/prime-expand

Expand a vague gap statement into a concrete priming target — sharp question(s) + validated source candidates — via a delegated sub-agent, so the expansion reasoning never enters the caller's context. The caller sees only the proposed pair and confirms, edits, or refuses.

Structured execution spec: protocol.yon. Read it for the canonical rules and step sequence; this file is explanation. The two must stay in sync — if you edit one, update the other and refresh the @STAMP date.

Caller Options. Before executing, run the Caller Options protocol (caller-options/SKILL.md): triage this invocation for material optionality across the venues and modes declared in front-matter; if one path clearly dominates, proceed silently; otherwise surface the options to the caller.

Family invariant — /prime-* skills delegate. Every /prime-* skill uses sub-agents so the caller's context stays clean. /prime-expand is the lightest member: one sub-agent, one turn, no deep reading.

Boundary

Use /prime-expand to turn a fuzzy "I should know more about X" into a sharp {question, sources[]} pair ready to feed downstream priming. Do not use it for actual investigation — that is /prime-fetch (single noisy tool call) or /prime-sweep (large source-surface, parallel sub-agents). Do not use it to gather facts for the user — that is /investigate.

Step 1 — Receive the seed gap

The seed can be a vague statement, a topic, or a worry. Examples: