メニュー
Reviews infrastructure changes: GitHub Actions workflows, Terraform, Dockerfiles, docker-compose, IaC. Focuses on supply-chain pinning, secret handling, least-privilege permissions, action versions, and CI failure modes. Always verifies action hash pins when present.
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。
SOC 職業分類に基づく
| name | code-review-infra |
| description | Reviews infrastructure changes: GitHub Actions workflows, Terraform, Dockerfiles, docker-compose, IaC. Focuses on supply-chain pinning, secret handling, least-privilege permissions, action versions, and CI failure modes. Always verifies action hash pins when present. |
| when_to_use | Use for reviews of infrastructure files (`.github/`, `*.tf`, `Dockerfile`, `docker-compose*`). Invoked directly with a PR URL or diff file path, or dispatched by `/code-review`. Follow all steps in order; do not shortcut based on this description. |
| argument-hint | [PR URL | path to diff file] [--source=...] [--pr=<URL>] [--file=<path>] |
| effort | xhigh |
| allowed-tools | Bash(git *) Bash(gh *) Read Grep |
Read ~/.claude/skills/code-review/references/review-shared.md and follow its source detection and diff fetching sections. If --source and the corresponding identifier args were passed, use those and skip any prompting.
If the diff contains any line matching ^\+\s*uses:\s+\S+@[0-9a-f]{40}, run the verification per the shared doc for every pinned action. Infra reviews always run this step when pins are present.
Read ~/.claude/skills/code-review/references/review-checklist.md first.
Focus on:
permissions: blocks at the job or workflow level, GITHUB_TOKEN scope minimised, no blanket write-all.latest), layer-cache friendliness, no secrets baked into image, multi-stage builds where appropriate.Apply the common review rules from the shared doc.
Format per the output section of ~/.claude/skills/code-review/references/review-shared.md. The linter section does not apply; do not run a linter.
Computes the optimal Claude usage-window ping schedule from work hours and creates or reconciles the scheduled cloud routines that pin the window boundaries.
Reviews changes to prose files (markdown, text, blog posts, docs). Focuses on voice, grammar, factual claims, dead links, and structure. Loads the project's voice or style guide when one exists. Skips linter and Actions hash verification.
Full code review for large or security-sensitive changes. Gathers requirements first, loads all relevant language references, runs the linter where applicable, applies the full review checklist with security as the top priority.
Abbreviated code review for small or low-stakes code changes. Skips requirements gathering. Skips the linter in PR mode (CI runs it). Focuses on correctness against obvious intent, readability, and pattern consistency. For large or security-sensitive diffs, use code-review-deep instead.
Orchestrator. Triages a PR, local diff, patch file, or staged/branch changes into one of four review types (content, code-lite, code-deep, infra) and dispatches to the matching child skill. Use this when you don't already know which depth or type of review you want. For a known type, invoke the child skill directly.
Produces a one-shot devil's-advocate critique of a plan, design, or decision: steel-manned strengths first, then severity-tagged findings each with a concrete alternative, then a verdict.