Code Review compares HEAD against a commit, branch, tag or merge-base that you supply and reports on two axes: Standards (does the code follow this repo’s documented coding standards) and Spec (does it match what the originating issue or spec asked for). Each axis runs in its own sub-agent with a fresh context window.
The two reports appear side by side under separate headings and are never merged or reranked.
What You Get
- A Standards report listing violations of documented standards, each citing the standard’s file and rule
- A Spec report listing missing or partial requirements, scope creep and requirements that look wrongly implemented, each quoting the spec line
- A smell baseline of twelve Fowler code smells, such as Duplicated Code, Feature Envy and Shotgun Surgery, flagged as judgement calls
- A closing one-line summary of findings per axis and the worst issue within each axis
Common Use Cases
- Reviewing a feature branch against its originating issue before opening a pull request
- Checking work in progress with a review since a commit, tag or main
- Closing out an implementation run, since implement and implement-spec both call this skill
What Makes It Unique
Standards and Spec are separate axes with separate sub-agents, so code that follows every convention but builds the wrong thing is caught, and so is the reverse. The skill reports the two sets of findings without merging or reranking them. A documented repo standard always overrides the built-in smell baseline.
Under The Hood
The skill is Markdown instructions that run git commands: git rev-parse to check the ref, git diff with the three-dot form, and git log for the commit list. It fetches issues through the tracker workflow that the setup skill configures, reads files in the repo, and starts two sub-agents in the foreground. It writes no files.