Review Pr

Contract

• Input: problem or task defined by the skill body.
• Output: Markdown artifact or structured result with completion criteria met.
• Side effects: none (design/review/documentation only unless explicitly stated).
• Dependencies: none (self-contained unless linked to other skills).
• Stop condition: all process steps completed; artifact saved; criteria checked.
• Risk: low.
• Boundary: produces reasoning or documentation artifacts; does not modify external systems unless explicitly instructed.

Do not change source files, fix the PR, or merge it in this skill; publish findings only.

Two-axis review of the diff between HEAD and a fixed point the user supplies:

• 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-quirk-skills if docs/agents/issue-tracker.md is missing.

Process

1. Pin the fixed point

Whatever the user said is the fixed point — a commit SHA, branch name, tag, main, HEAD~5, etc. If they didn't specify one, ask for it.

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.

Before going further, confirm the fixed point resolves (git rev-parse <fixed-point>) and the diff is non-empty. A bad ref or empty diff should fail here — not inside two parallel sub-agents. If the branch is in a conflicted state from a merge/rebase or from review-request follow-up work, stop and route that state to resolving-merge-conflicts first; do not turn the conflict itself into Standards or Spec findings.

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, such as CODING_STANDARDS.md or CONTRIBUTING.md.

On top of whatever the repo documents, the Standards axis always carries the smell baseline below — a fixed set of Fowler code smells (Refactoring, ch.3) that applies even when a repo documents nothing. Two rules bind it:

• The repo overrides. A documented repo standard always wins; where it endorses something the baseline would flag, suppress the smell.
• Always a judgement call. Each smell is a labelled heuristic ("possible Feature Envy"), never a hard violation — and, like any standard here, skip anything tooling already enforces.

Each smell reads what it is → how to fix; match it against the diff:

• Mysterious Name — a function, variable, or type whose name doesn't reveal what it does or holds. → rename it; if no honest name comes, the design's murky.
• Duplicated Code — the same logic shape appears in more than one hunk or file in the change. → extract the shared shape, call it from both.
• Feature Envy — a method that reaches into another object's data more than its own. → move the method onto the data it envies.
• Data Clumps — the same few fields or params keep travelling together (a type wanting to be born). → bundle them into one type, pass that.
• Primitive Obsession — a primitive or string standing in for a domain concept that deserves its own type. → give the concept its own small type.
• Repeated Switches — the same switch/if-cascade on the same type recurs across the change. → replace with polymorphism, or one map both sites share.
• Shotgun Surgery — one logical change forces scattered edits across many files in the diff. → gather what changes together into one module.
• Divergent Change — one file or module is edited for several unrelated reasons. → split so each module changes for one reason.
• Speculative Generality — abstraction, parameters, or hooks added for needs the spec doesn't have. → delete it; inline back until a real need shows.
• Message Chains — long a.b().c().d() navigation the caller shouldn't depend on. → hide the walk behind one method on the first object.
• Middle Man — a class or function that mostly just delegates onward. → cut it, call the real target direct.
• Refused Bequest — a subclass or implementer that ignores or overrides most of what it inherits. → drop the inheritance, use composition.

When a finding is real enough to report, it must include:

• the exact file and line or hunk where the problem appears,
• the repo rule, spec line, or smell name that justifies the finding,
• a concrete explanation of what breaks, regresses, or becomes ambiguous,
• and, when operating on a GitHub PR, a published PR review comment or inline comment that points the author directly to the error.

If the branch already has unresolved review history, check that history before duplicating an existing concern with new wording.

The goal is not a summary of the PR. The goal is to identify defects in the applied changes and leave a review trail in the PR itself that explains where the error is and why it is wrong.

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 diff command and commit list.
• The list of standards-source files you found in step 3, plus the smell baseline from step 3 pasted in full — the sub-agent has no other access to it.
• The brief: "Report — per file/hunk where relevant — (a) every place the diff violates a documented standard: cite the standard (file + the rule); and (b) any baseline smell you spot: name it and quote the hunk. Distinguish hard violations from judgement calls — documented-standard breaches can be hard, but baseline smells are always judgement calls, and a documented repo standard overrides the baseline. Skip anything tooling enforces. Under 400 words."

Spec sub-agent prompt — include:

• The diff command and commit list.
• The path or fetched contents of the spec.
• The brief: "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 (see Why two axes).

End with a one-line summary: total findings per axis, and the worst issue within each axis (if any). Don't pick a single winner across axes — that's the reranking the separation exists to prevent.

6. Publish the review on the PR

If the target is a GitHub PR, publish the review instead of keeping the findings only in-chat.

• Use the review body to mirror the ## Standards and ## Spec structure.
• Put each finding at the exact file and line where the error occurs, or attach it as an inline comment when that is more precise.
• Explain the failure mode directly: what the code does, why that is wrong, and what the author should inspect or change.
• Keep the review factual and specific. Do not bury the location, and do not leave a finding without a concrete pointer.
• If there are no findings, publish the clean review state clearly so the PR author can see that the branch was inspected against the fixed point.

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.

When reviewing a spec or ADR, keep the spec axis aligned to CONTEXT.md and the repo's ADRs so findings use the project's canonical architecture and domain vocabulary. When the review is attached to a tracker-backed PR, treat the linked issue metadata as part of the review surface: the published review should preserve traceability to the issue labels and milestone, following docs/agents/work-item-format.md for any metadata references you include in the PR review body.

Review quality bar

• Prefer the smallest exact file or hunk that proves the failure.
• If a standards finding is only a smell, say so explicitly.
• If a spec finding is really a missing requirement from the spec source, say that instead of upgrading it into a bug.
• If a PR is already obviously broken by compile or test failure, name the failing command or observable symptom first.