content-filter

Community

Keep every auto-post safe and compliant

Authorbuzzbysolcex
Version1.0.0
Installs0

System Documentation

What problem does it solve?

The content-filter prevents an autonomous account from posting tweets that include unsafe, prohibited, or policy-violating language by rejecting content before it is published.

Core Features & Use Cases

  • Blocked Words Enforcement: Detects and blocks predefined high-risk terms and phrases related to financial promises, profanity, and misleading claims.
  • Blocked Patterns Detection: Rejects content that matches patterns for price predictions, financial advice, urgency/scarcity language, comparison attacks, AI/bot self-identification, and commission/pricing disclosures.
  • Operational Posting Guardrails: Applies the filter across all auto-posts (summaries, deploy confirms, engage actions, threads, digests) while excluding drafts that are queued for manual Ogie approval.

Quick Start

Use the content-filter to check a candidate tweet text and only publish it if it passes all blocked word and pattern checks.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: content-filter
Download link: https://github.com/buzzbysolcex/buzz-bd-agent/archive/main.zip#content-filter

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.