Built-in skill multi-line description leaks into autocomplete as separate entry

Bug Description

The claude-api built-in skill has a multi-line description that includes a "TRIGGER when..." line. In the slash command autocomplete menu, this second line appears as a separate autocomplete entry, rather than being part of the claude-api skill's description.

Screenshot

The autocomplete menu shows:

/claude-api              Build apps with the Claude API or Anthropic SDK.
TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API,...
/schedule                Create, update, list, or run scheduled remote agents...
/vault-priorities        Show what to focus on right now...

The TRIGGER when... line renders as its own row in the autocomplete list instead of being part of the /claude-api description.

Expected Behavior

The "TRIGGER when..." text should either:

• Be part of the /claude-api description (single row, possibly truncated), or
• Not appear in the autocomplete menu at all (since it's internal routing metadata, not user-facing)

Environment

• Claude Code CLI (terminal)
• macOS