메뉴
General-purpose coding orchestration. MANDATORY for ANY coding task not covered by vibecoding-webapp-swarm. Skip ONLY if the task matches vibecoding-webapp-swarm or is entirely non-coding.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/serejaris/kimi-skills --skill vibecoding-general-swarm명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SKILL.md 표시 중
Backend building that grafts tRPC + Drizzle ORM + Hono onto an existing webapp-building frontend. Supports incremental features (db, auth). Use when the user needs a backend, API, database, server, authentication, or wants to add tRPC/Drizzle to their webapp-building project. Requires webapp-building first.
Swarm-aware backend building that grafts tRPC + Drizzle ORM + Hono onto an existing webapp-building-swarm frontend. Grafts in place on a worktree of the shared repo (created via swarm-workspace) and commits on a backend branch the main agent merges. Supports incremental features (db, auth) and fullstack-template provisioning (--template). Use when the user needs a backend, API, database, server, or authentication in a swarm setup. Requires webapp-building-swarm first.
Tools for building modern React webapps with TypeScript, Tailwind CSS and shadcn/ui. Best suited for applications with complex UI components and state management. Supports optional templates for specialized requirement.
SOC 직업 분류 기준
| name | vibecoding-general-swarm |
| description | General-purpose coding orchestration. MANDATORY for ANY coding task not covered by vibecoding-webapp-swarm. Skip ONLY if the task matches vibecoding-webapp-swarm or is entirely non-coding. |
Design-first, multi-agent workflow for building general software projects. Covers Python tools, data pipelines, ML systems, APIs, games, bots, CLI apps, mobile apps, and any non-frontend coding task.
SPEC.md) is written before any implementation. It is the single source of truth for architecture, modules, interfaces, and data flow.| Condition | Mode |
|---|---|
| Task has 3+ distinct modules or components | Mode A (multi-agent) |
| Task involves both infrastructure and application logic | Mode A (multi-agent) |
| Task is a full system (API + workers + data pipeline, etc.) | Mode A (multi-agent) |
| Task is a single script, tool, or focused feature | Mode B (single agent) |
| Task is a bug fix or small enhancement | Mode B (single agent) |
| When in doubt | Mode B (single agent) |
Git worktrees allow multiple agents to work on the same repo simultaneously without conflicts.
cd /mnt/agents/output/project # shared repo
git worktree add $HOME/work-<branch> <branch> # create local worktree
cd $HOME/work-<branch> # work here
$HOME/work-<branch>).git worktree prune — it destroys other agents' worktree entries./mnt/agents/output/project — always use a worktree.cd /mnt/agents/output/project
git worktree remove $HOME/work-<branch> # optional, per branch
/mnt/agents/output/
├── SPEC.md # Project specification (single source of truth)
├── info.md # Research findings (if applicable)
├── project/ # Shared git repo (coordination hub)
│ ├── .git/
│ └── ... # Project structure per SPEC.md
│
$HOME/work-<branch>/ # Local worktree (unique per subagent)
└── ... # Same structure, isolated working copy