# Team Builder Packaging

Use when generating or auditing a multi-role agent team package with orchestrator, PM...

- Repository: https://github.com/agentlas-ai/Agentlas-OS (1593 stars)
- Category: Testing
- License: Apache-2.0
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add agentlas-ai/Agentlas-OS --skill team-builder-packaging -g -a claude-code -y`
Codex: `npx skills add agentlas-ai/Agentlas-OS --skill team-builder-packaging -g -a codex -y`
Cursor: `npx skills add agentlas-ai/Agentlas-OS --skill team-builder-packaging -g -a cursor -y`
Gemini CLI: `npx skills add agentlas-ai/Agentlas-OS --skill team-builder-packaging -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add agentlas-ai/Agentlas-OS`

## Description

Use when generating or auditing a multi-role agent team package with orchestrator, PM Soul, Memory Curator, Policy Gate, workers, eval, QA, handoffs, and runtime adapters.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Team Builder Packaging

## Procedure

1. Start with the orchestrator/HQ.
2. Run `contracts/builder-interview-research-gate.md` before writing the roster:
   ask an 8-12 question first batch, research official sources, similar agent
   repositories or comparables, academic/professional theory, and plugin docs,
   compare tool/plugin choices, and write the domain-expert synthesis plus
   prompt-performance contract.
3. Add PM Soul or project owner.
4. Add Memory Curator and Memory Ticket handoff.
5. Add Policy Gate, eval judge, and QA/evidence gate.
6. Add workers only for real domain ownership proved by interview or research.
7. Add `docs/builder-interview.md`, `docs/research-sources.md`,
   `docs/tool-selection.md`, `docs/domain-expert-synthesis.md`,
   `docs/prompt-performance-contract.md`, and
   `.agentlas/capability-eval-plan.json` unless explicitly creating a minimal
   private scaffold.
8. Encode handoff and return contracts.
9. Emit one orchestrator/HQ global command in `.agentlas/global-commands.json`
   and runtime command files. Do not expose worker commands unless requested.
9b. Declare the execution graph in `manifest.json`. This is what the Hub runtime
   reads to build the team; a package that omits it is published, charged for as
   a team, and can never be called:

   ```json
   {
     "entrypoints": { "orchestrator": "agents/00-orchestrator/agent.md" },
     "roster": ["agents/10-<role>/agent.md", "agents/20-<role>/agent.md"]
   }
   ```

The rest: https://github.com/agentlas-ai/Agentlas-OS/blob/HEAD/.agents/skills/team-builder-packaging/SKILL.md