Design optimal agent team compositions with sizing heuristics, preset configurations, and agent type selection. Use this skill when deciding how many agents to spawn for a task, when choosing between a review team versus a feature team versus a debug team, when selecting the correct subagent_type for each role to ensure agents have the tools they need, when configuring display modes (tmux, iTerm2, in-process) for a CI or local environment, or when building a custom team composition for a non-sta
The 'team-composition-patterns' skill provides a framework for designing optimal multi-agent teams, with a focus on team sizing, agent type selection, and display configuration. This skill addresses the challenges of efficiently structuring teams for various tasks, from simple bug fixes to complex system reviews. By using heuristic models, users can determine the appropriate number of agents for any given task and assign roles effectively based on the complexity and type of work. This skill also facilitates team configuration in both local and CI environments, ensuring that agents are equipped with the right tools and display setups for their specific roles.
Use the team sizing heuristics table to select the team size based on task complexity. For example, a simple task may require 1-2 agents, while a complex task might need 4-5 agents.
Yes, you can build custom team compositions for non-standard workflows, such as migrations or security audits, by selecting the right agent types and display modes.
For debugging, use the 'team-debugger' agent type, which is optimized for handling multiple hypotheses and root cause investigations.
Yes, the skill allows configuring display modes for both CI environments (like tmux or iTerm2) and local setups to ensure smooth team operations.
Preset team configurations are suited for specific tasks such as code reviews, debugging, or feature development. They may not be ideal for non-standard workflows without custom modifications.
Quick Setup:
.claude/skills/Repository
wshobson/agents