Which skill do I use?

Fifteen skills is a lot to hold in your head. You do not have to: start from whatever you already have in front of you, and each row names the skill that takes it from there.

Start from what you have

The groups are the ones in the sidebar, in the same order, so skim the group matching the stage you are at. Each skill's infrahub-* name is in the catalog on the front page.

Before anything else

You have	You want	Go to
No Infrahub background yet	Understanding, taught against your own repo	Concept Tutor

Build your model

You have	You want	Go to
A data model in your head or on a whiteboard	Valid schema YAML	Schema Manager
A schema, and no data in it yet	Object YAML you can load	Object Manager
A crowded web UI sidebar	A grouped custom menu	Menu Manager

Automate

You have	You want	Go to
A design document and repeated build work	Objects generated from the design	Generator Manager
Infrahub data and a target format	Device configs, exports, or reports	Transform Manager
A rule people keep breaking	A check that blocks the proposed change	Check Manager

Load data in

You have	You want	Go to
A CSV or TSV export from another system	Those rows as Infrahub objects	Data Importer
A NetBox device-type repository	Infrahub Object Templates	NetBox Device Type Converter

Operate and inspect

You have	You want	Go to
A running instance and a question	An answer, without writing GraphQL	Data Analyzer
A repository you inherited	A compliance report against best practices	Repo Auditor

When something breaks

You have	You want	Go to
An instance that is broken	A redacted bundle to hand to OpsMill	Diagnostics Collector
A collected bundle	A triage report naming the likely cause	Diagnostics Analyzer
A bug or a feature idea for Infrahub	A filed, routed, sanitized issue	Issue Reporter
A skill that kept getting it wrong	An issue proposing the rule change	Skill Gap Reporter

Pairs that are easy to confuse

Data Analyzer, Check Manager, Transform Manager

All three read Infrahub data. They differ in what happens to the answer.

Use Data Analyzer when...	Use Check Manager when...	Use Transform Manager when...
Answering a one-time question	Enforcing a rule in the pipeline	Producing a repeatable scheduled report
Interactive, exploratory analysis	Blocking changes that violate policy	Generating artifacts (configs, exports)
No pipeline integration needed	Automated enforcement required	Output needs to be stored as a versioned artifact

Diagnostics Collector, Diagnostics Analyzer

Sequential, not alternatives. Collect first, then analyze.

Use the Diagnostics Collector when...	Use the Diagnostics Analyzer when...
Infrahub is misbehaving and no bundle exists yet	A bundle already exists, or you have its contents
You need the right infrahub-collect command for your symptom	You need to know what the collected logs actually say
Output is a support bundle on disk	Output is a findings report citing that bundle
The next step is sharing it with OpsMill	The next step is an upgrade, a comment on an existing issue, or a new report

Concept Tutor, the managing skills, Data Analyzer

Use Concept Tutor when...	Use a managing skill when...	Use Data Analyzer when...
The learner wants to understand a concept	The learner wants the artifact built for them	The learner wants a live operational answer
Progress and exercises matter	Correctness and load-readiness matter	Speed and accuracy on current data matter
Output is a lesson and a verified exercise	Output is a schema, object, check, transform, generator, or menu file	Output is an answer, not a file

You do not have to choose

An agent that supports the Agent Skills format activates them on its own. Describe the task and the right skill fires. This page is for when you want to read ahead, or when two skills look like they overlap and you want to know which one owns the job.

For a build that spans several skills, see Spec-Driven Development.