Skip to main content
Back to the field guide

A field guide to the /pave-catalog skill

AI Service Catalog Design

Teams cannot operate what they cannot inventory. /pave-catalog builds a service catalog with owners, dependencies, health endpoints, and docs links.

Pave · Platform Engineering7 min readJanuary 14, 2026

A team that cannot list its services cannot operate them. The on-call engineer paged at 3am does not know who owns the service that broke. The new hire does not know which services exist. The architecture review skips services nobody mentioned. The catalog is the artifact that prevents these gaps.

The /pave-catalog skill builds the service catalog. Service inventory with owners, descriptions, tech stacks, upstream and downstream dependencies, health status endpoints, and documentation links. The catalog can be implemented in Backstage, a static site, or a structured document depending on team size and tooling.

What the catalog contains

Per service: name, description, owner team and primary contact, tech stack, upstream dependencies (what this service calls), downstream dependencies (who calls this service), health endpoint, runbooks link, source repo link, deploy environment links.

Tonone's /pave-catalog skill builds service catalogs with owners, dependencies, health endpoints, and documentation links.

Install

/pave-catalog ships with the Pave agent in Tonone for Claude Code.

1. Add to marketplace

$ claude plugin marketplace add tonone-ai/tonone

2. Install Pave

$ claude plugin install pave@tonone-ai

Frequently asked questions

What does /pave-catalog do?
It builds a service catalog with owners, descriptions, dependencies, health endpoints, and documentation links.
How do I install /pave-catalog?
Install Tonone for Claude Code via tonone.ai/get-started.

Pairs well with