Planner, Builder, Validator, Critic). |
| Artifact Contracts | Strict definitions for the format and content of files passed between steps. |
| Pattern Library | A set of 4 canonical control-flow patterns (sequential, parallel, iterative, fan-out). |
| Definition of Done | A checklist used by the Lead to verify the quality and completeness of the final output. |
Agent Team Workflows Advanced Features
- Support for 4 canonical pipeline patterns: sequential, parallel-merge, iterative-review, and fan-out-fan-in.
- Domain remapping for software dev, content creation, data analysis, business strategy, and research.
- Automated failure handling protocols for stuck teammates or insufficient output quality.
- Specialized Lead Discipline Rules that enforce delegation, context relay, and high-risk action gating.
- Resource optimization through direct messaging and token-efficient coordination strategies.
SKILL.md
Loading
Related Openclaw Skills
Agnxi Search
A powerful discovery utility that allows agents to search the Agnxi.com database for curated AI tools and MCP servers.
Tavily Web Search and Research
A powerful toolset for AI agents to perform real-time web searches, extract structured content, and execute deep research tasks with source citations.
apix
A CLI utility that allows developers and agents to discover, inspect, and call REST API endpoints using local markdown documentation.
Security Scanner
A professional security automation toolkit for penetration testing, service discovery, and vulnerability assessment across web apps and infrastructure.
Agent Task Manager
A robust orchestration framework for managing complex, multi-step agent workflows with persistent state and rate-limit handling.
Aubrai Longevity Research
A specialized AI research engine designed to answer complex questions about longevity and lifespan extension using cited scientific sources.
Featured*
