By devswha
Humanize AI-generated text across Korean, English, Chinese, and Japanese by detecting AI writing patterns, rewriting to sound human, and auditing for meaning preservation and residual AI tells.
Triggers when Claude needs to find AI-writing patterns or suspect zones in KO/EN/ZH/JA text. Use this agent to run a full detection pass — pattern scanning across all applicable packs, stylometric analysis (burstiness CV + MATTR + AI-lexicon density), and Korean diagnostic signals — and receive a structured span/paragraph-level findings report before any rewrite begins.
Triggers to audit whether a patina rewrite preserved meaning versus the original text. Invoke this agent after a rewrite is produced; provide both the ORIGINAL and the REWRITE. It checks all four fidelity criteria from core/scoring.md §§9-14 (claims, fabrication, tone, length) and returns a pass/needs-rollback verdict with offending spans identified.
Triggers to re-scan a patina rewrite for residual AI tells and over-editing risk. Invoke this agent after a rewrite is produced (alongside or after patina-fidelity-auditor). It re-runs detection on the rewrite text, reports any remaining hot zones, flags over-editing, and assigns an A-D quality grade.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub devswha/patina --plugin patinaAI가 쓴 한글 텍스트를 사람이 쓴 글처럼 윤문 — Fast(monolith) + strict 5인 파이프라인. 10대 카테고리 40+ AI 티 패턴 탐지·재작성.
Audit & rewrite content to remove AI writing patterns ("AI-isms"). Supports detect-only and edit-in-place modes, voice profiles, and iterate-to-convergence.
Deutsche KI-Schreibmuster erkennen und entfernen. 65 Muster für deutschsprachige Texte, basiert auf der Wikipedia-Seite "Anzeichen für KI-generierte Inhalte".
Kills AI smell in Russian text. 52 patterns across 12 categories, 20 hard bans, 3 modes (rewrite / audit / targeted fix), voice calibration, quad-pass audit, 2025-2026 stylistic fingerprints. | Убивает запах нейросети в русском тексте. 52 паттерна в 12 категориях, 20 жёстких банов, 3 режима, калибровка голоса, quad-pass аудит, стилистические фингерпринты 2025-2026.
去除文章中的 AI 寫作痕跡,使文字更自然、更有人味。以台灣正體中文為主。
Detects 43 AI writing patterns and rewrites text with burstiness, voice profiles, and a 0-100 AI-tell score. Pure Markdown, zero dependencies, no network calls.