Use when a PR is approved by vibe-review and ready to merge - verifies CI green, checks for conflicts against latest main, rebases if needed, squash merges, archives the…
他の AI ツール（Copilot CLI, Claude Engineer, Cursor 等）から開発のコンテキストや「ノリ」（スタイル・規約・進捗状況）を抽出し、Gemini CLI のメモリ（GEMINI.md 等）に移行するためのスキルです。
Use when starting or switching to a new human-collaboration task. Confirm the target issue, bootstrap the corresponding dev/issue flow scene, and hand off to the chosen…
Interact with Notion using the unofficial private API - pages, databases, blocks, search, users, comments
Set up a vibe-stack app as a BUSINESS / operations tool the owner runs by talking — define the things they manage (reservations, employees, orders, inventory, …) and the rules,…
Use when Codex needs to orient on the active Vibe repository, inspect the current Vibe work loop, or summarize repo/plugin surfaces before planning changes.
Use when a PR has merge conflicts with main or mergeStateStatus is BEHIND/DIRTY - dispatches an agent to rebase the branch onto latest main, resolve conflicts, re-run tests, and…
Audit, fix or verify Redis Streams, BullMQ or ARQ job identity, locks, acknowledgements, retention, backpressure and recovery. Respect the selected framework delivery semantics.
Top-level orchestration skill coordinating the entire 7-step surgical vibe-to-enterprise reengineering pipeline with automated safety and economic optimization controls.
Use when a PR is open and CI green - dispatches a fresh subagent for two-stage code review (spec compliance then quality), posts findings to the GitHub PR as review comments with…
Author and edit VibeFrame scene projects. Use when the user wants editable HTML-based video scenes, storyboard-to-MP4 composition, or a host-agent authoring loop.
Vibe-SDLC 流程總覽與導航。顯示完整 SDLC 流程、角色定義，並引導使用者進入對應的 Phase skill。 使用時機：專案啟動、查看目前進度、不確定該用哪個 Phase skill 時。
Vibe-SDLC Phase 3：開發循環 (Execution Loop)。領取 Issue 進行開發、測試、Vibe Check，通過後自動建立 PR。 使用時機：日常開發，需要從看板領取 Issue 並實作功能。
Vibe-SDLC Phase 4：CI 監控、失敗修正與合併後作業。處理 CI 結果、修正失敗、Merge 後更新 Dev Plan。 使用時機：PR 已建立（由 Phase 3 自動建立），需要監控 CI、處理失敗、或執行合併後作業。
Vibe-SDLC Phase 5：回饋收集、Release 發佈與迭代規劃。 使用時機：里程碑收尾完成（由 Phase 4 觸發），需要收集回饋、發佈 Release、啟動下一輪迭代。
Use when asked about Vibe's self-plan state, when docs/examples/vibe-self-plan.json may be stale relative to examples/vibe-self.vibe, or when explicitly told to regenerate the…
A package builder skill that compiles specs/ documents into standard spec-kits and scaffolds the clean target codebase sandbox.
Use when you want a daily or periodic summary of vibe-flow activity formatted for Slack/Discord - groups by merged/in-review/blocked/in-progress, includes cost aggregation and PR…
【Vibe】轻量意图捕获 — 3-5 轮对话把想法变成 spec → docs/specs/lite-spec.md。当用户说「快速试个东西/做个小玩具」时使用。
바선생 성장 리포트 — AI 활용 세션 데이터를 분석하여 성장 리포트를 자동 생성합니다. "성장 리포트", "성장 분석", "얼마나 성장했는지", "레벨 체크", "성장 트래킹", "growth" 같은 요청에 사용됩니다.
바선생 지식 베이스 — AI 활용 성장을 위한 용어, 레벨 시스템, 안티패턴, 멘토링 프레임워크 질문에 응답합니다. "안티패턴이 뭐야?", "레벨 시스템 설명해줘", "바이브코딩이 뭐야", "성장 지표", "멘토링 프레임워크", "회고 방법" 같은 요청에 사용됩니다.
바선생 멘토링 — AI 활용 능력을 코칭합니다. 요청 품질, 안티패턴, 개념 학습, 종합 코칭 4가지 모드를 지원합니다. "멘토링해줘", "코칭해줘", "요청 코칭해줘", "뭘 잘못하고 있는지", "어떻게 요청하면 좋을지", "mentor", "coach" 같은 요청에 사용됩니다.
바선생 초기 설정 — 프로젝트 연결, 워크스페이스 유형 분류, 첫 변환까지 안내합니다. "바선생 시작", "온보딩", "초기 설정", "처음이에요", "셋업", "setup" 같은 요청에 사용됩니다.
바선생 대화 변환 — Claude Code 대화 로그를 Markdown으로 변환하고 분석 가이드를 제공합니다. "변환", "retro", "대화 변환", "로그 변환", "회고", "이번 주 대화" 같은 요청에 사용됩니다.
Upgrade the local Vibe-Skills installation to the latest official default-branch state.
Complete 5-step workflow to build an MVP from idea to launch. Use when the user wants to start a new project from scratch, go through the full workflow, or says "help me build an…
Build ứng dụng web với Vibecode methodology. Claude Code = Builder, Claude Chat = Architect.
Guides VibeCoder (non-technical users) through natural language development. Use when user asks what to do next, how to use the system, needs help, or is stuck.
Plan and manage AI-assisted development sprints with GitHub branch protections. Analyze issues, group by feature or discipline, generate 3-sprint plans with semantic versioning…
Meta-doctrine for human taste, agent force, Loctree/AICX structure, and reality-tested shipping posture.
Framework de governança para desenvolvimento de software com IA — guia completo para vibe coders sem experiência em engenharia.
Control VibeDiff code review instances — fetch review comments, reply to threads, create comments, resolve/reopen threads, and manage review state.
Explain a jj revision by fetching its diff and adding explanatory comments in VibeDiff to document WHY changes were made.
Execute all open GitHub Issues in dependency order. Iris picks up Issues one by one, runs the 11-Step workflow for each, and reports progress.
Lightweight anti-hallucination workflow for task kickoff, review prioritization, and regression retrospectives.
A personality test that evaluates you through a standardized analysis of real Vibe Coding data, based on your long-term use of tools like Claude Code, Codex, etc.
Use to diagnose vibekit installation health — skill file integrity, runtime registration parity, `.vibekit/` directory health, `docs/` subdir presence, authoring-contract…
Use when VibePro work needs codebase-memory-mcp impact context for changed files, call paths, routes, symbols, or risk hints without treating topology as correctness evidence.
Use when reviewing VibePro PR preparation artifacts, deciding whether to proceed, split, add evidence, waive with reason, or block.
Use when working with VibePro CLI, Graphify, Story diagnosis, task planning, PR preparation, Gate evidence, or VibePro review artifacts.
Lightweight requirements gathering before app generation. Asks non-technical multiple-choice questions to understand user intent, then produces a brief for the generate prompt.
Vibes-Coded marketplace connector: npm vibes-coded-agent-connector (0.1.6+ getReclaimPublicSummary), Reclaim SOL UI /reclaim-sol, public reclaim stats API, register agent — from…
Uses the Vibesafe MCP server to scan, compile, test, save, diff, and report status for Vibesafe units.
Audita segurança de código e decisões de arquitetura durante o ciclo VibeDev. Use quando o usuário está adicionando autenticação, persistência de dados, integração com API de…
Colaboración multi-agente y multi-persona en tiempo real sobre un repo vía VibeSync. Úsala cuando el usuario quiera unirse a un proyecto compartido por un link de VibeSync,…
Front-end style guide for the Vibe Tracking project. Defines the visual design system including colors, typography, buttons, cards, and illustration style.
Query AI-generated trading signals from vibetrading-datahub. Signals are produced by autonomous agents analyzing whale activity, news, funding rates, and technical indicators.
Manage VibeTunnel terminal sessions. Create, list, monitor, and control terminal sessions visible in the VibeTunnel web dashboard.
Local Spanish TTS using Microsoft VibeVoice. Generate natural voice audio from text, optimized for WhatsApp voice messages.
Disciplined engineering workflow for any coding task — build, modify, debug, deploy. TRIGGER on any software task.
Use when a vibing.nvim chat session's context feels lost or discontinuous — after a session reset, a dropped connection, or when Claude's own reasoning no longer matches what was…
Use when the user wants to find a past vibing.nvim conversation by topic — phrases like "前に〜について聞いたことあったっけ", "did we talk about X before", "find that chat where I asked about Y".
Run several independent tasks in parallel by creating worker vibing.nvim chats, handing each one a self-contained brief, and aggregating their results.
Use when tending NTM agent swarms, unsticking panes, handling rate limits, or coordinating convergence.
Create a new git-worktree-backed isolated work area for the current vibing.nvim chat via natural language — no separate UI.
Remove a git-worktree-backed isolated work area for vibing.nvim chats via natural language — no separate UI.
List git-worktree-backed isolated work areas for vibing.nvim chats via natural language — no separate UI.
Get a git worktree branch's code actually running (dev server, tests, CLI invocation, etc.) without merging or rebasing it, for vibing.nvim chats.
Use when the sandbox app fails to build, boot, render, authenticate, call AI routes, read offers, or deploy cleanly.
Automatically log AI agent activity to the user's viboost.ai public profile. Tracks every tool call the agent makes. Fires at the end of every response.