Skills code-reviewer
📦

code-reviewer

Content revision r1 Safe ⚙️ External commands

Review Code Changes with Structured Feedback

Code reviews can miss important defects when the process is unclear. This skill guides Claude, Codex, and Claude Code through consistent reviews for local changes and pull requests.

Supports: Claude Codex Code(CC)
🥉 78 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "code-reviewer" from https://skillstore.io/skills/google-gemini-code-reviewer.md and its manifest at https://skillstore.io/api/skills/google-gemini-code-reviewer/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Test it

Using "code-reviewer". Review my local changes before I open a PR.

Expected outcome:

  • Summary: The change is small and mostly safe, but one edge case needs attention.
  • Findings: A new null path can skip validation when the input list is empty.
  • Conclusion: Request changes until the edge case is covered by code and tests.

Using "code-reviewer". Review PR #42 for maintainability and tests.

Expected outcome:

  • Summary: The implementation is readable and follows existing structure.
  • Improvements: Add a regression test for the error branch and simplify one duplicated condition.
  • Conclusion: Approve after the missing test is added.

Using "code-reviewer". Check whether this security-sensitive change is ready.

Expected outcome:

  • Summary: The change needs more validation before merge.
  • Critical: User-controlled input reaches a database query without a clear allowlist.
  • Conclusion: Request changes and add tests for malicious input cases.

Security Audit

Safe
v6 • 7/9/2026 Open versioned report

The static findings point to markdown code fences and inline command examples in SKILL.md, not executable backtick or Ruby code. The skill does recommend standard git, GitHub CLI, and npm review commands, but they are presented as normal review workflow steps with user-facing context and no malicious intent found.

1
Files scanned
66
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: claude View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/google-gemini-code-reviewer/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/google-gemini-code-reviewer/security.svg)](https://skillstore.io/skills/google-gemini-code-reviewer?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/google-gemini-code-reviewer?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/google-gemini-code-reviewer/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/google-gemini-code-reviewer.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

google-gemini. (2026). code-reviewer security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/google-gemini-code-reviewer/audits/6

BibTeX citation

@techreport{google-gemini-google-gemini-code-reviewer-2026, author = {google-gemini}, title = {code-reviewer security audit report (audit version 6)}, institution = {Skillstore}, year = {2026}, number = {6}, url = {https://skillstore.io/skills/google-gemini-code-reviewer/audits/6}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "code-reviewer security audit report (audit version 6)" version: "unspecified" type: report authors: - name: "google-gemini" date-released: "2026-07-09" url: "https://skillstore.io/skills/google-gemini-code-reviewer/audits/6" identifiers: - type: other value: "skillstore:google-gemini-code-reviewer:audit:6" description: "Skillstore immutable audit report identifier"

Compare variants

9 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Higher Skillstore usage
alirezarezvani Recommended

alirezarezvani-code-reviewer

Skillstore Score 83
Evidence Confidence High
Skillstore usage 368
Updated

2026-08-21

autumnsgrove-code-reviewer

Skillstore Score 83
Evidence Confidence High
Skillstore usage 77
Updated

2026-08-21

davila7-code-reviewer

Skillstore Score 81
Evidence Confidence High
Skillstore usage 13
Updated

2026-08-21

curiouslearner-code-reviewer

Skillstore Score 78
Evidence Confidence High
Skillstore usage 47
Updated

2026-08-21

sickn33-code-reviewer

Skillstore Score 78
Evidence Confidence High
Skillstore usage 18
Updated

2026-08-21

9tykeshav-code-reviewer

Skillstore Score 78
Evidence Confidence High
Skillstore usage 15
Updated

2026-08-21

dennisliuck-code-reviewer

Skillstore Score 78
Evidence Confidence High
Skillstore usage 14
Updated

2026-08-21

google-gemini-code-reviewer

Skillstore Score 78
Evidence Confidence High
Skillstore usage 11
Updated

2026-08-21

shubhamsaboo-code-reviewer

Skillstore Score 77
Evidence Confidence Medium
Skillstore usage 6
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
68
Community
83
Spec Compliance

What You Can Build

Review a teammate pull request

Check a remote PR for correctness, tests, maintainability, and security before approving it.

Check local work before opening a PR

Review staged and unstaged changes to catch problems before sharing them with the team.

Standardize review feedback

Use a consistent review structure for findings, improvements, nitpicks, and final recommendations.

Try These Prompts

Review my current changes
Review my local changes and tell me if they are ready for a pull request.
Review a pull request
Review PR #123 for correctness, maintainability, security, and missing tests.
Focus on risky changes
Review my staged changes and focus on correctness bugs, security issues, edge cases, and test gaps.
Run a release-grade review
Review this PR as a release blocker review. Include critical findings, improvement suggestions, and an approve or request changes conclusion.

Best Practices

  • Run or request the project verification suite when the change is substantial.
  • Provide review comments with clear reasons and concrete next steps.
  • Separate critical defects from improvement suggestions and optional nitpicks.

Avoid

  • Do not approve changes only because automated checks pass.
  • Do not leave vague feedback without explaining the risk or expected fix.
  • Do not switch branches or run optional commands without confirming user intent when needed.

Frequently Asked Questions

Can this skill review both local changes and pull requests?
Yes. It supports local staged or unstaged changes and remote pull requests by number or URL.
Does it run tests automatically?
It recommends preflight checks and asks when optional project commands should be run.
What does the review focus on?
It focuses on correctness, maintainability, readability, efficiency, security, edge cases, error handling, and testability.
Can it approve a pull request?
It can provide an approve or request changes recommendation based on the review findings.
Does it replace human code review?
No. It helps structure and improve review coverage, but human judgment remains important.
Which tools can use this skill?
The report lists support for Claude, Codex, and Claude Code.

Developer Details

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Ref

1ffa7643651792ccb4bd3b15d924d2c97edff755

Maintenance freshness

7/18/2026

Usage

8 downloads · 69 views

File structure

📄 SKILL.md