event-management
Planning and executing developer events, conferences, and meetups
kano-agent-backlog-skill
Local-first, multi-product backlog management with agent collaboration discipline.
technical-leadership
Provide technical leadership guidance for reviews, mentoring, and decisions
skill-bootstrap
Detect stack and generate project-specific skills
executing-plans
Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches
create-sprint
Sprint(Iteration) 목표 설정 및 시작. Use when (1) 새 Sprint 시작, (2) Sprint 계획 수립, (3) /SEMO:sprint create 커맨드.
nixtla-exogenous-integrator
Incorporates external variables (holidays, weather, events) into TimeGPT forecasts to improve accuracy. Use when forecasts require external data, holidays impact sales, or weather affects demand. Trigger with "include holidays", "add weather data", "integrate events".
start-task
작업 시작 (Supabase DB 기반). Use when (1) "랜드 #123 작업 진행", (2) "#45 시작하자", (3) "이슈 작업 시작해줘". 이슈 상태 변경 + 브랜치 생성 + Draft PR.
code-planning
Plan implementation changes before coding. Use when the user requests a new feature, modification, or asks for a plan. Ensures full understanding, discovers existing code, creates detailed file/folder structure with contracts and tests, and gets user approval before implementation.
release-reports
Generates weekly release cycle reports for the team. - preview: What's shipping (run Sunday after release train) - retro: What happened (run Tuesday after prod stabilizes)
kano-agent-backlog-skill
Local-first, multi-product backlog management with agent collaboration discipline.
subagent-driven-development
Use when decomposing complex work. Dispatch fresh subagent per task, review between tasks. Flow: Load plan → Dispatch task → Review output → Apply feedback → Mark complete → Next task. No skipping reviews, no parallel dispatch.
playbook-init
タスク開始フローのエントリーポイント。prompt-analyzer の分析結果を受け取り、pm SubAgent に委譲する。
ue
UE (user experience engineering) skill for defining end-to-end user experience behavior and interaction logic. Use for tasks like flow design, interaction models, state machines, error recovery, input validation, usability heuristics, accessibility, and turning UX intent into testable acceptance criteria for implementation.
bd-workflow
How to use bd (beads) for issue tracking, ready work, status updates, and comments in this repo.
subagent-driven-development
在当前会话中执行包含独立任务的实施计划时使用。每个任务派送新的子Agent，并进行两阶段审查。Use when executing implementation plans with independent tasks - dispatch fresh subagent per task + two-stage review (spec then quality).
waterline-model
Diagnose team problems by checking structural issues (goals/roles) at the surface before diving deep into personality conflicts. 80% of team problems are structural, not personal.
feedback-collector
Systematically gather, organize, and act on user feedback
spec-verification
Use during Phase 5 of spec creation to verify completeness and accuracy before implementation - checks requirements accuracy, visual integration, reusability leverage, task specificity, and identifies over-engineering concerns
resize-story
Use when a story needs to be resized based on new information. Adjusts estimates and splits/combines stories as needed.
