qiao-920/claude-desktop-cn/code-review

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Thorough code review covering bugs, security, performance, and maintainability. Use when reviewing code, checking for bugs, auditing quality, or getting feedback on implementations.

Install

npx vskill@latest install qiao-920/claude-desktop-cn/code-review

SKILL.md

Code Review: Thorough Analysis of Code

Review the provided code or recent changes with a focus on correctness, maintainability, and best practices.

Review Process

Step 1: Identify What to Review
  • If the user provided a file path or pasted code, review that
  • If no specific target, run git diff to find recent changes
  • If no git changes, ask the user what to review
Step 2: Read the Code

Use the Read tool to examine the full file(s). Understand the context — what does this code do? What's its role in the project?

Step 3: Analyze

Check for these categories of issues:

Bugs & Correctness

  • Logic errors, off-by-one errors, null/undefined handling
  • Missing edge cases, race conditions
  • Incorrect API usage or wrong assumptions
  • Type mismatches or unsafe casts

Security

  • SQL injection, XSS, command injection risks
  • Hardcoded secrets or credentials
  • Unsafe deserialization, path traversal
  • Missing input validation at system boundaries

Performance

  • Unnecessary loops or redundant computation
  • N+1 query patterns, missing pagination
  • Memory leaks (unclosed resources, growing collections)
  • Blocking operations in async contexts

Maintainability

  • Unclear naming, overly complex logic
  • Missing error handling for external calls
  • God functions/classes that do too many things
  • Dead code or unreachable branches
Step 4: Report

Present findings organized by severity:

  1. Critical — Bugs or security issues that must be fixed
  2. Important — Significant improvements for correctness or maintainability
  3. Suggestions — Nice-to-have improvements

For each finding: state the issue, explain WHY it's a problem, and show the fix. Skip categories with no findings.

If the code is clean, say so — don't invent issues.

Security

  • Security scanPassed, 93 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
202
Repository forks
28
7-day trend score
27

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/qiao-920/claude-desktop-cn/code-review/badge)](https://verified-skill.com/skills/qiao-920/claude-desktop-cn/code-review)

Something wrong with this skill or its page? Tell us.