Diff Analyze
Skill AktivAnalyze git diffs for risk scoring, reviewer recommendations, and change classification
To enhance code review efficiency and quality by providing automated analysis of git diffs, helping developers understand risk and classify changes.
Funktionen
- Git diff analysis
- Risk scoring for changes
- Reviewer recommendations
- Change classification (feature, bugfix, etc.)
- Diff statistics (line counts, complexity)
Anwendungsfälle
- Before submitting a Pull Request to assess risk.
- After making significant code changes to understand impact.
- To identify appropriate reviewers based on code ownership.
- To classify the nature of code changes automatically.
Nicht-Ziele
- Performing code style auto-formatting.
- Directly merging or deploying code.
- Writing or executing tests.
- Analyzing code outside of a git diff context.
Trust
- warning:Issues AttentionWhile the repository has many closed issues, the ratio of open to closed issues in the last 90 days (68 open, 373 closed) suggests a slow response time to new issues.
Installation
Zuerst Marketplace hinzufügen
/plugin marketplace add ruvnet/ruflo/plugin install ruflo-jujutsu@rufloQualitätspunktzahl
Vertrauenssignale
Ähnliche Erweiterungen
Migrate Validate
100Validate pending migrations for foreign key consistency, rollback safety, and best practices
Semgrep Rule Creator
100Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep rules or building custom static analysis detections.
Moyu (摸鱼)
100자동으로 과잉 엔지니어링 패턴을 탐지합니다: (1) 사용자가 명시적으로 요청하지 않은 코드나 파일을 수정하는 경우 (2) 요청되지 않은 새로운 추상화 레이어(클래스, 인터페이스, 팩토리, 래퍼)를 생성하는 경우 (3) 요청되지 않은 주석, 문서, JSDoc, 타입 어노테이션을 추가하는 경우 (4) 요청되지 않은 새로운 종속성을 도입하는 경우 (5) 최소한의 편집 대신 파일 전체를 다시 작성하는 경우 (6) diff 범위가 사용자의 요청을 명백히 초과하는 경우 (7) 사용자가 "너무 많아", "거기는 건드리지 마", "X만 변경해", "간단하게", "그만"과 같은 신호를 보내는 경우 (8) 발생할 수 없는 시나리오에 대한 오류 처리, 유효성 검사, 방어적 코드 추가 (9) 요청되지 않은 테스트, 설정 스캐폴딩, 문서 생성
Karpathy Coder
100Use when writing, reviewing, or committing code to enforce Karpathy's 4 coding principles — surface assumptions before coding, keep it simple, make surgical changes, define verifiable goals. Triggers on "review my diff", "check complexity", "am I overcomplicating this", "karpathy check", "before I commit", or any code quality concern where the LLM might be overcoding.
Claude Handoff
100Führen Sie /handoff aus, um Sitzungsdaten zu erfassen, und schreiben Sie dann einen phasenweisen Implementierungsplan, der darauf verweist. Erstellt Beads für die Nachverfolgung.
Unslop Review
100Schreibt Code-Review-Kommentare so um, dass sie wie von einem menschlichen Teammitglied klingen. Reduziert typische KI-Einleitungen ("Ich habe bemerkt...", "Ich frage mich, ob vielleicht...", "Es könnte sich lohnen, zu überlegen..."). Jeder Kommentar ist direkt: Ort, Problem, konkrete Lösung. Verwenden Sie es, wenn der Benutzer "Review als Mensch umschreiben", "PR-Kommentar de-slopen", "dieses Feedback menschlich klingen lassen", "diesen PR überprüfen", "Code-Review", "/review", "/unslop-review" sagt. Löst automatisch aus, wenn PRs überprüft werden.