Team Builder

Interactive picker for composing ad-hoc teams from your agent collection. You point it at a directory of agent markdown files (flat or organized by domain), pick 2-5 agents from a menu, describe the task, and it spawns them all in parallel using the Agent tool. Works especially well when you need multiple perspectives on the same thing, like running a launch checklist through security, SEO, and architecture agents simultaneously. The synthesis step highlights where agents agree and where they conflict, which is more useful than reading five separate reports. Enforces a 5-agent limit to keep token costs sane. Requires agents formatted as markdown personas with headings and descriptions.

skills.sh installs: 5.4K
GitHub stars: 300.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/ecc --skill team-builder --agent claude-code

Installs into .claude/skills of the current project.

Files

Team Builder

Interactive menu for browsing and composing agent teams on demand. Works with flat or domain-subdirectory agent collections.

When to Use

You have multiple agent personas (markdown files) and want to pick which ones to use for a task
You want to compose an ad-hoc team from different domains (e.g., Security + SEO + Architecture)
You want to browse what agents are available before deciding

Prerequisites

Agent files must be markdown files containing a persona prompt (identity, rules, workflow, deliverables). The first # Heading is used as the agent name and the first paragraph as the description.

Both flat and subdirectory layouts are supported:

Subdirectory layout — domain is inferred from the folder name:

agents/
├── engineering/
│   ├── security-engineer.md
│   └── software-architect.md
├── marketing/
│   └── seo-specialist.md
└── sales/
    └── discovery-coach.md

SKILL.md on GitHub