ai-writing plugins

47 tagged ai-writing, measured the same way as everything else here.

Browse within: claude-skill 9claude-code-plugin 8ai-detection 7cursor 7

humanizer

01

blader/humanizer

Plugin Claude Code

Bundles 1 skill · 81 tokens together

Rewrite AI-sounding text so it reads like the writer without changing what it says.

5 · 1 57k +2.1k changed 17d ago A tokens not measured original MIT

webnovel-writer

03

lingfengQAQ/webnovel-writer

Plugin Claude Code

Bundles 8 skills, 4 agents, 2 hooks · 366 tokens together

A long-form web-novel writing system made of reusable instructions, helper agents, linked data, and retrieval tools. Retrieval means finding relevant stored material while writing.

not rated 7.5k +106 yesterday A tokens not measured GPL-3.0

sepia

04

Nanako0129/sepia

Plugin Claude Code

Bundles 6 skills · 276 tokens together

De-AI writing package with the general Sepia router plus five separate operation entries: write, review, refactor, recreate, and hemingway.

not rated 3.2k +127 changed today A tokens not measured original MIT

shuorenhua

05

MrGeDiao/shuorenhua

Plugin Claude Code

Bundles 1 skill · 34 tokens together

A Chinese-language writing editor that removes common signs of machine-written prose while preserving facts, versions, commands, and responsibility.

not rated 2.1k +84 changed 15d ago A tokens not measured original MIT

patina

07

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 375 +10 changed 19d ago A tokens not measured original MIT

humanizer

08

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 281 +16 changed 1mo ago A tokens not measured original MIT

humanizer-de

09

marmbiz/humanizer-de

Plugin Claude Code

Bundles 1 skill · 54 tokens together

Deutscher Stil-Editor für Claude Code/Codex: misst Register und Rhythmus, redigiert proportional auf ein Zielprofil, gleicht erkennbare Faktenanker konservativ ab und auditiert/entfernt KI-Schreibmuster. German AI Text Humanizer / deutscher Humanizer Skill. Supports Claude Code and Codex. 72 Muster in 10 Kategorien…

not rated 176 +5 changed 12d ago A tokens not measured

slopgent

10

ehmo/slopkit

Plugin Claude Code

Bundles 1 skill · 81 tokens together

Shape the agent's own replies so they are honest about what ran, action-first, and plain — without dropping load-bearing precision.

not rated 109 +3 2mo ago A tokens not measured original MIT

openwriter

12

travsteward/openwriter

Plugin Claude Code

Bundles 1 skill, 2 agents, 1 MCP server · 294 tokens together

A local markdown editor your agent writes in. Claude drafts and edits documents through MCP tools, and you accept or reject each change in your browser. Plain .md files on your disk.

not rated 35 +3 changed yesterday A tokens not measured original MIT

xiaomoBoy/claude-writing-skills

Plugin Claude Code

Bundles 5 skills · 379 tokens together

Claude Code skills for long-form content workflow: research collection via NotebookLM, multi-platform publishing via wechatsync, viral-score evaluation, single-article rewrite loops, and yt-dlp media helpers.

not rated 34 4mo ago A tokens not measured original MIT

insanca

15

tahiryildiz/insanca

Plugin Claude Code

Bundles 1 skill · 221 tokens together

Türkçe metinlerdeki yapay zeka yazım izlerini temizler; metni doğal, akıcı, insan elinden çıkmış gibi okunan Türkçeye çevirir.

not rated 28 2mo ago A tokens not measured original MIT

writing-humanizer

16

shyuan/writing-humanizer

Plugin Claude Code

Bundles 1 skill · 92 tokens together

A writing tool that removes common signs of AI-generated text and makes prose sound more natural, mainly in Traditional Chinese used in Taiwan.

not rated 27 3mo ago A tokens not measured original MIT

signs-of-ai

17

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 27 changed 29d ago A tokens not measured original MIT

humanizer-kr

20

hjongc/humanizer-kr

Plugin Claude Code

Bundles 1 skill · 85 tokens together

Korean-specialized writing skill for rewriting AI-sounding Korean into natural, source-grounded Korean.

not rated 17 +2 3mo ago A tokens not measured original MIT

humanize-pro

21

msdanyg/humanize-pro

Plugin Claude Code

Bundles 1 skill · 174 tokens together

Make AI-drafted text read like a person wrote it, for the channel it ships in. De-AI pass, channel fit, voice profiles, and a two-gate audit before delivery.

not rated 13 changed 1mo ago A tokens not measured original MIT

humanizer-fr

22

ferr079/humanizer-fr

Plugin Claude Code

Bundles 1 skill · 138 tokens together

Réécrit un texte français qui sonne IA pour qu'il se lise comme son auteur, sans changer ce qu'il dit.

not rated 10 +1 3d ago A tokens not measured original MIT

sansheng-write

23

sanshengai/sansheng-write

Plugin Claude Code

Bundles 1 skill · 141 tokens together

A Chinese long-form writing engine for Claude Code: topic to outline to draft to revision to typeset HTML to cover art. Bring your own corpus, it learns your voice.

not rated 7 changed today A tokens not measured original MIT

anti-ai-tell

24

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 13d ago A tokens not measured original MIT