review

Compile contextual evidence and policy-aligned decision options for flagged content review.

7|3|Updated Mar 17, 2026

Search Tags:#moderation #review #policy #redaction #case-management #content-moderation

Ready to run

npx skills add https://github.com/brainbrewlabs/brainbrew-devkit --skill review-brainbrewlabs

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: review
Source: https://github.com/brainbrewlabs/brainbrew-devkit/tree/main/plugin/config/templates/moderation/skills/review
Command: npx skills add https://github.com/brainbrewlabs/brainbrew-devkit --skill review-brainbrewlabs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps moderators turn flagged content and machine classifications into a safe, well-documented human review case so decisions are faster, consistent, and auditable.

Core Features & Use Cases

Assemble Context: Gather original content, scan/classification outputs, author history, reports, and related items into a single review view.
Safe Presentation: Redact or excerpt extreme content, clearly label material under review, and highlight relevant evidence for the reviewer.
Policy & Decisions: Surface applicable policy sections, present AI assessment with confidence, and offer clear decision options (Approve, Remove, Warn, Escalate).
Use Case: A moderator receives a flagged post with borderline language; use this Skill to compile context, evaluate severity, cite policy, and record the final decision.

Quick Start

Review the flagged content case and produce a complete human review case including context, policy citations, AI assessment, and recommended decisions.

Frequently Asked Questions about review

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

FAQPage Schema

How do I compile a content moderation case for human review?▼

Redact sensitive content for moderation review by excerpting extreme material and clearly labeling items under review. This Skill highlights relevant evidence while ensuring safe presentation for human moderators evaluating flagged posts.

What context do I need to prepare a moderation review case?▼

Surface applicable policy sections during review by matching classification metadata against relevant policy texts. This Skill presents AI assessment with confidence levels and offers clear decision options like Approve, Remove, Warn, or Escalate.

Can I reconcile automated scan outputs with human moderation decisions?▼

Moderation review cases produced by this Skill include original content, scan results, author history, report counts, and policy citations. They present recommended decisions and AI assessments to document the final moderation outcome.

Does this moderation review Skill work without external dependencies?▼

Use this Skill when flagged content requires human judgment, senior review, or reconciliation of automated classifications. It is applicable for borderline language posts or escalated items needing documented policy-aligned decisions across moderation workflows.