Skip to main content

Infrahub Skills

Infrahub Skills is an open-source AI skills package covering the full Infrahub development lifecycle. Describe what you want to build in plain language, and the skills produce Infrahub resources that follow the platform's conventions: schemas, object data, generators, transforms, checks, and menus, ready to load into a running instance.

When you would reach for it​

You are modelling a new domain and the relationship identifiers have to match on both sides. You have a CSV export from the system Infrahub is replacing, and every column needs a home. You inherited a repository and cannot tell which of its files still follow current conventions. A generator runs, produces the wrong objects, and the traceback points at the SDK rather than at your code. An instance stops answering and support wants logs you have not collected before.

Each of those is a skill. The AI reads the one that matches, applies its rules while it writes, and leaves the rest unread. That last part is what keeps the assistant accurate on long sessions: a skill loads its entry point first and pulls in individual rule files only when the task reaches them.

Three ways to work​

Direct mode​

For well-scoped, single-skill tasks. Describe what you need and the AI matches it to the right skill automatically. Best for adding an attribute, creating a check, populating a batch of objects, or any task that maps to a single skill.

Spec-Driven Development (SDD)​

For complex or multi-part builds. The AI reasons through requirements with you first: capturing what needs to be built, validating the approach against Infrahub conventions, and laying out a task plan for review. Nothing is generated until you approve the plan. Best for designing new schema domains, building generator chains, or any task that involves design decisions across multiple skills. See Spec-Driven Development for details.

End-to-end execution​

For full lifecycle workflows. The AI generates files, loads them with infrahubctl, validates the result, and iterates if something fails, all in a single session.

Skills included​

SkillWhat it doesSkill name
Schema ManagerCreates, validates, and modifies Infrahub schema YAML from natural languageinfrahub-managing-schemas
Object ManagerProduces and updates YAML data files for infrastructure objectsinfrahub-managing-objects
Check ManagerBuilds and debugs Python validation checks for proposed change pipelinesinfrahub-managing-checks
Generator ManagerCreates, modifies, and debugs design-driven generators that auto-create infrastructure objectsinfrahub-managing-generators
Transform ManagerBuilds and debugs Python or Jinja2 transforms for config generation and data exportinfrahub-managing-transforms
Menu ManagerDesigns and restructures custom navigation menus for the Infrahub web UIinfrahub-managing-menus
Data AnalyzerQueries and analyzes live Infrahub data via MCPinfrahub-analyzing-data
Repo AuditorAudits a repository against Infrahub best practicesinfrahub-auditing-repo
Data ImporterConverts CSV/TSV inputs into Infrahub object YAML and loads onto a fresh branchinfrahub-importing-data
Diagnostics CollectorGuides infrahub-collect to gather a support bundle when Infrahub is misbehaving, and reviews it before hand-offinfrahub-collecting-diagnostics
Issue ReporterRoutes a bug or feature request to the right Infrahub-ecosystem repository and prepares a sanitized draft for your reviewinfrahub-reporting-issues
Skill Gap ReporterTurns friction with an Infrahub skill into a reviewed issue with a proposed rule change, filed through the Issue Reporterinfrahub-reporting-skill-gaps
Concept TutorTeaches Infrahub concepts through the learner's own repo and instance, with verified exercises and progress trackinginfrahub-teaching-concepts
Diagnostics AnalyzerTurns a collected diagnostic bundle into a triage report, correlating errors into incidents and matching them against known Infrahub issuesinfrahub-analyzing-diagnostics
NetBox Device Type ConverterConverts NetBox device-type and module-type definitions into Infrahub Object Templates via a mapping-profile-driven converterinfrahub-converting-netbox-device-types

A shared reference library (infrahub-common) provides GraphQL query syntax, .infrahub.yml configuration format, YAML structure conventions, and the Profiles vs Object Templates distinction to all skills.

Compatibility​

Infrahub Skills works with any AI tool that supports the Agent Skills format or reads custom context files from the project directory. Agents with plugin support get auto-detection and direct invocation; everything else activates passively from project context.

The full matrix and the per-tool setup are in Installation and setup.

Next steps​