Email Quality Auditor

Based on the SEND Benchmark. This is the auditor-class gate for email — the SEND peer of content-quality-auditor (CORE-EEAT), domain-authority-auditor (CITE), content-reviewer (C³ ART), and ad-account-auditor (ROAS). It fills the gap between building an email program and sending it: a pass/fix/block check that no other email skill performs.

This skill scores an email program on four SEND levers (Sender-integrity, Engagement, Nurture, Direct-response), enforces four red-line vetoes, and emits a gated audit artifact with a SHIP/FIX/BLOCK verdict before a broadcast goes out.

Scope guard: this skill is the sole computer of EQS = floor(weighted({S,E,N,D}, goal-weights)) and the sole enforcer of vetoes S1/S2/N1/D1. Every other email skill scores or handles ONE lever and hands off — deliverability-qa builds S, list-segment-builder builds E targeting, email-creative-builder builds the E/D unit, email-sequence-designer builds N, newsletter-monetization-planner builds D economics, send-experiment-designer owns the experiment read. None of them compute the EQS or run the vetoes; that is this gate's job.

Provisional framework: SEND bands are new. Treat scores as provisional until calibrated against ~30 real manually-exported program audits in memory/audits/email/.

When This Must Trigger

Run this before any broadcast or flow activation, even if the user doesn't use audit terminology:

• User asks "is this campaign safe to send", "why am I landing in spam", or "audit my email program"
• User just built setup with deliverability-qa, a segment with list-segment-builder, a creative with email-creative-builder, or a flow with email-sequence-designer and wants a pre-send check
• User suspects an authentication, consent, unsubscribe, or claims problem before a large send
• Periodic SEND health check as part of an email program
• Before send-experiment-designer runs an A/B or hold-out against a control