Vault Clarification — Interactive Session

Process the steps below in order; each step's output informs the next, and the first-session infrastructure capture in Step 4 gates profile generation downstream. Do not skip ahead.

Run after vault-ingress has processed talks. Purpose: resolve ambiguities, validate findings, capture intent, and fill in speaker infrastructure config.

The vault lives at ~/.claude/rhetoric-knowledge-vault/ (may be a symlink). Read tracking-database.json from there to get vault_root.

Key Files & References

Step 1 — Rhetoric Clarification

For each surprising, contradictory, or ambiguous observation, ask one topic at a time via AskUserQuestion: intentional vs accidental patterns, invisible context, conflicting signals, and flagged improvement areas. Update summary and DB after each answer.

Example clarification question:

AskUserQuestion(
  question: "Your talks show a delayed self-introduction pattern — brief bio at slide 3,
  then a fuller re-intro mid-talk. Is this intentional or accidental?",
  options: [
    {label: "Deliberate", description: "I do this on purpose to hook first, credential later"},
    {label: "Accidental", description: "I didn't realize I was doing this"},
    {label: "Context-dependent", description: "Depends on the audience/venue"}
  ]
)

Proceed immediately to Step 2.

Step 2 — Blind Spot Moments

Follow references/blind-spot-moments.md — ask about audience reactions, physical performance, and room context that transcripts cannot capture.

Proceed immediately to Step 3.

Step 3 — Humor Post-Mortem

Follow references/humor-post-mortem.md — walk through detected humor beats, grade effectiveness, capture spontaneous material.

Proceed immediately to Step 4.

Step 4 — Speaker Infrastructure (first session only)

If config.clarification_sessions_completed is already ≥ 1, skip this step — infrastructure was captured in the first session. Proceed immediately to Step 5.

Otherwise, ask for any empty config fields (speaker_name through publishing_process.*). See references/schemas-config.md for the full field list and questions to ask.

Proceed immediately to Step 5.

Step 5 — Structured Intent Capture

Store confirmed intents in the confirmed_intents array of the tracking DB. Example:

{
  "pattern": "delayed_self_introduction",
  "intent": "deliberate",
  "rule": "Use two-phase intro: brief bio at slide 3, full re-intro mid-talk",
  "note": "Speaker confirmed this is intentional — hooks audience before credentialing"
}

See references/schemas-config.md for the full schema.

Proceed immediately to Step 6.

Step 6 — Mark Session Complete

Increment config.clarification_sessions_completed in the tracking DB. This counter gates profile generation (vault-profile skill requires >= 1).

Finish here.

Important Notes

• One topic at a time — don't dump all questions at once.
• Update the summary and DB after each answer, not in a batch at the end.
• After completing a session, suggest running the vault-profile skill if 10+ talks are processed and the profile hasn't been generated yet.