Expert code review skill: SOLID, security, performance, error handling, boundary conditions

This project offers a suite of specialized agent skills designed for AI terminals, enhancing code quality and learning. It provides a "Code Review Expert" for deep code analysis, "Sigma" for personalized AI tutoring, and "Skill Forge" to facilitate the creation of new agent skills, aiming to boost developer efficiency and knowledge acquisition.

How It Works

The skills are distributed as a collection installable via npx. The "Code Review Expert" skill leverages senior engineering practices to scrutinize code for adherence to SOLID principles, security vulnerabilities, performance issues, robust error handling, and edge cases. "Sigma" employs Bloom's 2-Sigma mastery learning methodology combined with Socratic questioning to deliver tailored AI-driven tutoring. "Skill Forge" functions as a meta-skill, guiding users through 12 established techniques for developing high-quality agent skills.

Quick Start & Requirements

• Primary install / run command: Install any skill using npx skills add sanyuan0704/sanyuan-skills --path skills/<skill-name>.
• Non-default prerequisites and dependencies: Requires an AI agent terminal environment compatible with npx skill installations (e.g., Claude Code). No specific hardware, OS, or software dependencies beyond the agent terminal are detailed.
• Usage: Skills are invoked via commands such as /code-review-expert, /sigma <topic>, or /skill-forge.
• Links: The README does not provide direct URLs for official quick-start guides, demos, or further documentation.

Highlighted Details

• The "Code Review Expert" skill provides comprehensive analysis covering SOLID principles, security, performance, error handling, and boundary conditions.
• "Sigma" skill implements Bloom's 2-Sigma mastery learning and Socratic questioning for targeted AI tutoring.
• "Skill Forge" offers a framework and techniques for AI agents to generate new, high-quality skills.

Maintenance & Community

The provided README does not contain information regarding notable contributors, sponsorships, community channels (like Discord/Slack), or a roadmap.

Licensing & Compatibility

• License type: MIT License.
• Compatibility notes: The MIT license is permissive and generally suitable for commercial use and integration into closed-source projects.

Limitations & Caveats

The README lacks specific performance benchmarks, details on potential limitations of the underlying AI models, or a clear enumeration of the "12 battle-tested techniques" within Skill Forge. The efficacy of these skills is contingent upon the capabilities of the host AI agent terminal.