rrr Skill
description: "GLM-5 코드 리뷰 (유료). /rr의 상위 버전 — GLM-5 744B 모델로 더 깊은 리뷰. /rrr 또는 'GLM-5 리뷰' 요청 시 사용."
Want an agent-native computer in the browser? Try HappyCapy.
Cloud sandbox for AI agents · No setup · Run autonomous workflows from your browser
Affiliate link — we may earn a commission at no extra cost to you.
Why use this skill
rrr is most useful when you want an agent workflow that is more structured than an ad-hoc prompt. Instead of restating the same expectations every time, a dedicated SKILL.md file gives the assistant a repeatable brief. In this case, the core value is clarity: the repo already frames the workflow around productivity skills tasks, and the skill source gives you a portable starting point you can evaluate, adapt, and reuse. The inferred platform for this skill is Claude Code Skills, which helps you judge whether it is likely to feel native in your current agent ecosystem or whether it is better treated as a general reference.
That matters because AI assistants are better when the operating context is explicit. A good skill turns hidden team expectations into visible instructions. It can name preferred tools, describe failure modes, define what “done” looks like, and reduce the amount of corrective prompting you need after the first draft. For developers exploring the wider SKILL.md ecosystem, this page helps answer the practical question: is this skill specific and maintained enough to be worth trying?
How to evaluate and use it
Start with the source repo and the preview below. The preview tells you whether the instructions are actionable or just aspirational. Strong skills usually describe triggers, recommended tools, steps, and known pitfalls. Weak skills tend to stay generic. This one lives in dgk-dev/dgk-claude, which gives you a concrete repo context, update history, and direct ownership trail.
Once you confirm the scope looks right, test it on a small task before making it part of a larger workflow. If it improves consistency, keep it. If it is too broad, outdated, or conflicts with your own process, treat it as a reference rather than a drop-in rule. That is the healthiest way to use directory-discovered skills: not as magic plugins, but as reusable operational knowledge that still deserves judgment.
SKILL.md preview
Previewing the source is one of the fastest ways to judge whether a skill is truly useful. This snippet comes from the public file in the linked repository.
--- name: rrr description: "GLM-5 코드 리뷰 (유료). /rr의 상위 버전 — GLM-5 744B 모델로 더 깊은 리뷰. /rrr 또는 'GLM-5 리뷰' 요청 시 사용." allowed-tools: [Bash, Read, Edit, Glob, Grep] argument-hint: "review mode or custom instructions (예: 'pr', 'staged', '보안 집중')" --- # /rrr - GLM-5 Code Review GLM-5 (744B) 모델로 현재 변경사항을 깊이 있게 코드 리뷰한다. `/rr` (glm-4.7-flash, 무료)의 상위 버전. ## 사용법 ``` /rrr # GLM-5 리뷰 (staged + unstaged 변경사항) /rrr staged # staged 변경사항만 /rrr pr # PR diff 리뷰 /rrr 보안 집중 # 커스텀 인스트럭션 추가 ``` --- ## 실행 방법 `glm-review --model glm-5` CLI를 **반드시 `run_in_background=true` + `dangerouslyDisableSandbox=true`** 로 실행한다. ### 1. 세션 컨텍스트 감지 + diff 생성 (리뷰 실행 전 필수) 멀티 세션 환경(동시 5-10개 Claude Code가 main에서 커밋/푸시)에서 안정적으로 동작하는 `--diff-file` 방식을 사용한다. 1. 이번 세션에서 수정/생성한 파일 목록을 정리 2. git 루트 디렉토리를 확인: `git rev-parse --show-toplevel` 3. 상태에 따라 diff 생성: **케이스 A: 이미 커밋됨** (가장 흔함) ```bash GIT_ROOT=$(git rev-parse --show-toplevel) COMMIT_HASH=<이 세션의 커밋 해시> cd "$GIT_ROOT" && git show "$COMMIT_HASH" -- <file1> <file2> ... > /tmp/glm-review-diff.patch ``` **케이스 B: 미커밋 (uncommitted 상태)** ```bash GIT_ROOT=$(git rev-parse --show-toplevel) cd "$GIT_ROOT" && git diff HEAD -- <file1> <file2> ... > /tmp/glm-review-diff.patch # 신규 파일은 git add -N 후 diff에 포함 ``` **케이스 C: 단독 세션 (다른 변경 없음)** ```bash # --diff-file 없이 기본 모드 사용 가능 glm-review --model glm-5 ``` 4. diff 파일이 비어있으면 → "리뷰할 변경사항 없음" 안내 후 종료 ### 2. 사전 확인 (선택) 헬스 체크로 API 연결 확인: ```bash glm-review --model glm-5 --health ``` ### 3. 리뷰 실행 ```bash # ★ 권장: diff 파일로 리뷰 (멀티 세션 환경에서 가장 안정적) glm-review --model glm-5 --dif ...