tf-judge-criteria

What problem does it solve?

Terraform code quality often lacks consistent measurement, making it hard to compare modules and persuade teams to adopt best practices. This Skill provides objective rubrics, severity classifications, and an iterative refinement protocol to standardize assessments and drive improvements.

Core Features & Use Cases

• Evidence-Based Evaluation: Every judgment cites file:line references and relevant code quotes to ensure traceability.
• Actionable Feedback: Each issue includes concrete remediation steps with before/after examples to guide fixes.
• Calibrated Scoring: Applies a 1–10 production readiness scale with defined severities and constitution rules to enable consistent risk assessment.
• Governance & Compliance: Supports policy-driven evaluation for teams enforcing coding standards in Terraform configurations.

Quick Start

Run a quality evaluation on a Terraform project to generate a structured rubric and improvement plan.