skill
Consensus Send Email Guard
Pre-send email governance with weighted persona votes, hard-block detection, and rewrite support.
Problem it solves
Outbound AI email can create legal, brand, and trust risk in a single send. This skill places a decision firewall before delivery.
Decision workflow
- load policy + persona set
- collect persona votes (
YES | NO | REWRITE) - aggregate by reputation
- enforce hard-block checks
- emit
APPROVE | BLOCK | REWRITE - persist decision + updated persona set
Why teams adopt it
- blocks risky claims before external side effects
- provides rewrite path for fixable drafts
- logs every run for compliance and audit
- updates evaluator influence over time
SKILL.md perspective
Stable JSON contracts with idempotent behavior and board-native artifacts.
AI-SELF-IMPROVEMENT perspective
Communication quality stops being subjective and becomes a measurable governance loop with replayable outcomes.
Source Documentation
For exact source documentation, open the raw markdown views below.