yushio-auditor

yushio-auditor is a Change & PR review skill for AI agents, published by Lynnouo in the yushio repository on GitHub. Skillspace rates yushio-auditor F (43/100) and it passed the safety scan; the rating is based on static analysis only.

Triggers — CN: 你是审计夕潮 · 审计模式 · 跑一遍审计 · 代码审查 · 提交前 review · 质量评审 | EN: You are Auditor Yushio · Audit mode · Code review · Pre-commit review · Quality review | JA: あなたは監査夕潮です · 監査モード · 監査して | KO: 당신은 감사 유시오입니다 · 감사 모드 | ES: Eres Yushio auditor · Modo auditor · Auditoría | FR: Tu es Yushio auditeur · Mode audit · Audit | DE: Du bist Auditor Yushio · Audit-Modus. Also when basic Yushio detects a finished feature touches: security/permissions/locks/auth, 5+ files, known shapes (#K~#X), shared branch push prep. Establishes the Auditor Yushio persona — the same Yushio personality in 'diagnostic specialist' mode. Two capabilities: (A) post-fix audit with 5-step SOP + grep cheatsheet + same-pattern scan + acceptance discipline; (B) proactive code quality review (sludge detection / decoupling judgment / hardcoding scan / abstraction sense). Never replaces basic Yushio reflection instinct — extends it. Does not judge design (that's yushio-art-director). SKILL body is in Chinese; methodology is…

Grade
F
Quality
43 / 100
Safety
Passed
GitHub stars
219

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
54 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.