skywatch-working-the-queue

Implement an OODA-loop workflow for triaging Ozone moderation reports.

6|Updated Feb 21, 2026
One-click install
npx skills add https://github.com/skywatch-bsky/skywatch-agent-skills --skill skywatch-working-the-queue
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skywatch-working-the-queue
Source: https://github.com/skywatch-bsky/skywatch-agent-skills/tree/main/polytoken/skills/skywatch-working-the-queue
Command: npx skills add https://github.com/skywatch-bsky/skywatch-agent-skills --skill skywatch-working-the-queue

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the challenge of high-volume moderation queue management by providing a structured, OODA-loop-based workflow that ensures consistent, evidence-backed triage decisions while minimizing analyst fatigue.

Core Features & Use Cases

  • OODA-Loop Triage: Guides the analyst through observation, orientation, decision, and action phases for moderation reports.
  • Evidence-Based Classification: Automates the collection of rule hits, content context, and moderation history to support classification decisions.
  • Use Case: Use this skill when processing large batches of Ozone moderation reports to ensure that every decision is supported by verbatim evidence and policy precedents.

Quick Start

Use the skywatch-working-the-queue skill to pull 20 recent reports from the Ozone moderation queue for triage.

Frequently Asked Questions about skywatch-working-the-queue

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

FAQPage Schema
How do I streamline high-volume moderation queue triage in Ozone?

Moderation queue triage can be streamlined by implementing an OODA-loop workflow that guides you through observing reports, orienting with policy, and acting on classification decisions. This ensures consistent, evidence-backed outcomes while minimizing analyst fatigue.

What is the OODA loop workflow for moderation report classification?

The OODA loop workflow for moderation separates processing into four phases: observing the report, orienting with local policy documentation, deciding on a classification, and acting on the decision. It automates collection of rule hits and content context to support verbatim evidence-based actions.

How do I process batches of Ozone moderation reports with policy precedents?

You process batches of Ozone moderation reports by pulling recent entries, such as 20 at a time, into the OODA triage workflow. The system collects moderation history and rule hits to ensure every classification decision is supported by verbatim evidence and policy precedents.

Do I need local policy documentation and Skywatch MCP servers for moderation triage?

Yes, moderation triage requires integration with Skywatch MCP servers and local policy documentation. These dependencies ensure the OODA-loop workflow consistently aligns classification decisions with established rules and verbatim evidence from Ozone and ClickHouse data sources.

Can I handle appeals and proactive filtering across ClickHouse and Ozone data sources?

Yes, triage supports diverse entry points including appeals, proactive filtering, and standard reports across Ozone and ClickHouse data sources. This allows analysts to process varied moderation workflows through a single evidence-based classification system.