🤖
AI EngineeringPython

Agent Team Design

by agentlas-ai

Agent Team Design is an AI Engineering skill for Claude Code, published by agentlas-ai in Agentlas-OS.

1.2K stars116 forkson agentlas-ai/Agentlas-OSAdded 2026/08/20Repository updated 2026/08/20
a2aagentagent-frameworkagent-os-desktopagent-skillsagentic-aiagentic-workflowagentosagentsagents-teamagentshubai-agentsautonomous-agentsllmllm-agentsllm-toolsmcpmulti-agent-systemsochestration
Install in seconds
Install Agent Team Design
Copy Agent Team Design into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/agentlas-ai/Agentlas-OS/tree/main/skills/agent-team-design ~/.claude/skills/agent-team-design

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/agentlas-ai/Agentlas-OS.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/agent-team-design/SKILL.md in agentlas-ai/Agentlas-OS
Installs to
~/.claude/skills/agent-team-design
Collection
One of 25 skills cataloged from this repository
Category
AI Engineering2451 skills

What Agent Team Design does

Agent Team Design defines agent teams, role boundaries, handoffs, memory owners, policy owners, and evaluation roles for multi-agent systems. Use it when creating a new team, a meta-agent, or an agent operating system repository.

Agent Team Design is cataloged under AI Engineering on DirSkills. Agent Team Design comes from a repository tagged a2a, agent, agent-framework, agent-os-desktop and agent-skills.

Documentation

README

Agent Team Design

Procedure

  1. Define the user job and target runtime.
  2. Start with one agent. Add team roles only when routing, memory, review, policy, or parallel ownership is useful.
  3. Use a visible public tree:
    • agents/10-single-agent-builder/agent.md
    • agents/20-multi-agent-team-builder/agent.md
    • agents/30-agentlas-packager/agent.md
  4. Add skills/<capability>/SKILL.md for reusable procedures.
  5. Add .agentlas/company-blueprint.json for topology.

Output

Return the role list, handoff direction, memory owner, policy owner, and eval owner.

Frequently asked about Agent Team Design

  • What else does agentlas-ai publish alongside Agent Team Design?

    Agent Team Design is one of 25 skills that DirSkills catalogs from agentlas-ai/Agentlas-OS, the repository it ships in. Its siblings there include Agentlas, Agentlas Auto-Activation and Agentlas Browser. Each one is a separate skill with its own page in this directory, installs the same way Agent Team Design does, and is maintained by agentlas-ai in that same repository. The rest of the collection is listed on the agentlas-ai/Agentlas-OS page.

  • How does Agent Team Design compare to other AI Engineering skills?

    Agent Team Design ranks #1201 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Agent Team Design against them. Open each page to compare what they document and how they install.

More from agentlas-ai/Agentlas-OS

Agent Team Design is one of 25 skills cataloged on DirSkills from agentlas-ai/Agentlas-OS.

See all 25 skills
🤖
2w ago

Agentlas

Agentlas provides a single entry point for all Agentlas commands, including staffing federated workforces, building agent teams, running DAG graphs, browser automation, and searching agent catalogues. Use it when orchestrating multi-agent systems.
AI Engineering
1.2K116
🤖
2w ago

Agentlas Auto-Activation

Agentlas Auto-Activation turns a project folder into an Agentlas-aware workspace with .agentlas memory and sitemap files. Use it when adding or auditing local runtime behavior that activates project continuity.
AI Engineering
1.2K116
🌐
2w ago

Agentlas Browser

Agentlas Browser runs headless browser interactions via CDP for Agentlas tasks, such as rendering pages, completing form flows, and capturing visual evidence when a URL or query requires a real browser.
Automation
1.2K116
🤖
2w ago

Agentlas Build

Agentlas Build designs, assembles, and packages installable single agents or multi-agent teams. Use it after /agentlas-build, /agentlas build, or /hep-build to classify mode, interview requirements, author routing card and soul, generate runtime adapters, and verify the package.
AI Engineering
1.2K116
🤖
2w ago

Agentlas Call

Agentlas Call invokes named Agentlas Hub or Cloud agents attached to the current project. Use it when you type /agentlas-call <agents> <context>, /agentlas call, or /hep-call to borrow and execute those agents.
AI Engineering
1.2K116
☁️
2w ago

Agentlas Cloud Workforce

Agentlas Cloud Workforce staffs specialist roles from the owner's private Agentlas Cloud packages. It is triggered by the /agentlas-cloud, /agentlas cloud, or /hep-cloud commands.
AI Engineering
1.2K116