Team Builder
Interactive picker that discovers your agent personas, groups them by domain, dispatches up to five in parallel on one task, and synthesizes agreements and conflicts into one report.
- What
- Interactive picker that discovers your agent personas, groups them by domain, dispatches up to five in parallel on one task, and synthesizes agreements and conflicts into one report.
- Cost
- Free
- Needs
- Use "Team Builder" with your Muse.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor: an interactive menu for browsing and composing agent teams on demand, from a community contributor, listed here with credit to its creator. 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. Agents are discovered two ways, merged and deduplicated by name: the `claude agents` command (primary, covers user agents, plugin agents and built-ins automatically, including ECC marketplace installs) and file globs over `./agents/**/*.md` and `~/.claude/agents/**/*.md` (fallback, for reading agent content). Earlier sources take precedence on name collisions: user agents, then plugin agents, then built-ins. Both flat and subdirectory layouts are supported; the domain is inferred from the folder name, or from shared filename prefixes in flat layouts. You pick up to five personas, they are dispatched in parallel on one task, and their outputs are synthesized into a unified report of agreements and conflicts. From the affaan-m/ECC repository (MIT). Honest caveats: community skill; every dispatched agent is a full session, so five parallel agents cost five sessions of tokens; in flat layouts the domain algorithm splits at the first hyphen, so multi-word domains need the subdirectory layout. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Copy the install package below, then paste it into MuseThe install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Use "Team Builder" with your Muse. Prerequisites: Claude Code CLI. Agent personas as markdown files (first # heading = name, first paragraph = description) in ./agents/ or ~/.claude/agents/, or discoverable via `claude agents`. 1. Open the skill: https://github.com/affaan-m/ECC/blob/main/skills/team-builder/SKILL.md and copy the full SKILL.md text. 2. Paste it into a chat with Muse and add: "Show me my available agents" or "Build a team for [task]: I want Security + Architecture perspectives." 3. Pick up to five personas from the interactive menu and let Muse dispatch them in parallel, then read the synthesized agreements-and-conflicts report. Tip: compose cross-domain teams (e.g. Security + SEO + Architecture) when a decision has real trade-offs; single-domain teams just echo each other. Safety: a skill is plain-text instructions; it runs nothing by itself. Keep agent markdown free of secrets; parallel agents multiply token spend.
Saved to your recent installs. Find it anytime on /connect.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.