Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This skill provides Platform and DevEx teams with a structured response contract for managing Infrastructure as Code. It focuses on the rigorous review of modules, tests, and CI pipelines to ensure production-grade stability.
By applying version-aware guards, the skill helps engineers identify high-risk failure modes including state corruption, CI drift, identity churn, and blast radius concerns.
WHO IT'S FOR
Platform / DevEx teams
standardizing IaC patterns for AI agents
DevOps / Site Reliability Engineers
diagnosing state corruption and CI drift
Cloud Architects
reviewing infrastructure migration and risk controls
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Installs: terraform-skill plugin from the antonbabenko/agent-plugins marketplace. · Claude Code
Before you start
Claude Code.
Terraform 1.0+ or OpenTofu 1.6+ for infrastructure work.
Enter these commands in a Claude Code session. Use antonbabenko/agent-plugins as the marketplace; adding antonbabenko/terraform-skill as another marketplace causes a name clash.
Runtime and exact version, providers, backend, execution path, and environment criticality.
Use terraform-skill to review the module I provide for identity churn and secret exposure. Identify the most important issues, propose focused fixes, and give a validation plan tailored to my runtime and version. State any missing context as assumptions.
A short description of the resources, cloud provider, and environments.
Runtime and exact version, backend, execution path, and environment criticality.
Use terraform-skill to propose a small directory layout for the infrastructure I describe. Separate environment configurations from reusable modules, include a minimal example as documentation and a test fixture, and explain which resources belong together in a single-responsibility module.
Review production and nonproduction state isolation
Uses terraform-skill
Current state boundaries, backend configuration, and which environments or teams share each state.
Runtime and exact version, providers, execution path, and environment criticality.
Use terraform-skill to review the state layout I describe for production and nonproduction. Identify shared-state or oversized-stack blast-radius risks and propose a small, practical improvement with tradeoffs and validation steps. Keep this to a proposal without changing state.
Claude
Codex
Cursor
Gemini CLI
Copilot
OpenCode
Kiro
Antigravity