code-review skill
✓ VerifiedPerforms parallel code reviews focusing on coding standards and specification compliance using sub-agents.
- GitHub stars
- 5
- Files
- 1
- Last commit
- Oct 29, 2026
- License
- MIT
- Allowed tools
- —
What does the code-review skill do?
code-review performs parallel code reviews focusing on coding standards and specification compliance using sub-agents.
Summary generated from the skill's SKILL.md.
About the code-review skill
Reviewing pull requests or work-in-progress branches by comparing them against a specific commit, tag, or merge-base is what this skill enables. It uses parallel sub-agents to perform a two-axis evaluation, ensuring that coding style and functional requirements are judged independently. This separation prevents one type of feedback from masking the other, providing a clear view of whether code follows project conventions or fails to meet the intended design.
An agent should load this skill when a developer needs to validate a diff. The process begins by pinning a fixed point using git commands like git diff and git log to establish a baseline. The skill then identifies standards from repository files like CONTRIBUTING.md and searches for specifications in commit messages, provided paths, or documentation folders. It applies a baseline of Fowler code smells, such as Feature Envy or Primitive Obsession, while allowing documented repository standards to take precedence. The final output aggregates findings into distinct sections for Standards and Spec, concluding with a summary of the most significant issues found in each category.
What an agent can do with it
- 1Validate PR complianceCheck if a new branch follows the existing repository coding standards and implements the assigned ticket correctly.
- 2Detect architectural code smellsIdentify issues like Shotgun Surgery or Data Clumps within a code change using a predefined heuristic baseline.
- 3Identify scope creepDetermine if a developer has added functionality that was not requested in the original specification.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the code-review skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the code-review skill in Plugin
/plugin marketplace add KunanonJ/superstacks /plugin install superstacks@superstacks
Install the code-review skill in Claude Code
~/.claude/skills/code-review/SKILL.md
$ npx degit KunanonJ/superstacks/plugins/superstacks/skills/code-review ~/.claude/skills/code-reviewInstall the code-review skill in Claude Code (project)
.claude/skills/code-review/SKILL.md
$ npx degit KunanonJ/superstacks/plugins/superstacks/skills/code-review .claude/skills/code-reviewInstall the code-review skill in Codex
~/.agents/skills/code-review/SKILL.md
$ npx degit KunanonJ/superstacks/plugins/superstacks/skills/code-review ~/.agents/skills/code-reviewInstall the code-review skill in Gemini CLI
~/.gemini/skills/code-review/SKILL.md
$ npx degit KunanonJ/superstacks/plugins/superstacks/skills/code-review ~/.gemini/skills/code-reviewInstall the code-review skill in Claude.ai
npx degit KunanonJ/superstacks/plugins/superstacks/skills/code-review code-review && zip -r code-review.zip code-review # claude.ai → Customize → Skills → + → Create skill → Upload a skill → code-review.zip
Automated checks
Ran Nov 16, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachablekunanonj/superstacks/plugins/superstacks/skills/code-review is public and reachablegithub.com/kunanonj/superstacks/tree/HEAD/plugins/superstack ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-10-29github.com/kunanonj/superstacks/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/kunanonj/superstacks/blob/HEAD/plugins/superstack ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/kunanonj/superstacks/blob/HEAD/plugins/superstack ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 91 linesgithub.com/kunanonj/superstacks/blob/HEAD/plugins/superstack ↗Pass
SKILL.md
View on GitHubTwo-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 / spec?
Both axes run as parallel sub-agents so they don't pollute each other's context, then this skill aggregates their findings.
Read ticket identifiers from the workflow-profile skill and safety-overrides. Do not close, fix, or resolve tracker items; cite them as Refs #N.
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,Refs #45, GitLab!67, etc.). Fetch titles only when the user already has tracker access; never write to the tracker. TreatCloses/Fixes/Resolvesin history as citations, not as a license to close anything. - A path the user passed as an argument.
- A spec file under
docs/,specs/, or.scratch/matching the branch name or feature. - 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. 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.
4. Spawn both sub-agents in parallel
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 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 should 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, 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.
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.
Files in this skill
1code-review skill questions
How do I install the code-review skill in Claude Code?
Run npx degit KunanonJ/superstacks/plugins/superstacks/skills/code-review ~/.claude/skills/code-review. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the code-review skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
How does the tool handle coding standards?
It checks code against documented repository standards and a baseline of Fowler code smells, where documented standards take precedence.
What happens if no specification is provided for the review?
The tool will ask the user for the spec location; if none exists, the Spec sub-agent skips the process and reports that no spec is available.
Can the tool automatically close or fix issues in a tracker?
No, the tool is restricted to citing tracker items and is not permitted to close, fix, or resolve them.
Why are the reviews split into two separate axes?
Separating Standards and Spec reviews prevents one axis from masking the other, such as code that follows standards but implements the wrong logic.