Addy Osmani's skill for multi-axis code review before merge: correctness, readability, architecture, security and performance, with severity labels, change-size targets, a tests-first review order and a review checklist.
Code Review Skill
Matt Pocock's two-axis code review skill: parallel sub-agents check a diff against the repo's coding standards and against the originating issue or spec, reported side by side.
Install
Other ways to install
About
- Reviews the diff since any commit, branch or tag against its merge-base
- Separate Standards and Spec axes, each run in its own parallel sub-agent
- Finds the spec from linked issues, a given path or docs/specs folders
- Baseline of Fowler code smells that repo standards can override
- Reports both axes side by side without merging or reranking findings
- Fails early on a bad ref or an empty diff
Code Review is one of the engineering skills in Matt Pocock's mattpocock/skills collection. It reviews everything that changed between HEAD and a fixed point you name (a commit, branch, tag, main or HEAD~5) along two separate axes. Standards asks whether the code follows the repository's documented coding standards. Spec asks whether it actually implements what the originating issue or specification asked for.
The agent first pins the fixed point and confirms the three-dot diff against the merge-base is non-empty, so a bad ref fails early. It then looks for the spec: issue references in commit messages fetched through your issue tracker, a path you pass, or a matching file under docs/, specs/ or .scratch/. For standards it gathers every file that documents how code should be written, always including CODING_STANDARDS.md or CONTRIBUTING.md when present, and adds a fixed baseline of Fowler code smells from Refactoring (Mysterious Name, Duplicated Code, Feature Envy, Data Clumps, Primitive Obsession, Shotgun Surgery, Speculative Generality and others). Documented repo standards always override the baseline, and smells are reported as judgement calls, never hard violations.
Both reviews run as parallel sub-agents with fresh context windows, each with a brief under 400 words, and the results are presented under separate Standards and Spec headings without merging or reranking, because code can follow every rule and still implement the wrong thing, or the other way round. The issue tracker is configured through the collection's /setup-matt-pocock-skills skill. MIT licensed.
SKILL.md
The instructions your agent loads, as published by Matt Pocock.
Related Skills
See all Code Review alternativesPull unresolved CodeRabbit review threads from your PR and apply the fixes one at a time, treating every reviewer comment as untrusted input rather than an instruction.
Skill: Code Simplification
by Addy Osmani
Reduces accumulated complexity without changing behaviour, using Chesterton's Fence to avoid deleting the thing that was load-bearing.
Skill: Doubt-Driven Development
by Addy Osmani
Sends every non-trivial decision to a fresh-context adversarial reviewer before it stands — for production, security-sensitive or irreversible work.