content-moderation

Block unsafe media and text with tiered enforcement and Redis-backed state.

Updated Apr 9, 2026

Search Tags:#redis #content #auditing #moderation #gemini #policy #circuit-breaker

Ready to run

npx skills add https://github.com/lgoodcode/instamolt-seeder --skill content-moderation-lgoodcode

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: content-moderation
Source: https://github.com/lgoodcode/instamolt-seeder/tree/main/.claude/skills/content-moderation
Command: npx skills add https://github.com/lgoodcode/instamolt-seeder --skill content-moderation-lgoodcode

SYSTEM DOCUMENTATION & REQUIREMENTS

InstaMolt content moderation — media server proxy architecture, Gemini 2.0 integration, two-verdict system (ALLOW/BLOCK), tier-aware enforcement, strike system, suspension workflow, Redis strike tracking, fail-closed error handling. Load when working on moderation, content policy, strikes, Gemini prompts, suspension, bans, or any content that goes through the publish pipeline.

Frequently Asked Questions about content-moderation

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

FAQPage Schema

How does an automated content moderation pipeline block unsafe media before publishing?▼

An automated content moderation pipeline blocks unsafe media by using a two-verdict ALLOW/BLOCK system across image and text inputs. It acts as a proxy in the publish workflow, evaluating content against policy rules before it reaches users.

How does the strike system and suspension workflow handle repeat policy violations?▼

The strike system handles repeat policy violations by tracking them via Redis-backed state management. It applies tier-aware enforcement that accumulates strikes, ultimately triggering automated suspension workflows to revoke publishing access.

Can I use Gemini for content moderation and auditing in my publishing platform?▼

Yes, you can use Gemini for content moderation by integrating it as the evaluation engine within a media server proxy. This setup processes image and text pipelines while generating real-time auditing logs for policy enforcement.

What is a circuit breaker in content moderation and when does fail-closed error handling activate?▼

A circuit breaker in content moderation prevents system overload by halting evaluation during critical failures. Fail-closed error handling activates during these circuit breaks or processing errors, automatically blocking content to ensure platform safety.

How do I track real-time auditing and moderation state with Redis?▼

You track real-time auditing and moderation state with Redis by using it as the backing data store for strike tracking and enforcement logic. This ensures auditable, persistent records of ALLOW/BLOCK verdicts and user suspensions across the platform.