AI Agent Skills

Use when aweskill state is abnormal or repair-first: broken projections, duplicates, stale entries, suspicious or new matches, sync problems, malformed SKILL.md frontmat…

End-of-session ritual — audit today's patterns against accumulated memory, propose promotions, refresh MEMORY.md, and write the session handoff. Use when the user says "…

Reconcile the project's documents with what the code now shows, after a merge or at the end of a build: spec statuses (building → done only with a named gate, or → stale…

Write the human-facing prose about a change — PR body · changelog entry · release note · postmortem — and put it in the right file. Use when the user says "write the PR"…

Audit MEMORY.md against the memory discipline — oversized sections, settled multi-session patterns that belong in knowledge/concepts/, session-headed chronicle blocks, r…

Cross-check the agent's own answer with independent reviewers before bringing it to the user. Use when the user says 'second opinion', 'sanity check', 'cross-check', 'am…

End-of-session adversarial review loop. Assemble the session's work into a role-assigned, self-contained brief, then run independent reviewers in parallel — an

Interactive walkthrough of the Memory Kit system using the user's actual project files. Use when the user says "/memory-kit:tour", "give me a tour", "покажи как это рабо…

Template skill shipped by the example-plugin oh-my-gjc plugin. Use when you want a worked reference for how an oh-my-gjc plugin packages a skill. Replace this body with…

완성된 작업을 머지 전 독립 외부 리뷰 게이트로 재심한다. "외부 리뷰 게이트 / 최종 리뷰 / 머지 전 교차 리뷰 / extragoal / 완성 diff 독립 검증 / 다른 모델로 최종 점검하고 머지" 같은 요청에 활성화. ultragoal(또는 임의 완성 브랜치)을 끝낸 뒤, 무공유 컨텍스트·교차패…

`/omg:no-english` 명령이 명시적으로 요청했을 때만 한국어 응답의 불필요한 영어 혼용·직역투·영어 전문용어 남발을 줄이고 자연스럽고 정확한 한국어를 우선한다. 다른 입력에서는 자동 활성화하지 않는다. 코드 식별자·명령어·파일명·API 이름·정확한 인용은 그대로 보존하며 사용자가 영어 답변이…

`/omg:preset-pack` 명령이 명시적으로 요청했을 때만 omg 최종 프리셋(daily/agent)을 사용자 `~/.gjc/agent/models.yml`에 이름 단위로 병합·확인·제거한다. 다른 입력에서는 자동 활성화하지 않으며, 명시 호출 없이는 models.yml을 절대 수정하지 않는다.

Automatically generate clear, comprehensive documentation for codebases — including API references, inline docstrings, README files, and usage guides.

Perform thorough code reviews on files or pull requests, checking for bugs, security vulnerabilities, performance issues, and style violations.

Set up and manage data labeling workflows using manual annotation tools, semi-automated pipelines, active learning, and programmatic weak supervision.

Systematically diagnose and fix software bugs by analyzing error messages, stack traces, logs, and runtime behavior across multiple languages.