ai-detection plugins

21 tagged ai-detection, measured the same way as everything else here.

Browse within: ai-writing 7claude-skill 7humanizer 6claude-code-plugin 5

humanize-korean

01

epoko77-ai/im-not-ai

Plugin Claude Code

Bundles 5 skills, 9 agents · 2,073 tokens together

A Korean-language text editor that detects patterns commonly associated with AI-written or translation-like writing and rewrites them to sound more human.

not rated 6.3k +168 changed 1mo ago A tokens not measured original MIT

humanize

02

harshaneel/humanize

Plugin Claude Code

Bundles 2 skills · 195 tokens together

Strip AI tells from text, and score text for the tells it still has.

not rated 577 +16 1mo ago A tokens not measured original MIT

humanizer-ru

03

ilyautov/humanizer-ru

Plugin Gemini CLI

A Russian-language editing plugin that checks text for patterns associated with machine-generated writing and applies a chosen voice.

not rated 489 +20 changed 6d ago A tokens not measured original MIT

patina

04

devswha/patina

Plugin Claude Code

Bundles 1 skill, 3 agents · 275 tokens together

Detect and rewrite AI writing patterns in Korean, English, Chinese, and Japanese so text reads as if a human wrote it. Meaning-preservation (MPS) verified, audit-friendly. The root SKILL.md is loaded as the /patina skill.

not rated 379 +4 changed 29d ago A tokens not measured original MIT

humanizer

05

Aboudjem/humanizer-skill

Plugin Claude Code

Bundles 1 skill · 139 tokens together

Detects 55 AI writing patterns and rewrites text in five voice profiles so it reads like a specific human wrote it, with an optional 0-100 AI-tell score. Use when text sounds AI-generated or like a chatbot, when preparing a blog post, README, or LinkedIn post for publication, when auditing prose for AI tells, or when…

not rated 290 +7 changed 1mo ago A tokens not measured original MIT

unslop

06

MohamedAbdallah-14/unslop

Plugin Claude Code

Bundles 6 skills · 675 tokens together

Make assistant output sound human. Strip AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), engineer burstiness, restore voice. Preserves code, URLs, and technical accuracy.

not rated 163 +2 7d ago A tokens not measured original MIT

slopornot

07

numen-tech/slopornot

Plugin Claude Code

Bundles 1 skill · 147 tokens together

Slop or Not tools for AI humanization, voice matching, local AI text detection, AI image detection, readability analysis, and Text Cleanup for Claude, Codex, Hermes Agent, and OpenClaw.

not rated 56 +3 3mo ago A tokens not measured original MIT

signs-of-ai

08

peopleworks/SignsofAI

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 181 tokens together

Measure a text for the signs of AI writing and read back the evidence — offline, EN/ES, with the tool's own false-positive rate attached.

not rated 28 +1 changed 1mo ago A tokens not measured original MIT

untell

09

ssamba1/untell

Plugin Claude Code

Bundles 1 skill · 135 tokens together

Humanize AI-generated text via a closed-loop, detector-feedback rewrite. Optimizes against GPTZero, ZeroGPT, Originality.ai and other Turnitin-class checkers while preserving meaning, citations and facts. Research/defensive tool.

not rated 24 3d ago A tokens not measured original MIT

humanizer-zh-tw

11

nagameTW/humanizer-zh-tw

Plugin Claude Code

Bundles 1 skill · 183 tokens together

A Claude Code plugin for making Traditional Chinese writing sound more natural and less machine-generated.

not rated 8 3mo ago A tokens not measured original MIT

humanizer-ko

13

IsaacEryn/humanizer-ko

Plugin Claude Code

Bundles 1 skill · 179 tokens together

A Korean-language editing tool that finds writing patterns associated with AI-generated text and rewrites the prose to sound more natural.

not rated 6 +1 changed 4d ago A tokens not measured original MIT

anti-ai-tell

14

MikkoParkkola/anti-ai-tell

Plugin Claude Code

Bundles 1 skill, 2 commands, 3 hooks · 215 tokens together

Cross-media discipline so prose AND design don't read as AI-generated. Generation-time rules, a mechanical linter for prose + visual tells, a style fingerprint that injects a chosen point of view, a population-level sameness detector, and hooks that lint-on-write and ask for a style anchor when one is missing.

not rated 6 24d ago A tokens not measured original MIT

ai-humanizer

16

ofershap/ai-humanizer

Plugin Claude Code

Bundles 1 skill, 1 command · 49 tokens together

Make AI-generated content undetectable. Rules that prevent em dashes, buzzwords, over-formatting, narrating comments, git co-author trailers, and uniform sentence structure.

not rated 5 8mo ago A tokens not measured original MIT

ai-pattern-detector

17

ananas-agency/ai-pattern-detector

Plugin Claude Code

Bundles 1 skill · 83 tokens together

Scan text for telltale AI-writing patterns (vocabulary, constructions, punctuation, hedges, closers, formatting, voice) and propose specific rewrites to make it sound human.

not rated 4 3mo ago A tokens not measured original MIT

ghostwriter

18

an2n/ghostwriter

Plugin Claude Code

Bundles 3 skills · 276 tokens together

Writes and rewrites text in your own voice instead of generic AI prose, with a check and polish pass built in.

not rated 0 2mo ago A tokens not measured original MIT