sanyuan0704/sanyuan-skills

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

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 24 minutes ago
Added to GitGenius on September 17th, 2026
Created on February 4th, 2026
Open Issues & Pull Requests: 8 (+0)
GitHub issues: Enabled
Number of forks: 343
Total Stargazers: 3,923 (+0)
Total Subscribers: 18 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 3.9 days
Mean response time: 3.7 days
90th percentile: 7.1 days
Tracked items: 6

Most active contributors

Sign in to see contributor activity.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 5
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 170 days
Stale 30+ days: 5
Stale 90+ days: 5

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

Sanyuan-skills is a collection of production-grade agent skills for Claude Code and other AI agent terminals.

The collection addresses the need for specialized capabilities in AI-assisted workflows by packaging reusable skills that extend agent functionality. Each skill encapsulates a specific domain of expertise—from code review and tutoring to knowledge management—designed to be installed and invoked within agent terminals. The skills are built to handle complex tasks that require structured reasoning and domain knowledge, such as evaluating code against SOLID principles and security standards, or guiding learners through mastery-based instruction.

Developers should adopt these skills if they work with Claude Code or compatible AI agent terminals and need to augment their agents with specialized capabilities. The collection suits teams that want to standardize code review practices, implement structured learning approaches, or build knowledge bases from unstructured content. Individual skills can be installed independently, allowing teams to adopt only what they need. The Code Review Expert skill targets senior-level review criteria including SOLID principles, security, performance, and error handling. The Sigma skill provides one-on-one tutoring based on Bloom's 2-Sigma mastery learning framework with Socratic questioning. The Skill Forge skill itself is a meta-skill for creating high-quality skills using battle-tested techniques. Wiki Ingest compiles articles and documents into structured, cross-referenced knowledge bases. Book Study functions as a reading coach with knowledge compilation, mastery testing through Socratic questioning, spaced repetition, and cross-book querying capabilities.

The project shows active development with a focused skill set of six distinct capabilities. The codebase is organized with each skill in its own directory, suggesting a modular architecture that supports independent maintenance and iteration. The inclusion of meta-skills like Skill Review and Skill Forge indicates the maintainers are building tooling to improve the quality and consistency of skills themselves. Installation is straightforward through a standard command-line interface, and the project is licensed under MIT terms.