メニュー
Scoring rubrics, severity classification, evaluation methodology, and iterative refinement protocol for Terraform code quality assessment. Preloaded by code-quality-judge agent.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
SOC 職業分類に基づく
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/hashi-demo-lab/terraform-provider-aap --skill tf-judge-criteriaコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
Analyze and optimize Terraform provider acceptance test execution for maximum speed with 100% pass rate. Use when the user wants to run tests faster, analyze test timing, find slow tests, parallelize test execution, or optimize their test suite's throughput. Also use when the user mentions "test speed", "slow tests", "parallel tests", "test performance", "speed up tests", or asks why tests take so long.
Analyze GitHub issues for any repository to discover themes, assess community demand, and produce prioritized roadmap recommendations. Use when the user wants to understand issue trends, group issues by theme, prioritize features, plan a roadmap, triage a backlog, or assess community demand for a GitHub project. Also use when the user mentions "issue analysis", "backlog prioritization", "feature demand", "issue themes", "roadmap planning", or asks what users are asking for most in a repo.
Terraform provider acceptance test patterns using terraform-plugin-testing with the Plugin Framework. Covers test structure, TestCase/TestStep fields, ConfigStateChecks with custom statecheck.StateCheck implementations, plan checks, CompareValue for cross-step assertions, config helpers, import testing with ImportStateKind, sweepers, and scenario patterns (basic, update, disappears, validation, regression), and ephemeral resource testing with the echoprovider package. Use when writing, reviewing, or debugging provider acceptance tests, including questions about statecheck, plancheck, TestCheckFunc, CheckDestroy, ExpectError, import state verification, ephemeral resources, or how to structure test files.
| name | tf-judge-criteria |
| description | Scoring rubrics, severity classification, evaluation methodology, and iterative refinement protocol for Terraform code quality assessment. Preloaded by code-quality-judge agent. |
| Score | Level | Action |
|---|---|---|
| 9.0-10.0 | Exceptional | None — use as reference |
| 8.0-8.9 | Excellent | Optional refinement |
| 7.0-7.9 | Good | Address high-priority issues |
| 6.0-6.9 | Adequate | Fix critical issues before production |
| 5.0-5.9 | Below Standard | Rework required |
| 4.0-4.9 | Poor | Substantial redesign needed |
| 1.0-3.9 | Unacceptable | Complete rework required |
| # | Dimension | Weight | Key Criteria |
|---|---|---|---|
| 1 | Module Usage | 25% | Private registry, semantic versioning, minimal raw resources |
| 2 | Security & Compliance | 30% | No creds, encryption, IAM least privilege, audit logs. <5.0 = Not Production Ready |
| 3 | Code Quality | 15% | terraform fmt, naming, validation, DRY, organization |
| 4 | Variables & Outputs | 10% | Type constraints, validation rules, defaults, descriptions |
| 5 | Testing | 10% | terraform validate, .tftest.hcl, pre-commit hooks |
| 6 | Constitution Alignment | 10% | Matches plan.md, constitution MUST compliance |
Score formula: (D1×0.25) + (D2×0.30) + (D3×0.15) + (D4×0.10) + (D5×0.10) + (D6×0.10)
Security override: If D2 < 5.0, force "Not Production Ready" regardless of overall score.
Store evaluations in JSONL format at <FEATURE_DIR>/evaluations/:
{"timestamp":"ISO-8601","iteration":N,"overall_score":X.X,"dimension_scores":{...},"readiness":"status","critical_issues":N}