Add launch skill: scenario to a verified, monitored Spice.ai Cloud project

AGENTS.md

@@ -39,7 +39,11 @@ with `skills/setup/scripts/spice-local.sh`, then hands off:
 setup → spicepod, secrets → connectors + datasets → acceleration, accelerators, cache, search, models, chat, sql, sdk
 ```
 
-`cookbook` is the recipe track, not greenfield bootstrap. `cloud` and `terraform` cover Spice.ai Cloud.
+`launch` is the Spice.ai Cloud counterpart: it takes a scenario to a deployed, verified, monitored
+project with `skills/launch/scripts/spice-launch.sh` — create or fork → secrets → deploy (confirming
+the endpoint serves the new spicepod) → verify (rows, model answers, MCP) → monitors → fire drill →
+runbook. `cookbook` is the recipe track, not greenfield bootstrap. `cloud` and `terraform` cover
+individual Spice.ai Cloud operations and infrastructure as code.
 Keep each skill self-contained: skills can be installed one at a time, so a skill may mention another
 skill's helper but must not depend on it.
 

CHANGELOG.md

@@ -2,6 +2,23 @@
 
 ## Unreleased
 
+- Add the `launch` skill: from a plain-language scenario ("serve Snowflake, Postgres, and S3 data to
+  agents with OpenAI") to a Spice.ai Cloud project that is designed, deployed, verified, monitored,
+  and documented. `scripts/spice-launch.sh` creates the managed project (or forks a base project to
+  inherit linked org secrets), stores secrets without printing them or putting them on a command
+  line, and deploys. It watches the new instance and stops early on an unresolved secret, a dataset
+  stuck in Error, or a model that fails to load, instead of waiting out a rollout that stays
+  `in_progress` while the old version serves. `verify` proves rows from every dataset and view, a
+  model answer grounded in the data, embeddings and search, and an MCP session across several tool
+  calls, and records a p50/p99 baseline. `monitors` creates the demo, POC, or production alert set in
+  place, and `fire-drill` proves an alert is delivered. `handoff` writes `RUNBOOK.md` and
+  `AGENT-CONNECT.md`. The skill documents what live testing found: Cloud MCP needs
+  `runtime.mcp.allowed_hosts: ["*"]`, multiple replicas break MCP sessions, OpenAI SDK clients need
+  `Accept-Encoding: identity` for non-streaming chat completions, org secrets reach a project only
+  when linked, Cloud's schema needs search `row_id`s as lists, resizing needs private compute, and
+  local or private-network sources are rejected before deploy. The skill never reads the user's
+  mailbox or chat to confirm an alert; it asks them.
+
 - Make `setup` the single entry point that takes an agent from an empty directory to a verified SQL
   result. Its Quick Start used to stop at an empty `spice init`, which `spice validate` reports as `OK`
   with zero datasets. The new `scripts/spice-local.sh` checks the existing installation, seeds a local

README.md

@@ -15,8 +15,10 @@ and finishes only when a query returns rows. Then it hands off to the specialist
 setup → spicepod, secrets → connectors + datasets → acceleration, accelerators, cache, search, models, chat, sql, sdk
 ```
 
-[cookbook](skills/cookbook/) runs ready-made recipes instead of your own project, and
-[cloud](skills/cloud/) and [terraform](skills/terraform/) manage Spice.ai Cloud. You install Spice
+To go further — a scenario such as "serve our Snowflake, Postgres, and S3 data to agents with OpenAI"
+deployed to Spice.ai Cloud, tested end to end, monitored with alerts, and handed off with a runbook —
+use [launch](skills/launch/). [cookbook](skills/cookbook/) runs ready-made recipes instead of your own
+project, and [cloud](skills/cloud/) and [terraform](skills/terraform/) manage Spice.ai Cloud resources. You install Spice
 itself by following the [installation docs](https://spiceai.org/docs/installation); the skills check
 `spice version` and never install or upgrade it.
 
@@ -193,6 +195,7 @@ The skills are version-aware. Each one names the release line it is written for,
 | Skill | Description |
 | --- | --- |
 | [setup](skills/setup/) | **Start here.** Take a directory to a running runtime that answers SQL with rows, using an existing installation; CLI, ports, and `/v1/sql` reference |
+| [launch](skills/launch/) | Take a scenario to a Spice.ai Cloud project that is deployed, verified (rows, model answers, MCP), monitored with alerts and a fire drill, and handed off with a runbook; for demos, POCs, and greenfield production |
 | [cookbook](skills/cookbook/) | Find, set up, and run recipes from the Spice.ai cookbook, including from a pull request |
 | [spicepod](skills/spicepod/) | Create and configure spicepod.yaml manifests |
 | [datasets](skills/datasets/) | Connect to data sources and query across them with federated SQL |
@@ -220,6 +223,7 @@ related commands; configuration topics are not invented CLI subcommands.
 | `chat` / `models` | `spice chat`, `spice models`, OpenAI-compatible APIs and provider configuration |
 | `datasets` / `connectors` | Dataset and catalog configuration, `spice datasets`, `/v1/datasets` |
 | `cloud` | Available `spice cloud` commands and the Cloud Management API |
+| `launch` | `spice cloud project`/`deploy`/`status`/`logs`, Management API monitors and forks, `/v1/sql`, `/v1/chat/completions`, `/v1/mcp` |
 | `sdk` | Client construction, endpoints, credentials, typed results, and language-specific methods |
 | `spicepod`, `acceleration`, `accelerators`, `cache`, `secrets` | Runtime configuration and related operations |
 | `terraform` / `cookbook` | Infrastructure as code and documented recipe workflows |