im-not-ai
AI가 쓴 한글을 사람 글처럼 윤문하는 Claude 스킬 — Korean AI-text humanizer: detects and rewrites translationese, mechanical parallelism, and 71 other AI tells
- 6.7k
- Python
- MIT
- 4 d ago
AI가 쓴 한글을 사람 글처럼 윤문하는 Claude 스킬 — Korean AI-text humanizer: detects and rewrites translationese, mechanical parallelism, and 71 other AI tells
Open-source browser extension that flags AI-generated images and video as you browse. Runs entirely on your device. Chrome, Edge and Firefox.
Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserves code/URLs/headings. Plugin for Claude Code, Cursor, Windsurf, Codex, Cline, Copilot, Gemini.
DeepSeek 蓝色大肥鱼消除计划:识别并清理 B 站(Bilibili)评论区中由 DeepSeek 大模型、AI Agent 驱动的机器人账号(大肥鱼)的 Chrome / Edge / Firefox 浏览器插件。离线规则 + DeepSeek API 精判,AI 评论检测、空间主页鉴定、鲸鱼娘一键清场。DeepSeek AI bot detector for Bilibili comments.
A humanizer for work writing: takes the AI tone out without changing what your text says or commits to. Agent Skill + evidence: blind judges, hand-checked meaning changes, Pangram.
Stop shipping AI slop. Detects empty functions, fake documentation, and inflated comments in AI-generated code. Production-ready.
Transform AI text to natural, human-like writing
Runs in the browser on Hugging Face
A linter for the mistakes AI coding tools leave in TypeScript and JavaScript: imports that don’t exist, missing packages, placeholder code, swallowed errors and unsafe casts.
Find and remove AI provenance signals from files you own: hidden Unicode, token watermarks, visible image marks, and C2PA/EXIF/XMP metadata. Zero-dependency Python 3.10+ core; models, GPUs, and system binaries sit behind opt-in adapters.
中文 AI 文本去痕迹 + Claude 水印检查 — 六段式改写;零宽字符、同形字清干净,SynthID 采样水印只量残留、不声称能删。纯 Python 本地跑,零 LLM 零 API Key。Chinese AI-text humanizer & Claude / SynthID watermark inspector, fully offline, zero-dependency.
Free, local-first academic integrity checker and MCP server: citation hallucination detection, AI-text and plagiarism signals, venue guideline checks (IEEE, ACM, Elsevier). Documents never leave your machine.
4-pass AI text humanizer + voice agent humanization engine. 30 severity-ranked patterns, statistical fingerprint manipulation, SSML disfluency patterns, retail API enrichment for personalized calls, 6 voice modes. Free Claude Code skill — replaces $10-20/mo paid humanizers.
Strip AI writing patterns from any text. Claude Code skill with 507-entry banned word list, structural pattern detection, and 12-check validation.
Local AI text humanizer for Spanish & English, built on controlled experiments: a base model without chat training rewrites, a fidelity guard keeps every concept and quote, the rhythm is rebuilt, and flagged paragraphs are re-sampled and selected. 0% in Grammarly, ZeroGPT and GPTZero. No API · Humanizador IA local.
Open-source academic writing integrity toolkit: AI detection, plagiarism, grammar, IEEE/Elsevier/ACM/IET/BCS style checking
Static analysis binary for agent-sh ecosystem - git history, AST mapping, collectors
Claude Code plugin that audits a GitHub profile through its author's intent: README review, AI-marker detection, recruiter signals, keyword and SEO advice. From The Product Crew (TPC) GitHub Roast live.
Sound like you, not AI — feed it one sample of your writing and get a Claude Code skill that rewrites any text in your own voice. Korean & English.
ArtifactBench — a reproducible, lineage-aware benchmark for AI-generated music detection. v2 frozen protocol (arXiv:2609.23550), plus the v1.1 8-way public model comparison.
A Claude Code skill that removes the signs of AI-generated writing. Layered rule set plus a dependency-free scoring battery. Honest about what it can't do.
Detector de textos generados por IA y de copias entre entregas (Jupyter, PDF, DOCX, MD, TXT) con reporte CSV · AI-text and similarity detection for student submissions
Real-time AI / solicitation / parrot-bot scores for X posts and replies. Chrome extension + Workers API on open-compute, judged by TypeSafe Jev.
Detector-guided humanizer skill for Claude Code: lower the AI-detection score of English text while preserving every key term, number, citation, and the original logic. Keyless, agent-as-rewriter.
Local, full-logit AI text forensics and humanization toolkit. It scores markdown with observer/performer llama.cpp models (logPPL, logXPPL, B), surfaces chunk-aware hotspots and heatmaps, ranks rewrites, and ships CLI, desktop UI, Obsidian plugin, VS Code extension, and HTTP API (dev-grade) server with GUI test/demo harness.
Multi-generator AI image provenance detection - identifies Stable Diffusion, Midjourney, DALL·E 3, Flux or real photographs with calibrated confidence, Grad-CAM and async batch serving.
Remove AI-generated writing patterns. Detects and fixes 24 common AI tells based on Wikipedia's guide.
12 texts through 6 detectors, one table
Runs in the browser on Hugging Face
Code fingerprinting engine. Detect AI-generated code, find stolen code, catch license violations, trace code lineage.
Detect AI-generated slop on the web — heuristic scoring for em-dash overuse, hedge phrases, listicle structure, generic openings, and missing authorship.
Raycast extension that checks selected text for AI-generated content with Pangram, segment by segment