Infrahub Skills is an AI skills package for infrastructure engineers and platform teams using Infrahub. It gives their AI coding assistant built-in expertise on Infrahub. Teams describe what they want in plain language, and the skills produce valid, best-practice schemas, generators, transforms, checks, and more. Whether they’re prototyping a new use case, extending an existing implementation, or onboarding a new engineer, Skills helps them get more out of Infrahub, faster.
Bringing Infrahub expertise to where you already work
Infrahub is the AI-ready data management platform for network and infrastructure automation at scale. Its extensible, schema-first architecture lets teams model any domain, version every change, and drive reliable automation across production environments. With that flexibility comes a set of conventions and best practices.
Teams typically pick that expertise up over time — through documentation, example projects, and conversations with more experienced colleagues. It works, and it’s how platforms of this depth get learned. But it can be time-consuming and sequential, and the expertise gained on one project doesn’t automatically carry over to the next engineer who joins the team.
AI changes what’s possible. We can now embed platform expertise directly into the AI coding assistants engineers already use so that anyone building with Infrahub gets the benefit of conventions and best practices they haven’t yet developed, applied automatically to their own work, and explained along the way.
What it looks like to build with Skills
Infrahub Skills is useful whether you’re just getting started, deep in a build, or running Infrahub in production.
Prototyping a new use case: Describe what you want to model in plain language and see what it looks like in Infrahub. No need to master the schema format first. What used to take weeks of ramp-up to prove out can happen in hours.
Actively building: Infrahub Skills shortens the loop between idea and working implementation. Infrahub conventions are applied at the point of generation, so output works the first time. There’s no rework loop needed to unwind non-standard patterns later. Six skills cover the core build workflow:
- Schema Manager turns a plain-language description of your domain into a valid schema, with naming conventions, relationships, and generics applied automatically.
- Object Manager populates your schema with data files that load in the right order.
- Generator Manager builds generators that create infrastructure objects from design definitions.
- Transform Manager creates Python or Jinja2 transforms that turn Infrahub data into device configs, reports, and other formats.
- Check Manager writes Python validation checks that run in proposed change pipelines.
- Menu Manager shapes the web UI to match how your team thinks about your data.
Extending a production implementation: Infrahub Skills helps you keep moving. Add new features. Build integrations with external systems like spreadsheets, CMDBs, NetBox, and Nautobot, historically one of the most time-consuming parts of any Infrahub project. When new engineers join the team, Infrahub expertise travels with the repo rather than being trapped in Slack history. Two skills are built specifically for this stage:
- Data Analyzer queries a running Infrahub instance in plain language — cross-node correlation, drift detection, blast-radius analysis, data quality audits — without writing GraphQL by hand.
- Repo Auditor surfaces where a project has drifted from best practices over time and reports what to adjust.
Three ways to work
Not every task needs the same treatment. Infrahub Skills supports three modes, matched to task complexity:
- Direct mode — for well-scoped, single-skill tasks. Describe what you need, and the AI matches it to the right skill and produces it. Best for adding an attribute, creating a check, or populating a batch of objects.
- Spec-Driven Development (SDD) — for complex, multi-part builds. The AI first reasons through the requirements with you, validates the approach against Infrahub conventions, and lays out a task plan for review. Nothing is generated until you approve the plan.
- 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.
Across all three, the AI explains the reasoning behind every recommendation. The result: users build real Infrahub expertise as they work.
How to use it
Infrahub Skills runs inside the AI coding assistant you already use. Once it’s installed, open your Infrahub project, and the skills are picked up automatically. From there, describe a task in plain language and let the AI match it to the right skill or invoke one directly if you know which you want.
Infrahub Skills follows the open Agent Skills format, so it works with Claude Code, GitHub Copilot, Cursor, Windsurf, Amp, Cline, and Codex — any AI tool that reads custom context files from the project directory.
Get started
Head over to the Infrahub Skills documentation for installation options for your AI tool of choice, a walkthrough of each skill, and more on how to get the most out of them.
Community contributions are welcome — new rules, examples, and improvements can be submitted via PR on the GitHub repo.
And if you’re looking for a live introduction, Solution Architects Benoit Kohler and Phillip Simonds will be conducting a livestream on May 11th, which you can register for here.
