gitlab-ci-kiro-pipeline

# GitLab CI/CD Pipelines with Kiro CLI Headless Mode Build `.gitlab-ci.yml` pipelines where Kiro CLI acts as an AI reviewer/analyst on merge requests. The pattern: each job installs Kiro CLI in a throwaway container, gathers context (the MR diff, config files, failure logs), and runs `kiro-cli chat --no-interactive` with a role-scoped prompt. Output goes to the job log and optionally gates the merge. ## Workflow 1. **Understand the repo and goals.** Ask (or infer from the repo) which checks the user wants: advisory review only, or merge-blocking gates? Which languages/config layouts exist? Is there an existing `.gitlab-ci.yml` to extend? 2. **Pick jobs from the recipe catalog.** Read `references/job-recipes.md` for nine proven job patterns (code review, PII/secrets scan, test-failure analysis, diff issue detection, build-failure remediation, config drift, cross-repo config validation, duplication sync check, change-impact analysis). Copy only the ones the user needs. 3. **Start from the template.** `assets/gitlab-ci-template.yml` is a complete, working pipeline skeleton. Adapt stages and jobs rather than writing from scratch. 4. **Decide advisory vs. gating per job** (see below) and set `allow_failure` accordingly. 5. **Verify prerequisites with the user**: the `KIRO_API_KEY` CI/CD variable must be set (masked, protected) in GitLab → Settings → CI/CD → Variables, and confirm your runners have internet access to `https://cli.kiro.dev/install`. If your GitLab Runner sandbox ...