terraform-aws-base

Review SKILL.md quality for Waza readiness and agent-skills-instructions compliance. Use when evaluating SKILL.md quality, checking compliance with skill authoring standards, preparing skills for release, reviewing skill PRs, or running waza readiness checks.

Survey and update CHANGELOG.md from unreleased commits and undocumented releases (conventional, renovate, chore, pin/finalize subjects, and git tags). Use when the user asks to check, review, or update the changelog, or when automation supplies commit/release detect JSON. Default is survey only; edit CHANGELOG.md only when the user explicitly requests a fix or automation sets may_edit in Constraints.

Triage failing CI on integration branches and/or PR heads, classify failures, apply minimal fixes when actionable. Use when the user asks to triage or fix CI failures, when automation detects failed workflow runs, or when automation supplies detection JSON. Default is survey only; edit files only when the user explicitly requests a fix or automation sets may_edit in Constraints.

Detect documentation drift and patch affected docs — via git diff (hooks, manual) or structured detect JSON from an external caller. Keeps references, links, tables, and nav entries accurate. Use when syncing docs after code changes, before PRs, on doc sync requests, or when automation reports documentation drift. Default is survey only; edit documentation files only when the user explicitly requests a fix or caller constraints allow edits. Not for new document creation (use docs-creator) or markdown linting (use markdown-validation).

Review GitHub Actions workflows for correctness, security, and maintainability. Use when reviewing GitHub Actions workflow PRs, checking workflow security, evaluating CI/CD pipeline design, or assessing permissions and secret handling.

Validate GitHub Actions workflows for syntax and security with actionlint, ghalint, and zizmor. Use when committing workflow changes, running CI validation, or checking workflow security issues.

Update PR body content with deterministic baseline sections and optional full-body completion. Use when creating PRs or regenerating template-driven summaries.

Review instruction and rule files for structure, consistency, applyTo precision, and portable cross-references — package sources (`*.instructions.md`) and distributed agent rule targets (`.cursor/rules/*.mdc`, `.claude/rules/*.md`, `.kiro/steering/*.md`). Use when reviewing instruction PRs, audits, or distributed rule changes after package sync.

Validate Markdown syntax, formatting, and links using markdownlint-cli2 and markdown-link-check. Use when committing docs changes, checking broken links, or validating Markdown in pull requests.

Behavior-preserving structural refactors with stack gates. Survey candidates first, then apply all actionable in-scope structural fixes in one run — interactively or from automation hints (duplication_block, oversized_unit). Default is survey only; apply edits only when the user explicitly requests apply or automation sets may_edit in Constraints. Architecture: proposal first, one approved slice per apply batch. Not for lint-only style, features, behavior-changing bugfixes, or upgrades.

Review shell scripts for security, correctness, maintainability, and Bats suite pairing (TEST-00) with emphasis on operational safety. Use when reviewing shell script PRs requiring judgment beyond static checks, including whether paired Bats suites were added or updated per TEST-00.

Validate shell scripts with bash -n and shellcheck for syntax safety and maintainability checks. Does not enforce Bats suite pairing (TEST-00) — run `bats` and shell-script-review for that. Use when committing script changes, running CI validation, or debugging shellcheck findings in PRs.

Discover and classify technical debt from mechanical signals, apply closed-set fixes when requested, and publish structured reports (override via TECH_DEBT_DIR or report_file from detect JSON / Constraints). Use for scheduled automation scans, ad-hoc surveys from detection JSON, or when the user asks to fix safe documentation/dependency debt. Default is survey only; write report_file and apply fixes only when the user explicitly requests apply or automation sets may_edit in Constraints. Delegate structural work to refactor.

Review Terraform quality, security, and architecture decisions. Use when reviewing Terraform PRs requiring judgment beyond automated checks across modules and environments.

Validate Terraform syntax, linting, and security with terraform fmt/validate, tflint, and trivy. Use when committing Terraform changes, running CI validation, or checking IaC security issues.

Create or improve documentation files with Diataxis-aware placement and consistent naming. Use when the user wants to create any new documentation, improve existing docs, write a README, or restructure documentation. Also use when asked to "write docs", "improve this doc", "add a tutorial", "update the readme", or any request involving markdown documentation authoring, even if they don't explicitly say "create documentation".