flagging

Routes severity-classified content to appropriate moderation queues or hides it, notifying moderators and updating statuses.

7|3|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/brainbrewlabs/brainbrew-devkit --skill flagging
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: flagging
Source: https://github.com/brainbrewlabs/brainbrew-devkit/tree/main/plugin/config/templates/moderation/skills/flagging
Command: npx skills add https://github.com/brainbrewlabs/brainbrew-devkit --skill flagging

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Flag content that has been classified and automatically route it to the appropriate moderation workflow based on severity and category.

Core Features & Use Cases

  • Automatic flagging and routing: Route content to urgent or standard queues based on severity, and trigger notifications to moderators.
  • Queue management: Move items through hidden/flagged/queued/monitored statuses with SLA awareness.
  • Use Case: When a post is flagged as high severity, the system hides it, escalates to the appropriate moderation queue, and notifies the moderation team.

Quick Start

Instruct the system to flag the current content and route it to the appropriate queue based on the classification results.

Frequently Asked Questions about flagging

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automatically route content moderation actions based on severity?

Automatic content moderation routing applies severity classifications to move items through hidden, flagged, queued, or monitored statuses and trigger notifications. It uses severity levels like Critical or High to hide content and escalate to urgent review queues.

What is the best way to handle high severity content flags in a moderation queue?

Handling high severity content flags involves hiding the flagged post immediately, escalating it to the appropriate urgent moderation queue, and sending notifications to the moderation team. This ensures critical items receive immediate attention.

Can I use automated moderation actions for low and medium severity classifications?

Automated moderation actions support low, medium, high, and critical severity classifications. Lower severity items can be routed to standard review queues or monitored statuses with SLA awareness, ensuring appropriate prioritization.

Do I need classification results before flagging and routing content?

Classification results are required before flagging and routing content. The system relies on these results to determine the severity level, apply automated actions like hiding, and update the status in moderation records.

How does queue management work for flagged content with SLA awareness?

Queue management for flagged content moves items through hidden, flagged, queued, and monitored statuses while tracking SLA awareness. This ensures moderation teams meet response time requirements based on severity classifications.