Refine ideas into detailed designs through Socratic dialogue. Use when: user has rough idea, needs to clarify requirements, explore approaches. Triggers: "brainstorm", "discuss idea", "I'm thinking about", "what if", "help me think through", "explore options", "/brainstorm".
/plugin marketplace add timequity/vibe-coder/plugin install vibe-coder@vibe-coderThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Turn rough ideas into fully formed designs through natural collaborative dialogue. Integrated with idea-validation — brainstorming is an optional deep-dive before PRD creation.
| Trigger | Action |
|---|---|
/brainstorm command | Full brainstorm session |
| Short idea (<10 words) | Suggest brainstorm in /ship |
| Complex project type | Suggest brainstorm in /ship |
| User asks "what if" / "help me think" | Start brainstorm |
| User has detailed description | Skip to idea-validation |
Questions to ask (one at a time):
"Расскажи подробнее — что именно это должно делать?"
"Кто будет этим пользоваться? В каком контексте?"
"Какую проблему это решает?"
"Как понять что получилось?"
Based on project type, explore key decisions:
Ask about constraints and non-goals:
"Что точно НЕ должно быть в MVP?"
"Есть ограничения? Бесплатные сервисы only? Дедлайн?"
"Какой масштаб ожидаешь — 10 пользователей или 10000?"
Once you understand:
## Резюме
**Проект:** {name}
**Тип:** {type}
**Проблема:** {one sentence}
**Пользователь:** {who}
**MVP Features:**
1. {Feature 1}
2. {Feature 2}
3. {Feature 3}
**Не делаем:**
- {Non-goal 1}
- {Non-goal 2}
**Ограничения:**
- {Constraint 1}
Всё верно? Готов создать PRD?
After brainstorm completes:
Brainstorm Complete → idea-validation → PRD.md (Full)
| Principle | Why |
|---|---|
| One question at a time | Don't overwhelm |
| Multiple choice when possible | Easier to answer |
| YAGNI ruthlessly | Remove unnecessary features |
| Explore alternatives | Propose 2-3 approaches |
| Validate incrementally | Present sections, validate each |
| No technical jargon | User chooses nothing technical |
If user runs /brainstorm without /ship:
User: /brainstorm I want to make a bot that tracks expenses
Claude: [Starts brainstorm]
"Интересная идея! Давай уточним детали.
Это для Telegram, Discord, или другой платформы?"
[After brainstorm]
Claude: "Готово! Хочешь сразу начать строить? Могу запустить /ship"
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.