Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

glin-profanity

bởi thegdsks

Security & Passwords
1.5kLượt tải do clawskills.sh công bố
1Sao
1Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Profanity detection and content moderation library.

Mô tả

Kỹ năng này làm gì

Profanity detection library for JavaScript, TypeScript, and Python that handles evasion techniques like leetspeak, Unicode homoglyphs, and obfuscated text. Supports 24 languages with optional ML-powered toxicity scoring via TensorFlow.js. Includes context-aware analysis for domains like medical, gaming, and technical content.

Unlike simple word-list filters, it catches evasion attempts like leetspeak and Unicode lookalikes that users commonly exploit to bypass moderation.

Khi nào nên dùng

  • Filtering user comments on a forum before they go live
  • Blocking profane usernames during account registration
  • Moderating chat messages in a multiplayer game
  • Validating form submissions in a web app
  • Scanning batch-uploaded content for policy violations

Quy trình ví dụ

ĐẦU VÀO

User asks: Check if a chat message contains profanity before sending

AGENT
  1. 1

    Import Filter from glin-profanity

  2. 2

    Initialize filter with detectLeetspeak and normalizeUnicode enabled

  3. 3

    Call filter.checkProfanity() on the message text

  4. 4

    Inspect result.containsProfanity and result.profaneWords

  5. 5

    Block or replace the message using result.processedText if flagged

ĐẦU RA

Message is either sent as-is or replaced with a censored version, and the user is warned if violations are found

Cài đặt

clawhub install thegdsks/glin-profanity

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết