Skip to content
Back to skills

Code Review

ASecurity

Use on Desktop when reviewing a diff, commit, branch, or local code for correctness, regressions, security, performance, and maintainability.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 13, 2026
ai-agentscode-reviewsecurityperformance

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned October 13, 2026

npx -y skills add z-Zihan/Evir --skill code-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Code Review?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Code Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/z-zihan-code-review/badge)](https://www.skillsdirectory.com/skills/z-zihan-code-review)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: code-review
description: Use on Desktop when reviewing a diff, commit, branch, or local code for correctness, regressions, security, performance, and maintainability.
---

# Code Review

Adapted for Evir from Awesome Copilot `review-and-refactor`. This version is review-only unless
the user separately asks for fixes.

## Review contract

1. Resolve the exact scope: working tree, staged diff, commit range, branch, or named files.
2. Read repository instructions and the surrounding implementation, not only the changed lines.
3. Understand the intended behavior and trace each change through callers, state, persistence,
   errors, permissions, cancellation, concurrency, and user-visible output.
4. Run focused read-only checks when they materially improve confidence. Never mutate the tree
   merely to review it.
5. Report only issues the author can act on and that were introduced or exposed by the scope.

## Finding format

For every finding include severity, a tight file/line location, the triggering condition, the
concrete impact, why current tests do not prevent it, and the smallest credible fix. Prioritize
correctness, data loss, security, broken contracts, and regressions over style preferences.

If no actionable findings remain, say so and list residual verification gaps. Do not equate a
clean diff scan with proof that the feature works in its real runtime.

Files in this skill

  • SKILL.md1.4 KB
  • manifest.json1.2 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.