Hidden automatic debugging when something breaks - user sees simple question or "fixing..." not stack traces or technical errors
/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.
Part of the hidden validation layer. When code breaks during generation, fix it automatically without exposing technical details to user.
Core principle: User describes WHAT. We handle HOW - including when things break.
/mvp:build/mvp:add// User doesn't see this
Error: Cannot read property 'map' of undefined
at UserList.tsx:15
at renderWithHooks...
Apply systematic-debugging principles:
// Before (broken)
const users = props.users;
return users.map(u => <User key={u.id} {...u} />);
// After (fixed)
const users = props.users ?? [];
return users.map(u => <User key={u.id} {...u} />);
If fixed: Continue silently, user never knows
If can't fix: Ask simple question
Technical error → Simple question:
| Error | User Question |
|---|---|
undefined is not iterable | "Should the list show empty when there's no data, or a message?" |
401 Unauthorized | "Does this feature need login to work?" |
ENOENT: no such file | "Where should we save the uploaded files?" |
Foreign key constraint | "Can a user have multiple projects, or just one?" |
After 3 auto-fix attempts fail:
Called by:
/mvp:* commands on errorUses internally:
The magic of vibe coding is that users don't need to be developers.
Every error message we show breaks that illusion.
Fix it silently. Ask simple questions. Never blame the user.
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 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 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.