21pounder/terminalagent/code-review

Claude Code and agent skill by 21pounder/terminalagent

Trust tier 2
  • community
LLM review pending
Source check pending

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

Use this skill when user asks to "review code", "check for issues", "analyze code quality", "find bugs", or wants feedback on code implementation.

Install

npx vskill@latest install 21pounder/terminalagent/code-review

SKILL.md

Code Review

Perform thorough code review analyzing quality, potential bugs, security issues, and suggesting improvements.

Parameters

json
{
"type": "object",
"properties": {
"target": {
"type": "string",
"description": "File path, directory, or glob pattern to review"
},
"focus": {
"type": "string",
"enum": ["general", "security", "performance", "maintainability"],
"description": "Primary focus area",
"default": "general"
}
},
"required": ["target"]
}

When to Use

  • User asks to "review" or "check" code
  • User wants to find bugs or issues
  • User asks about code quality
  • User wants security analysis
  • User asks for improvement suggestions

Methodology

Phase 1: Context Gathering
  • Read the target files
  • Understand the codebase structure
  • Identify the programming language and framework
  • Check for related tests and documentation
Phase 2: Analysis
  1. Logic Review: Check for bugs and edge cases
  2. Security Scan: Look for vulnerabilities (injection, auth issues, etc.)
  3. Performance Check: Identify bottlenecks and inefficiencies
  4. Style Review: Check consistency and best practices
Phase 3: Prioritization
  • Categorize issues by severity (Critical, High, Medium, Low)
  • Focus on actionable feedback
  • Provide concrete examples
Phase 4: Output

Provide structured review with:

  • Summary of findings
  • Issues list with severity and line numbers
  • Specific improvement suggestions
  • Code examples where helpful

Guidelines

  • Be constructive, not just critical
  • Provide specific line references
  • Explain WHY something is an issue
  • Suggest concrete fixes, not just problems
  • Acknowledge good patterns when found
  • Consider the project's existing style

Examples

Example 1: File Review

User Input: "Review src/auth.ts for security issues"

Expected Behavior:

  1. Read the file and understand authentication flow
  2. Check for common security issues (SQL injection, XSS, weak crypto)
  3. Verify input validation and sanitization
  4. Check for proper error handling
  5. Provide prioritized list of findings with fixes
Example 2: Directory Review

User Input: "帮我 review 一下 src/utils/ 目录的代码质量"

Expected Behavior:

  1. 列出并读取目录中的所有文件
  2. 分析代码结构、命名、错误处理
  3. 检查是否有重复代码或可抽象的模式
  4. 用中文输出详细的 review 报告
  5. 按严重程度排序问题列表

Security

  • Security scanPassed, 100 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
129
Repository forks
1
7-day trend score
24

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 18 Mar 2026, 7 months ago.

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/21pounder/terminalagent/code-review/badge)](https://verified-skill.com/skills/21pounder/terminalagent/code-review)

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