OpenClaw skill
claude-team
An OpenClaw skill that enables agents to interact with Anthropic's Claude Teams API for managing teams, members, and conversations. It supports creating teams, inviting members, listing resources, and executing prompts across team members. The skill provides tools like create_team, list_teams, and team_prompt for these operations.
Security notice: review the SKILL.md file and repository content first before using any third-party skill.
Files
Review the files below to add this skill to your agents.
SKILL.md content
Unable to load SKILL.md content from source.
How this skill works
- Creates team_size Claude agents during initialization, assigning roles if provided
- The lead agent (first Claude) decomposes the task into subtasks
- Assigns subtasks to team members
- Each agent works on its subtask independently using Claude API calls
- Agents review each other's work
- Lead agent synthesizes final result from reviews
- Returns the synthesized result
When to use it
- When assembling a virtual team of Claude AI instances to collaborate on complex tasks
- When delegating subtasks to specialized Claude team members based on defined roles
- When facilitating discussion rounds among Claude team members to refine ideas
- When synthesizing consensus outputs from multiple Claude team members
Best practices
- Store CLAUDE_API_KEY securely in environment variables
- Define TEAM_MEMBERS as a JSON array of lowercase GitHub usernames
- Prefix GitHub usernames with '@' in team mentions
- Use '/team:list' slash command to view configured team members
- Enable the skill only after verifying CLAUDE_API_KEY validity
Example use cases
- Creating a multi-Claude research team: Use create_claude_team to assemble a team of Opus (leader), Sonnet (researcher), and Haiku (data processor) for research projects, as shown in the tool example.
- Delegating analysis tasks to a Claude team: Delegate tasks like competitive analysis or trend research to a managed Claude team using delegate_to_team, with coordination handled internally.
- Monitoring and retrieving team outputs: Track team status with get_team_status and retrieve synthesized results using get_team_output for collaborative task completion.
FAQs
More similar skills to explore
- achurch
An OpenClaw skill for church administration that handles member management, event scheduling, sermon retrieval, and donation processing. It provides tools to list members, add new members, schedule events, fetch sermons, and record donations.
- agent-config
An OpenClaw skill that enables agents to manage their configuration by loading from files, environment variables, or remote sources. It supports retrieving, setting, and validating configuration values. The skill allows for hot-reloading of configurations.
- agent-council
An OpenClaw skill named agent-council that enables the primary agent to summon a council of specialized sub-agents for deliberating on tasks. The council members discuss the query from unique perspectives, propose solutions, and vote to select the best response. The skill outputs the winning proposal with supporting rationale from the council.
- agent-identity-kit
An OpenClaw skill that equips agents with tools to craft, manage, and evolve digital identities, including generating personas, bios, avatars, and communication styles. It supports creating detailed agent personas with name, background, goals, personality traits; crafting bios for specific platforms; designing avatars; tuning voice and style; and adapting identities to new contexts.
- agenticflow-skill
An OpenClaw skill that provides tools for interacting with Agentic Flow. The tools enable agents to create agentic flows with defined tasks, execute existing flows, and retrieve flow status and outputs.
- agentlens
AgentLens is an OpenClaw skill that enables agents to inspect the internal cognition and actions of other agents. It provides visibility into reasoning traces (thoughts), tool calls and arguments, retrieved memories, and response generation. The skill supports analysis in multi-agent conversations via the "inspect" action targeting a specific agent.