cyanluna-git

Run multiple kanban tasks end-to-end in Rolling Wave order — refine each task based on the prior card's actual implementation, then implement, then verify, then refine the next. Use for epic-level batch execution. --big-bang flag disables rolling wave for simple independent tasks.

Codebase exploration skill for uncertain implementation direction. Deeply explores the codebase, produces a direction report, and creates phased kanban tasks. Use when you don't know exactly how to implement something. NOT for direct implementation.

Scan kanban boards for stagnant tasks and optionally mark them. Detects tasks with no agent activity for N days (default 3), outputs a markdown report table, and appends Heartbeat entries to agent_log unless --dry-run.

Refine backlog requirements through structured user interview. Turns rough task descriptions into concrete, actionable requirements with goal, scope, acceptance criteria, and edge cases.

Run the AI team pipeline for kanban tasks — orchestration loop with 6 agents (Planner, Critic, Builder, Shield, Inspector, Ranger), single-step execution, and code review. Use /kanban-run to execute tasks through the 7-column pipeline. AUTO-TRIGGER when: user says "implement task NNN" or any task ID + implement/build/do combination; or user confirms with "yes/ok/go/do it" after Claude proposes implementing a specific kanban task.

프로젝트의 전체 아키텍처, 목표, 주요 결정사항을 wiki/ 디렉토리에 합성하여 정리합니다. 첫 실행 시 전체 생성, update로 변경분 반영. 매 카드가 아닌 프로젝트 수준의 지식을 정리합니다.

Initialize the current project in local SQLite kanban. Creates ~/.claude/kanban-dbs/{project}.db and writes local config. Usage: /kanban-init or /kanban-init my-project-name. Run with /kanban-init.

Local markdown-file kanban for toy and personal projects. No server, no PostgreSQL, no auth — all state lives in KANBAN.md in the project root. Use for solo/small projects where the remote kanban board is overkill. Auto-trigger when KANBAN.md exists and user says "태스크 추가", "add task", "칸반 보여줘", "다음 할 일", "task list", or similar task-management phrases. Sub-commands: init, list, add, move, done, show, edit, refine, run, rm, stats.

Deploy the Javis viewer frontend to the remote server with sw-portal.atlascopco.group as the canonical host. Use when the user says "배포해줘", "deploy viewer", or "publish Jarvis".

Initialize a Javis workflow or project context. Use when the user asks to start Javis, initialize Javis for the current repo, bootstrap Javis state, or prepare the project for later Javis story/review work.

Sprint management. View current/past sprints, velocity tracking, sprint planning, per-member workload. Usage: /javis-sprint, /javis-sprint list, /javis-sprint velocity, /javis-sprint plan

Define, refine, or implement a Javis story workflow for the current repository. Use when the user asks to create a story, break down a requirement into a story, prepare acceptance criteria, or execute work for a named Javis story.

Jira/Confluence/Bitbucket/Boards/Sprints/Members data sync. Usage: /javis-sync all, /javis-sync issues, /javis-sync boards, /javis-sync sprints, /javis-sync members, /javis-sync confluence, /javis-sync bitbucket, /javis-sync status

Pulls latest data from Jira/Confluence to the local database and then deploys that data to the remote Javis server (10.182.252.32). Use when the user wants to update the remote server's database with current data.

프로젝트의 workthrough 문서들을 참조하여 과거 개발 작업 기록과 패턴을 이해하고 적용합니다.

Gemini-Claude Engineering Loop 방법론을 적용하여 계획, 검토, 구현의 3단계 프로세스로 안전하고 품질 높은 코드를 작성합니다.

Vercel Engineering의 React/Next.js 성능 최적화 가이드라인을 적용하여 렌더링 성능, 번들 크기, API 호출을 최적화합니다.

PostgreSQL 데이터베이스 백업 및 복원. Docker/로컬 환경 지원.

CSV에서 worklog를 DB로 증분 마이그레이션. User/Project/WorkType을 의미론적으로 추론하여 매핑. 날짜 범위 지정 가능.

React and Next.js performance optimization guidelines for CPET.db. Tailored for three-tier architecture with Vercel frontend, Google Cloud Run backend, and Supabase database. Use when writing, reviewing, or refactoring React components, data fetching, or optimizing performance.