skills.rest
buzzbysolcex
buzzbysolcexCOMMUNITY
Explore all skills by this author →
Website𝕏@BuzzBySolCexGitHub

content-filter

Filters outbound Buzz auto-posts by rejecting blocked words and patterns before publishing.

5|2|Updated Feb 6, 2026
Search Tags:#pattern detection#content moderation#financial compliance#twitter auto-posting#blocked words#safety logging#social media governance
One-click install
npx skills add https://github.com/buzzbysolcex/buzz-bd-agent --skill content-filter
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: content-filter
Source: https://github.com/buzzbysolcex/buzz-bd-agent/tree/main/skills/content-filter
Command: npx skills add https://github.com/buzzbysolcex/buzz-bd-agent --skill content-filter

SYSTEM DOCUMENTATION & REQUIREMENTS

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.

Frequently Asked Questions about content-filter

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

FAQPage Schema
How do I filter outbound tweets for blocked words and non-compliant patterns?▼

To filter outbound tweets, scan candidate text for predefined blocked words and blocked patterns, rejecting any content that matches before publishing to ensure social media governance and compliance.

What is content moderation for automated Twitter auto-posting?▼

Content moderation for automated Twitter auto-posting is the process of scanning generated tweet artifacts like summaries and threads to detect and reject unsafe financial claims, profanity, or misleading language before publication.

Does the content filter apply to all auto-posted tweets and threads?▼

Yes, the content filter applies to all auto-posts including summaries, deploy confirmations, engagement replies, threads, and digests, but it excludes drafts queued for manual approval.

How do I block financial advice and price predictions in social media governance?▼

Block financial advice and price predictions by enforcing blocked patterns detection to reject tweets containing urgency language, comparison attacks, or prohibited financial promises prior to publishing.

Can I log blocked tweet attempts to Telegram for safety logging?▼

Yes, when a tweet is rejected for matching a blocked word or pattern, the attempt is logged to Telegram with the matched term and the specific reason for the block.

What types of blocked patterns are detected for financial compliance on Twitter?▼

Detected blocked patterns for financial compliance include price predictions, financial advice, urgency or scarcity language, comparison attacks, AI self-identification, and commission or pricing disclosures.

Related Skills

Explore More Legal & Compliance Skills→
gauravprwl14gauravprwl14

tweet-generator

Generate 3-5 tweet threads from ideas.md with hooks and CTAs.

Community
Intermediate
avansaberavansaber
5

erpclaw-alerts

Configure ERPClaw notification triggers and channels for event-based messaging.

Official
Advanced
ZhanlinCuiZhanlinCui
178

x-article-publisher

Convert Markdown to rich text and publish drafts to X Articles via clipboard paste.

Community
Advanced
vikingokftvikingokft

gws-modelarmor

Filter user-generated text and media against configurable safety policies.

Official
Advanced