# sanyuan0704/sanyuan-skills

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

Repository: https://github.com/sanyuan0704/sanyuan-skills
Canonical: https://ross.abutalabs.com/products/sanyuan-skills
Language: Python
License: MIT
License Family: permissive
Last push: 2026-05-11T07:21:45+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 81, release rhythm 35, longevity 15
- inputs: {"age_days": 210, "days_push": 114, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3881, forks 340 (observed 2026-08-28T04:08:28.120614+00:00)

## What it is
A collection of production-grade agent skills for Claude Code and other AI agent terminals, installable via npx. It includes a code review expert, an AI tutor, skill quality auditing and authoring meta-skills, a wiki compiler, and a reading coach.

## Use cases
- review my git changes for security and performance issues
- get a senior-engineer style code review of SOLID and error handling
- set up an AI tutor for mastery learning on a topic
- audit the quality of an existing agent skill
- create a new high-quality agent skill
- compile my notes into a structured wiki knowledge base
- run a guided reading session with spaced repetition

## When to choose
- you use Claude Code or a compatible agent terminal and want ready-made expert skills
- you want consistent, structured code reviews on your git changes
- you author agent skills and want quality auditing and authoring guidance

## When to avoid
- you need a standalone code review tool that runs in CI without an AI agent
- you don't use any AI agent terminal or LLM-based workflow
- you need deterministic, non-LLM static analysis

## Facets
- artifact type: plugin
- maturity: active
- function: code-review, agent-framework, prompt-engineering, developer-tools
- domain: developer-tools, education
- platform: cli, cross-platform
- tags: claude-code, agent-skills, ai-tutoring, skill-authoring, knowledge-base, automation, nodejs

## Member repositories
- sanyuan0704/sanyuan-skills (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:28.120614+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:25:43.131227+00:00, confidence not recorded.
  - readme: https://github.com/sanyuan0704/sanyuan-skills (fetched 2026-08-28T04:08:28.120614+00:00, sha e2edc1b4c7f4)
- Data as of 2026-08-30T08:39:29.467469+00:00.