moveju112
UserClaude Code skill that builds a project's AI rule set — slim CLAUDE.md index + AGENTS.md pointer + on-demand docs/*.md rules, with link/budget verification and a quiz test
Categories
Indexed Skills (4)
rule-architect
Use when a project needs AI agent rules built or upgraded — no AI_RULES.md exists, an existing rule index has grown into one bloated file, or the user asks for a project rule set. Triggers on "make rules for this project", "generate AI rules", "set up project rules", "upgrade the project rules", "rule-architect", "/rule-architect", and the Korean equivalents "룰 만들어줘", "룰 생성", "AI 룰 만들어", "프로젝트 룰 고도화", or refreshing rules after a major refactor ("--update"). English and Korean triggers are equivalent.
unit-test
Use when the user directly requests efficiency-aware multi-angle unit tests or a test report after code changes. Triggers include "단위 테스트", "유닛테스트", "테스트 돌려", "다방면 테스트", "테스트 문서 정리", and the English equivalents "unit test", "run the tests", "multi-angle tests", "write up the test results", and "/unit-test". Codex or Claude runs tests locally without calling another LLM, avoids duplicate full-suite gates, and writes a focused report to the project's test directory. Not for E2E, external DB/network checks, runtime verification, or performance benchmarks.
crosscheck
Use in Claude when the user wants Claude↔Codex cross-verification ping-pong — both analyze independently (blind), exchange findings, merge conclusions, the host implements, and the counterpart checks completion. On this Claude entrypoint, Claude is the host and Codex is the reviewer. Supports analyze-only / plan-only / full / verify-only. Triggers — "크로스체크", "codex 교차검증", "코덱스랑 핑퐁", "codex 리뷰 받아", "교차검증하고 작업해", "codex한테 물어봐", "둘이 의견 취합해", and the English equivalents "crosscheck", "cross-check with codex", "ping-pong with codex", "get a codex review", "ask codex", "have codex verify this", "merge both opinions", "/crosscheck". Korean and English triggers are equivalent; reply in whichever language the user writes. Every Codex call goes through scripts/codex_ask.sh; never call codex exec directly or paste file contents or diffs into prompts.
verify
Use in Codex for evidence-based local verification, or for explicit Claude↔Codex crosschecks where Codex is the host and Claude is the independent reviewer. Local triggers include "검증해줘", "다 됐는지 확인", "verify", and "review this change". Crosscheck triggers include "클로드랑 크로스체크", "Claude 교차검증", "클로드 리뷰 받아", "cross-check with Claude", and "ask Claude to review". Multi-angle unit-test requests belong to the shared unit-test skill. Generic verification stays local and never calls an external LLM.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.