meeting

PR/FAQ Review Meeting

Run an interactive review meeting where four personas — a principal engineer, a target customer, a skeptical executive, and a builder-visionary — debate the weak spots in your PR/FAQ document. You are the PM and final decision-maker.

Steps

1. Find the document. If $ARGUMENTS specifies a path, use it. Otherwise, search for prfaq.tex in the project root using Glob. If no document exists, tell the user to run /prfaq first — the meeting validates an existing document, it doesn't generate one.

2. Read the meeting guide. Load ${CLAUDE_PLUGIN_ROOT}/skills/prfaq/references/meeting-guide.md for the full meeting flow, synthesis guidelines, and persona details. Also load ${CLAUDE_PLUGIN_ROOT}/skills/prfaq/references/plain-style.md — generative prose rules (no em dash, no negative parallelism, no corporate-register vocabulary, no value-claim filler, no explaining the document to the reader). The four persona agents load this guide themselves for their own structured responses, but the debate narrative you synthesize in step 6c is authored directly by you, never written to a file before the user sees it, and never reaches prose_lint.py's hook — this guide is the only check on it.

3. Run the pre-meeting scan. Read the full .tex document. Extract \prfaqstage{value} to calibrate expectations (see Stage Calibration in the meeting guide). Identify 5-8 hot spots using the four risk-lens questions first (feasibility, value/customer reality, strategic fit/viability, ambition — see Phase 0 in the meeting guide) — documentation issues (unsupported claims, vague language, thin evidence, hedging gaps) are valid but must be at most half the agenda. Rank each as Critical, Warning, or Suggestion — calibrated to the document's stage.

4. Get the opening assessment. Launch a single prfaq:meeting-executive (Alex) agent, standalone, with the document's stage, the Risk Assessment table, and the hot spot titles/severities from step 3. Tell Alex explicitly: this is a meeting-opening assessment, not a section evaluation — reply in 3-5 sentences of continuous prose, not the structured format (see the Exception in meeting-executive.md). Ask for a 3-5 sentence holistic opening read, organized around Phase 0b's three questions (problem worth solving / strong and differentiated solution / build it now) in the meeting guide. Present it to the user before the agenda. If the agent call fails, times out, or returns ungrounded content, tell the user the opening assessment could not be generated and proceed to the agenda without one.