Skill v1.0.1
currentAutomated scan100/100+4 new
name: code-review description: Review the changes since a fixed point (commit, branch, tag, or merge-base) along two 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?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X". metadata: version: "1.0.1"
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? If the spec contains Gherkin scenarios (from
/mattpocock:bdd), those are the authoritative acceptance criteria.
Both axes run as parallel sub-agents so they don't pollute each other's context, then this skill aggregates their findings. Start every sub-agent with a fresh context window.
The issue tracker should have been provided to you. If not, tell the user to run /mattpocock:setup-matt-pocock-skills.
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.
2. Identify the spec source
Look for the originating spec, in this order:
- Issue references in the commit messages (
#123,Closes #45, GitLab!67, etc.), fetched via the workflow in the tracker doc. - A path the user passed as an argument.
- A PRD/spec file under
docs/,specs/, or.scratch/matching the branch name or feature. - If nothing is found, use the AskUserQuestion tool to ask where the spec is (options: in the repo / linked from the issue or PR / external document / no spec exists). If there isn't one, the Spec sub-agent will skip and report "no spec available".
3. Identify the standards sources
Search the repo for every file that documents how code should be written. When CODING_STANDARDS.md or CONTRIBUTING.md exists, it must be on the list.
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. 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.
AI slop baseline
Language-model-generated code tends to emit low-evidence, low-signal patterns regardless of language. The smell baseline's two binding rules apply unchanged: the repo overrides, and skip any pattern that tooling already enforces (for example, a repository running dedicated anti-slop lint rules). Each pattern reads what it is → how to fix it:
- Fabricated evidence: casts or suppressions that assert a type or invariant the code never established: chained
as/as unknown as,cast(Any, x),# type: ignore, unjustified@ts-ignore,unsafeblocks or.unwrap()standing in for real handling. → parse at the boundary or guard the type; require a written invariant justification for any suppression. - Evidence widening: known precise values funneled into
unknown/any/object/interface{}/open dictionaries, or finite records degraded to open maps. → preserve the precise type end to end; widen only at an unparsed boundary. - Defensive clutter:
try/except: pass, redundant null checks in trusted codepaths, conditional empty-spread omission tricks, silent fallbacks. → delete the check; validate at the boundary once. - Mock patching: tests that mock or monkey-patch the module's own internals instead of exercising real seams. → test through an injected adapter or the public interface.
- Vacuous names: symbols named after their type or shape (
data,info,obj,helper,manager,*Shape) instead of their domain meaning. → rename to the domain concept; no honest name means the design is murky.
Match each pattern against the diff the same way as the smell baseline: labelled judgement calls, hard only when a documented standard forbids them, and skipped when repository tooling enforces the pattern.
4. Spawn both sub-agents in parallel
Send a single message with two Agent tool calls, in the foreground, and aggregate the reports they return.
Standards sub-agent prompt should include:
- The full diff command and commit list.
- The list of standards-source files you found in step 3, plus the smell and AI slop baselines from step 3 pasted in full (the sub-agent has no other access to them).
- 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 or AI slop pattern you spot: name it and quote the hunk. Distinguish hard violations from judgement calls: documented-standard breaches can be hard, but baseline smells and AI slop patterns are always judgement calls, and a documented repo standard overrides the baseline. Skip anything tooling enforces. Under 400 words."
Spec sub-agent prompt should include:
- The diff command and commit list.
- The path or fetched contents of the spec.
- The brief: "Report: (a) Gherkin scenarios (Given/When/Then) in the spec 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. If the spec contains Gherkin scenarios, those are the authoritative acceptance criteria. 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, because 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.
Evidence for causal claims
Before calling a concurrency guard load-bearing, show a reachable interleaving using the actual public API: which operation replaces or deletes the entry, when each callback runs, and how the guard changes the observable result. A hypothetical future invalidation or replacement operation is not evidence about this candidate. If no such operation exists, describe the guard as redundant or a deliberate readability preference, not as a verified race fix. Apply the same standard to other causal claims: distinguish an observed failure, a source-supported possibility, and an untested hypothesis. Green tests alone do not prove the explanation.
A judgement call changes confidence, not the verdict: once the report identifies an unresolved smell, Standards is REWORK even if no lint rule prohibits it. If current evidence shows the candidate is not a smell, explain that refutation and remove it from the findings; naming it a deliberate preference or a safeguard for a hypothetical future API does not resolve it. Do not let a necessary rejection handler justify a separate redundant identity guard by association.
5.4 Memory read-before (Standards axis)
Before scoring, load the project's known traps: Glob docs/memory/*.md, then read every file whose frontmatter category is pitfall or convention and whose summary is topically related to this review (the diff's files, patterns, or stack). These are evaluator-verified failure modes this repo already paid for.
In step 5.5's Standards scoring, treat a read memory file as a red flag: if the diff exhibits a known pitfall, record it as a FAIL in the Standards report with evidence citing the memory file (docs/memory/pitfall_<slug>.md). If docs/memory/ does not exist, skip this step.
5.5 Binary verdict + refute-before-PASS
After presenting the two reports, emit a binary verdict per axis:
- Standards axis: binary PASS (no unresolved standard violations or smells in the Standards report) / REWORK (any standard violation or listed smell).
- Spec axis: binary PASS (all Gherkin scenarios in the spec demonstrably implemented) / REWORK (any scenario missing/partial/wrong).
Refute-before-PASS (red-team protocol): Before assigning PASS to either axis, attempt to refute your own PASS:
- State the strongest reason the work might FAIL this axis despite looking green.
- Cite the specific evidence (diff hunk or missing scenario) that would confirm that failure.
- Only if that failure case is itself refuted by concrete contrary evidence does PASS hold.
A PASS without an attempted refutation is invalid — downgrade to REWORK and list the un-refuted risk.
Final verdict: REWORK if either axis is REWORK; PASS only if both axes PASS (post-refutation).
CRITICAL: Refute-before-PASS
A PASS without an attempted refutation is invalid. Before assigning PASS to either axis, state the strongest reason the work might still fail, cite the evidence (diff hunk or missing scenario) that would confirm it, and hold PASS only when concrete contrary evidence refutes it. Never merge or rerank the two axes — the separation exists to stop one axis masking the other.
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.