agentskills.codes
CO

common-code-review

by li-lanceCodingSource

Conducts high-stakes code reviews with a focus on logic, security, and architectural integrity.

Code ReviewSecurity AuditTesting

Install

mkdir -p .claude/skills/common-code-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15943" && unzip -o skill.zip -d .claude/skills/common-code-review && rm skill.zip

Installs to .claude/skills/common-code-review

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Conduct high-quality, persona-driven code reviews. Use when reviewing PRs, critiquing code quality, or analyzing changes for team feedback. (triggers: review, pr, critique, analyze code)
186 chars✓ has a “when” trigger
Advanced

Key capabilities

  • →Audit code for injection vulnerabilities
  • →Check for design flaws against SOLID principles
  • →Provide actionable code suggestions
  • →Enforce P0 rules from active framework skills
  • →Group feedback by severity: BLOCKER, MAJOR, NIT

How it works

This skill acts as a Principal Engineer, focusing on logic, security, and architecture, and provides constructive feedback based on a mandatory review checklist.

Inputs & outputs

You give it
code to be reviewed
You get back
structured feedback with severity, file, description, why, and fix

When to use common-code-review

  • →Reviewing critical PRs
  • →Auditing code architecture
  • →Identifying security risks

About this skill

Code Review Expert

Priority: P1 (OPERATIONAL)

You are a Principal Engineer. Focus on logic, security, and architecture. Be constructive.

Review Principles

  • Substance > Style: Ignore formatting. Find bugs & design flaws.
  • Questions > Commands: "Does this handle null?" vs "Fix this."
  • Readability: Group by [BLOCKER], [MAJOR], [NIT].
  • Cross-Check: Enforce P0 rules from active framework skills.

Review Checklist (Mandatory)

  • Shields Up: Injection? Auth? Secrets?
  • Performance: Big O? N+1 queries? Memory leaks?
  • Correctness: Requirements met? Edge cases?
  • Clean Code: DRY? SOLID? Intent-revealing names?

See references/checklist.md for detailed inspection points.

Output Format (Strict)

Use the following format for every issue found:

[SEVERITY] [File] Issue Description
Why: Explanation of risk or impact.
Fix: 1-2 line code suggestion or specific action.

Anti-Patterns

  • No Nitpicking: Don't flood with minor style comments.
  • No Vague Demands: "Fix this" -> Explain why and how.
  • No Ghosting: Always review tests and edge cases.

References

When not to use it

  • →When the user wants to focus on formatting or style issues
  • →When the user wants vague demands without explanation
  • →When the user wants to ignore tests and edge cases

Limitations

  • →It ignores formatting issues
  • →It does not provide vague demands
  • →It always reviews tests and edge cases

How it compares

This skill provides structured, persona-driven feedback with specific fixes, unlike a manual review that might lack consistency or actionable suggestions.

Compared to similar skills

common-code-review side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
common-code-review (this skill)04moNo flagsAdvanced
reviewing-code218moNo flagsIntermediate
pr-review62moReviewIntermediate
code-review-checklist31moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

More by li-lance

View all by li-lance →

Android Dependency Injection (Hilt)

li-lance

Standards for Hilt Setup, Scoping, and Modules

00

Android Navigation

li-lance

Standards for Jetpack Navigation Compose (Type-safe)

00

angular-ssr

li-lance

Implement Angular SSR with hydration, TransferState caching, and per-route render modes. Use when configuring Angular Universal SSR, client hydration, static prerendering, or preventing double-fetching. (triggers: **/*.server.ts, server.ts, hydration, transferState, afterNextRender, isPlatformServer

00

php-concurrency

li-lance

Implement concurrency and non-blocking I/O in modern PHP. Use when implementing concurrent requests, async processing, or non-blocking I/O in PHP. (triggers: **/*.php, Fiber, suspend, resume, non-blocking, async)

00

react-performance

li-lance

Optimize React rendering, bundle size, and data fetching performance. Use when optimizing React rendering performance, reducing re-renders, or improving bundle size. (triggers: **/*.tsx, **/*.jsx, waterfall, bundle, lazy, suspense, dynamic)

00

common-workflow-writing

li-lance

Rules for writing concise, token-efficient workflow and skill files. Prevents over-building that requires costly optimization passes. Use when creating or editing workflow files, SKILL.md files, or new skill definitions. (triggers: .agent/workflows/*.md, SKILL.md, create workflow, write workflow, ne

00

You might also like

reviewing-code

CaptainCrouton89

Systematically evaluate code changes for security, correctness, performance, and spec alignment. Use when reviewing PRs, assessing code quality, or verifying implementation against requirements.

21105

pr-review

pytorch

Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".

638

code-review-checklist

vudovn

Code review guidelines covering code quality, security, and best practices.

330

fix-review

sickn33

Verify fix commits address audit findings without new bugs

326

django-verification

affaan-m

Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

521

agent-reviewer

ruvnet

Agent skill for reviewer - invoke with $agent-reviewer

320

Search skills

Search the agent skills registry