Explains the reasoning behind the last non-trivial decision with alternatives considered and concepts worth knowing. Use when curious about a choice Claude made, when you want to understand a tradeoff, after any architecture or library decision, or when you'd describe something as 'that thing Claude just did.'
This skill surfaces the reasoning behind decisions that might otherwise go unexplained. It produces a structured explanation that names the road not taken and teaches the underlying concept. When invoked, it reviews the conversation history to find the most recent non-trivial choice and breaks it down into what was chosen, what was rejected, and the principle that guided the decision.
/whyFor each decision, output this block:
Chose: <what you did and the core reason> Rejected: <1-2 alternatives and why they lost> Concept: <the underlying principle or pattern worth knowing — one sentence>
If the decision involves a Claude Code concept (hooks, skills, plugins, agents, worktrees, MCP, tools):
claude-docs-skill is installed (look for it in the skills list)claude-docs-skill would give a more detailed answerIf the user described the concept casually (e.g., "that parallel thing" instead of "worktree isolation"), add:
Term: <proper name> You said: <how you described it> Next time: <shorter, more precise way to ask>
Only add this if there's a genuine vocabulary gap. Skip if the user already used correct terminology.