> rrr
GLM-5 코드 리뷰. /rr의 상위 버전으로 더 강한 모델로 변경사항을 검토하고, Codex가 결과를 다시 검증해 유효한 이슈만 정리한다.
curl "https://skillshub.wtf/dgk-dev/dgk-gpt/rrr?format=md"/rrr
Use glm-review --model glm-5 as the deeper paid review pass, then validate the results against the code before you trust them.
Default Flow
- Determine the exact review scope first.
- commit hash known -> commit mode
staged-> staged modepr-> PR mode- mixed unrelated local changes -> focused diff file
- Run a health check only when auth or connectivity looks questionable:
glm-review --model glm-5 --health
- Run the review with the smallest correct input:
glm-review --model glm-5
glm-review --model glm-5 --mode staged
glm-review --model glm-5 --mode pr
glm-review --model glm-5 --mode commit --ref <COMMIT_HASH>
glm-review --model glm-5 --diff-file /tmp/glm-review-diff.patch
- Verify every reported issue in the actual code and diff.
- Keep only confirmed issues.
- If fixes are requested or clearly in scope, apply them and rerun the closest verification.
Choosing Review Input
- committed single change:
glm-review --model glm-5 --mode commit --ref <COMMIT_HASH>
- committed subset of files:
glm-review --model glm-5 --mode commit --ref <COMMIT_HASH> --files src/a.ts src/b.ts
- custom focused diff:
GIT_ROOT=$(git rev-parse --show-toplevel)
cd "$GIT_ROOT" && git diff HEAD -- <file1> <file2> ... > /tmp/glm-review-diff.patch
glm-review --model glm-5 --diff-file /tmp/glm-review-diff.patch
If the diff is empty, stop and say there is nothing to review.
Validation Rules
glm-reviewis a reviewer, not an oracle.- Re-check referenced code paths before reporting a bug.
- Separate confirmed defects from debatable style feedback.
- If a finding depends on broader context, inspect the relevant surrounding code before accepting it.
Error Handling
command not found: glm-reviewInstall it withnpm install -g glm-reviewZAI_API_KEY not setExportZAI_API_KEYin the shell or your normal secret-loading path- auth or API failure
Re-run
glm-review --model glm-5 --healthafter refreshing credentials
Finish
Return:
- review scope used
- confirmed findings only
- notable false positives filtered out
- what verification ran after fixes, if any
> related_skills --same-repo
> test
Persistent verification mode. Use when the user explicitly says `/test` or clearly wants exhaustive test, QA, and fix loops before signoff, especially when they want you to keep grinding while they are away. Bias Codex toward running the relevant existing test stack, browser or desktop verification, and diagnosis repeatedly until the requested surface is verified or a real blocker remains.
> rr
코드 리뷰. 작업 후 변경사항을 Z.AI 모델로 검토하고, Codex가 결과를 다시 검증해 유효한 이슈만 정리한다. /rr 또는 'GLM 리뷰' 요청 시 사용.
> re
Explicit extra-research mode. Use only when the user says `/re` or clearly asks for a research-heavy pass before coding. This skill should bias Codex toward more source-checking and justification without replacing its normal orchestration.
> ralph
Persistent completion mode. Use when the user explicitly says `/ralph` or clearly wants you to keep iterating until the task is actually finished, repeating implement-verify-fix loops instead of stopping at partial progress.