Shell Tool · engineering · Sentinel

Provision a Database

Spin up D1, R2, KV, Vectorize, Hyperdrive, Supabase, or Neon — and wire the binding/connection string.

Updated today

View as MarkdownsentinelsonnetcheapMax 6 turns

Overview

Wraps provision-database/SKILL.md + the provision-db tool. Picks the right database for the access pattern (D1 for SQL on CF, KV for hot key/value, Vectorize for embeddings, R2 for blobs, Hyperdrive for external Postgres pooling, Supabase for auth + Postgres + Storage, Neon for serverless Postgres). Provisions via wrangler or the provider's API and prints the binding stanza (for CF) or connection string (for external) ready to paste into wrangler.toml or .env.

When to use this

user wants a database for a new app
user says 'I need a DB' / 'add auth/users' / 'store X persistently'
user wants to add embeddings/vector search to an app

When NOT to use this

user already has a DB and wants to query it → use shell_exec with the right CLI
user wants to migrate between providers → that's a separate workflow, not provisioning

Example prompts

provision a D1 database called users-db

I need vector search — set up Vectorize

spin up Supabase for auth and Postgres

give me an R2 bucket for uploads

Inputs and output

Inputs

Field	Description
`type`	d1 \| r2 \| kv \| vectorize \| hyperdrive \| supabase \| neon
`name`	resource name

Output

Binding stanza (wrangler.toml format) or connection string (for external DBs).

Runtime profile

What the engine commits when this skill runs.

Property	Value	Meaning
Model tier	`sonnet`	The balanced default model class. Trades quality against cost for the vast majority of skill runs.
Cost class	`cheap`	A small, fast model. Cents per invocation.
Turn budget	`6`	Hard cap on tool-calling iterations before the engine forces a final answer.
Execution	`synchronous`	Runs inside the live turn; result lands in the same response.

Under the hood

Tools the engine exposes to this skill and integrations it needs.

Resource	Kind
`shell_exec`	tool

Tags: engineering, database, infrastructure

Execution template

Shell tools dispatch via a command template. The model substitutes user inputs into the placeholders before firing the underlying tool.

shell_execbash

1provision-db {{type}} {{name}}; follow provision-database/SKILL.md for wiring

Related skills

Skill	What it does
Spin up a Web App	Scaffold a fresh web app in /work, start the dev server, surface the live preview URL.
Clone a Website	Fire ultron-capture: spider the site, deploy a branded clone, surface the URL when ready.
Build an Agent	Spin up an autonomous agent on the agent-runtime satellite — try templates first, custom build only if no fit.
Deploy to Cloudflare	Ship the current /work to Pages, Workers, or Containers — then verify the live URL.
Push to GitHub	Initialize /work as a git repo, create the GitHub repo, push, return the URL.
Swap Page Sections	Reorder <section> blocks in a minified HTML file with byte-level safety.

Invoking this from an agent

Three paths reach this skill. From the chat UI, a user can type the persona slash command followed by a natural request and the discovery step resolves to this skill automatically. From the MCP server, fetch the skill detail with get_skill({id: "provision-database"}) and then invoke it through the agent runtime once the authenticated tier ships. From your own code, hit /docs/skills/provision-database/llm.txt for the token-efficient markdown body and feed it to your model directly.

Note

Every skill page has a canonical permalink and a markdown alternate that LLM crawlers consume via Accept: text/markdown. The full machine-readable catalog lives at /.well-known/agent-skills/index.json.