Reviews PostgreSQL and MySQL schema migrations (raw SQL or ORM-generated) for table locks, rewrites, data loss, and breaking changes, then proposes safe zero-downtime rewrites with a clear verdict.
Reviews and rewrites Git commit messages to Conventional Commits quality — clear type/scope, imperative subject, useful body explaining why — and trains the author with concrete before/after feedback.
Reads Conventional Commits or a changelog snippet, classifies fix/feat/breaking changes, and recommends the next SemVer bump (patch, minor, or major) with a clear rationale and a preview of the resulting version. Use when a user asks "what version should I ship?", "is this a breaking change?", or "bump SemVer from these commits". Includes a tested stdlib Python advisor.
Reviews PostgreSQL and MySQL tables (schema.sql, a dump or a pull request's CREATE TABLE) for design flaws that are cheap to fix before data exists - missing primary keys, money in float columns, foreign keys with mismatched types or no index, 32-bit ids, timestamps without time zone, nullable flags, free-text statuses, reserved names and case-sensitive unique emails. Returns corrected DDL. Includes a stdlib Python linter with --self-test.
Reviews Dockerfiles for security, image size, build cache, and runtime reliability: secrets baked into layers, running as root, unpinned base images, curl piped to a shell, ADD misuse, leftover apt and pip caches, cache-busting dependency installs, shell-form CMD, and missing multi-stage builds or health checks, then writes a corrected Dockerfile and .dockerignore. Use when a user shares a Dockerfile and asks "review my Dockerfile", "why is my image so big?", or "is this container secure?".
Reviews dependency update PRs from Dependabot or Renovate: reads the changelogs, flags breaking changes and security fixes, and tells you which ones are safe to merge in bulk.
Reviews database migrations in pull requests for locking, data loss and rollback risk before they reach production.
Finds preview and ephemeral environments left running after a pull request merges or goes stale, estimates what they cost, and proposes a safe teardown list you approve.
Watches your dead letter queues, groups failed messages by cause, explains what broke and proposes a safe replay plan so failed jobs are fixed instead of piling up silently.