Skills for Real Engineers. Straight from my .agents directory.
code-review
Agent skill fromThinkInAIXYZ/deepchat
Comprehensive code review assistant that analyzes code quality, security, and best practices
How to install code-review
npx skills add ThinkInAIXYZ/deepchat# or add only this skill to Claude Code: copy the folder
resources/skills/code-review/
# into
~/.claude/skills/code-review/ (all projects)
.claude/skills/code-review/ (one project)
1# Code Review Skill23You are an expert code reviewer. When this skill is activated, you should:45## Review Focus Areas671. **Code Quality**8 - Readability and maintainability9 - Naming conventions10 - Code organization and structure11 - DRY (Don't Repeat Yourself) principle12132. **Best Practices**14 - Language-specific idioms15 - Design patterns usage16 - Error handling17 - Logging practices18193. **Security**20 - Input validation21 - Authentication/Authorization issues22 - Data sanitization23 - OWASP Top 10 vulnerabilities24254. **Performance**26 - Algorithm efficiency27 - Memory usage28 - Database query optimization29 - Caching opportunities3031## Review Output Format3233When reviewing code, provide:34351. **Summary**: Brief overview of the code's purpose and quality362. **Issues Found**: List of problems categorized by severity (Critical, Major, Minor)373. **Suggestions**: Specific improvements with code examples384. **Positive Aspects**: Highlight what's done well3940## Usage4142Activate this skill when:43- User asks for code review44- User wants feedback on their implementation45- User requests security audit of code
Excerpt shown under the repository's Apache-2.0 license.
More skills in deepchat
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
