# Deploy Qm

> Deploy the QM package from an organization-owned deployment repository to Fly.io or AWS, onboard an administrator, configure connectors, and optionally activate Slack.

- Skill: `evolvingagentslabs/deploy-qm-2` (Agent Skill, multi-file: 7 files)
- Install (CLI): `npx skillmds@latest add evolvingagentslabs/deploy-qm-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/evolvingagentslabs/deploy-qm-2/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: evolvingagentslabs (https://skillmd.com/u/evolvingagentslabs)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/evolvingagentslabs/deploy-qm-2

---


# Deploy QM

Read `../../../deployment.md` completely and follow it as the authoritative
workflow. Read only the selected provider reference. Read `references/email.md`
before collecting secrets, because sign-in needs an email transport and one of
its steps needs the operator's DNS. Read `references/slack.md` only when Slack
is requested.

A deployment needs a base model key and a way for people to sign in. Collect
both in the same pass. The base model provider is a deployment choice recorded
as `modelProvider`, not a setting to leave for the Admin page. Sign-in is either
the built-in `auth` broker, which needs an email transport, or an external OIDC
provider such as Slack, which needs no email at all — read `references/email.md`
only once the operator has chosen the broker.

Use the repository's installed `@yc-software/qm` dependency through
`npm exec qm -- <command>`. Do not require or clone the QM source repository.
Do not stop at infrastructure health: complete the acceptance checks and return
the handoff required by `deployment.md`.