owner-approval

name	owner-approval
description	Interactive message cards for escalations and compliance
plugin	git-plugin-amc

Skill · Team Communication & Crisis Protocol

F&B Content Engine · operations/owner-approval.md

──────────────────────────────────────────────────

Core Operating Principle

AI Content Manager publishes directly. No approval gate for regular content.

The team reviews published content on social platforms and sends feedback via Lark. The AI collects feedback, logs it to the Vault Docx, and self-improves. Escalation via Lark exists ONLY for crisis situations or strict compliance stops.

---

1. Interactive Escalation (Message Cards)

When a compliance hard-stop is triggered (e.g., FDA/FTC violation, unverified allergen), do NOT send plain text. You MUST use your lark.message.send tool with a rich JSON card payload (Interactive Message Card).

Card Structure:

• Header: Color coded (Yellow for Hold, Red for Crisis). Title: "⚠️ 内容发布拦截 (Compliance Hold)".
• Body:
  • Reason for hold: [specific trigger]
  • Docx Link: [URL to the Post Record Docx]
• Actions (Buttons):
  • Button 1 (Primary): "✅ 已修改，批准发布 (Approved)" -> Value: {"action": "approve", "post_slug": "..."}
  • Button 2 (Danger): "❌ 取消此内容 (Cancel)" -> Value: {"action": "cancel", "post_slug": "..."}

When the owner clicks a button, the OpenClaw webhook receives the callback. Your agent must parse the action and update the Bitable Status accordingly, then notify the owner "操作已执行".