review

name

review

description

Review changes against a supplied comparison target: a fixed Git point (commit, branch, tag, or merge-base) or a list of files to review against the rest of the current changes. Runs two parallel axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?) — and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, selected files within a larger change, or asks to "review since X".

Review

Two-axis review of the diff against the comparison target the user supplies. The target may be:

• A fixed Git point such as a commit SHA, branch name, tag, main, or HEAD~5.

• A list of files to review as the target subset, with the rest of the current changes treated as surrounding context.

• Standards — does the code conform to this repo's documented coding standards?

• Spec — does the code faithfully implement the originating issue / PRD / spec?

Both axes run as parallel sub-agents so they don't pollute each other's context, then this skill aggregates their findings.

The issue tracker should have been provided to you — run /setup-matt-pocock-skills if docs/agents/issue-tracker.md is missing.

Process

1. Pin the comparison target

Whatever the user said is the comparison target. Don't be opinionated; pass it through.

If the target is a fixed Git point, capture the diff command once: git diff <fixed-point>...HEAD (three-dot, so the comparison is against the merge-base). Also note the list of commits via git log <fixed-point>..HEAD --oneline.

If the target is a list of files, capture both commands once:

• Review diff: git diff HEAD -- <file> [<file> ...]
• Context diff: git diff HEAD -- . ':(exclude)<file>' [':(exclude)<file>' ...]

Tell the sub-agents that the review diff is the subject of the review, and the context diff is only for understanding how those files relate to the rest of the current changes. Do not report findings against context-only files unless they directly explain a finding in the review diff.

If the user didn't specify a comparison target, ask: "Review against what — a branch, a commit, main, or a list of files?" Don't proceed until you have it.

2. Identify the spec source

Look for the originating spec, in this order:

1. Issue references in the commit messages (#123, Closes #45, GitLab !67, etc.) — fetch via the workflow in docs/agents/issue-tracker.md.
2. A path the user passed as an argument.
3. A PRD/spec file under docs/, specs/, or .scratch/ matching the branch name or feature.
4. If nothing is found, ask the user where the spec is. If they say there isn't one, the Spec sub-agent will skip and report "no spec available".

3. Identify the standards sources

Anything in the repo that documents how code should be written. Common locations:

• CLAUDE.md, AGENTS.md
• CONTRIBUTING.md
• CONTEXT.md, CONTEXT-MAP.md, per-context CONTEXT.md files
• docs/adr/ (architectural decisions are standards)
• .editorconfig, eslint.config.*, biome.json, prettier.config.*, tsconfig.json (machine-enforced standards — note them but don't re-check what tooling already checks)
• Any STYLE.md, STANDARDS.md, STYLEGUIDE.md, or similar at the repo root or under docs/

Collect the list of files. The Standards sub-agent will read them.

4. Spawn both sub-agents in parallel

Send a single message with two Agent tool calls. Use the general-purpose subagent for both.

Standards sub-agent prompt — include:

• The full review diff command, any context diff command, and commit list if relevant.
• The list of standards-source files you found in step 3.
• The brief: "Read the standards docs. Then read the diff. Report — per file/hunk where relevant — every place the diff violates a documented standard. Cite the standard (file + the rule). Distinguish hard violations from judgement calls. Skip anything tooling enforces. Under 400 words."

Spec sub-agent prompt — include:

• The review diff command, any context diff command, and commit list if relevant.
• The path or fetched contents of the spec.
• The brief: "Read the spec. Then read the diff. Report: (a) requirements the spec asked for that are missing or partial; (b) behaviour in the diff that wasn't asked for (scope creep); (c) requirements that look implemented but where the implementation looks wrong. Quote the spec line for each finding. Under 400 words."

If the spec is missing, skip the Spec sub-agent and note this in the final report.

5. Aggregate

Present the two reports under ## Standards and ## Spec headings, verbatim or lightly cleaned. Do not merge or rerank findings — the two axes are deliberately separate so the user can see them independently.

End with a one-line summary: total findings per axis, and the worst single issue (if any) flagged.

Why two axes

A change can pass one axis and fail the other:

• Code that follows every standard but implements the wrong thing → Standards pass, Spec fail.
• Code that does exactly what the issue asked but breaks the project's conventions → Spec pass, Standards fail.

Reporting them separately stops one axis from masking the other.