🤖
AI EngineeringTypeScript

MetaBot Teams

by xvirobotics

MetaBot Teams is an AI Engineering skill for Claude Code, published by xvirobotics in metabot.

953 stars157 forkson xvirobotics/metabotAdded 2026/08/21Repository updated 2026/08/08
agent-nativeagent-organizationai-agentanthropicclaude-agent-sdkclaude-codefeishufeishu-botkimikimi-codelarkmetamemorymetaskillmoonshotmulti-agentself-improvingtask-schedulertelegram-botvoice-assistantwechat-bot
Install in seconds
Install MetaBot Teams
Copy MetaBot Teams 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/xvirobotics/metabot/tree/main/packages/skills/metabot-team ~/.claude/skills/metabot-team

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/xvirobotics/metabot.git

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

In this catalog

Source file
packages/skills/metabot-team/SKILL.md in xvirobotics/metabot
Installs to
~/.claude/skills/metabot-team
Collection
One of 8 skills cataloged from this repository
Category
AI Engineering2451 skills

What MetaBot Teams does

MetaBot Teams provides a CLI for creating and inspecting durable agent teams, spawning teammates, exchanging messages, and managing tasks and runs across sessions. Use it to coordinate multi-agent work and recover state after restarts.

MetaBot Teams is cataloged under AI Engineering on DirSkills. MetaBot Teams comes from a repository tagged agent-native, agent-organization, ai-agent, anthropic and claude-agent-sdk.

Documentation

README

MetaBot Agent Teams CLI

This Skill documents the metabot teams command surface and its durable-state semantics. It does not define Agent execution policy.

Core Model

Team = Agents + Messages + Tasks + Runs.

  • Agents retain a stable Team identity across engine Sessions.
  • Messages are the normal conversational handoff surface.
  • Tasks record durable assignment, dependencies, status, and result.
  • Runs record individual executions, output, failure, retry, cancellation, and card state.
  • Multiple dispatches to the same Agent create independent Tasks and Runs.

Inspect A Team

This is the opening of the README. Read the full README on GitHub.

Frequently asked about MetaBot Teams

  • What else does xvirobotics publish alongside MetaBot Teams?

    MetaBot Teams is one of 8 skills that DirSkills catalogs from xvirobotics/metabot, the repository it ships in. Its siblings there include Doubao TTS, Flows and Frontend Design. Each one is a separate skill with its own page in this directory, installs the same way MetaBot Teams does, and is maintained by xvirobotics in that same repository. The rest of the collection is listed on the xvirobotics/metabot page.

  • How does MetaBot Teams compare to other AI Engineering skills?

    MetaBot Teams ranks #1425 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 MetaBot Teams against them. Open each page to compare what they document and how they install.

More from xvirobotics/metabot

MetaBot Teams is one of 8 skills cataloged on DirSkills from xvirobotics/metabot.

See all 8 skills