Pulumi Agent Skills
Official Pulumi skills: writing infrastructure as code, migrating from Terraform, CDK, CloudFormation and ARM, secrets in ESC
- 78 ★ on the repository
- Last commit
- Apache-2.0
Extended access
Why this level
- The agent may run pulumi commands that change cloud infrastructure
- The skills deal with secrets and credentials through ESC
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/pulumi-agent-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The agent may run pulumi commands that change cloud infrastructure
- The skills deal with secrets and credentials through ESC
This is third-party code. Review the repository files before installing.
What it does
Skills from the Pulumi team come in four groups. The core group teaches the agent to write reliable Pulumi programs, author components, use the Automation API and ESC, upgrade providers safely and debug a failed pulumi up. The migration group converts Terraform, AWS CDK, CloudFormation, ARM and Bicep projects into idiomatic Pulumi code. Separate skills serve provider authors and hand off in-progress work to Pulumi Neo.
Who it is for. For DevOps engineers and developers who define cloud infrastructure with Pulumi or are moving to it.
Good fit when
- You are migrating a Terraform or CDK project to Pulumi
- You are writing or reviewing a Pulumi program in TypeScript or Python
- You are setting up secrets and dynamic credentials in Pulumi ESC
- You need to figure out why pulumi up failed
Not a fit when
- Your infrastructure stays on Terraform with no plans to migrate
- You manage servers by hand without infrastructure as code
Example request
Convert this Terraform configuration to Pulumi TypeScriptLimitations
Some skills rely on Pulumi Cloud: Discovery, the Context API, package usage tracking and Neo handoff require a Pulumi Cloud account. The skills do not replace reviewing pulumi preview before applying changes.
How to disable. Uninstall the pulumi plugin via /plugin in Claude Code or Codex, or delete the skill folders installed with npx skills.
FAQ
Which plugin should I install?
The pulumi plugin covers authoring, migration and Neo handoff. pulumi-migration and pulumi-delegation are subsets, so do not install them alongside pulumi. pulumi-package-maintenance is separate and meant for provider authors.
Why are plugins not found after configuring settings.json?
The marketplace key must be pulumi-agent-skills, matching the repo's marketplace.json, or plugins will not resolve.
Discussion
No questions or reviews yet.
Related
SkillsOfficial HashiCorp skills for Terraform and Packer: HCL style, modules, tests, imports, Stacks, provider development and image builds
Microsoft Agent Skills
Agent Skills
Official Microsoft skills that ground coding agents in Azure SDKs and Foundry for Python, .NET, TypeScript, Java and Rust
Microsoft Learn skills for nearly every Azure service: limits, configuration, security, architecture and troubleshooting with doc links
Terraform Skill
Terraform & OpenTofu Skill for AI Agents
A Terraform and OpenTofu best-practices skill: tests, modules, state, CI/CD and security scanning for AWS, Azure and GCP
A set of skills for agent work with AWS: common cloud service tasks packaged as ready instructions for a coding agent
A large base of DevOps, security, infrastructure and compliance skills for AI agents
README in short
The README describes four skill groups: migration, core Pulumi skills, provider maintenance and Neo handoff, with a table per skill. Install via /plugin in Claude Code, including declaratively through .claude/settings.json for teams, via the Codex marketplace or via npx skills per group. It gives example prompts for migration, ESC and components. Apache 2.0 licensed.
README badge
Original SKILL.md
--- name: pulumi-best-practices version: 1.0.0 description: Load when the user is writing, reviewing, or debugging Pulumi TypeScript/Python programs; asks about Output<T> or apply() usage; wants to create ComponentResource classes; needs to refactor resources without destroying them (aliases); is setting up secrets or config; or is configuring a pulumi preview/up CI workflow. Also load for questions about resource dependency order, parent/child resource relationships, or pulumi.interpolate. --- # Pulumi Best Practices ## When to Use This Skill Invoke this skill when: - Writing new Pulumi programs or components - Reviewing Pulumi code for correctness - Refactoring existing Pulumi infrastructure - Debugging resource dependency issues - Setting up configuration and secrets ## Practices ### 1. Never Create Resources Inside `apply()` **Why**: Resources created inside `apply()` don't appear in `pulumi preview`, making changes unpredictable. Pulumi cannot properly track dependencies, leading to race conditions and deployment failures. **Detection signals**: - `new aws.` or other resource constructors inside `.apply()` callbacks - Resource creation inside `pulumi.all([...]).apply()` - Dynamic resource counts determined at runtime inside apply