ai-writing plugins

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

Browse within: chinese-novel 14creative-writing 14claude-code-plugin 10claude-skill 9ai-detection 8humanizer 6

thoth

25

NirvanaGuha/thoth

Plugin Claude Code

Bundles 1 skill · 211 tokens together

Build a unique, consistent LinkedIn voice. Framework-driven persona interview, then daily post generation on a 30/25/20/15/10 content mix.

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

humanizer-ko

26

IsaacEryn/humanizer-ko

Plugin Claude Code

Bundles 1 skill · 127 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 3 +1 18d ago A tokens not measured original MIT

professional-skills

27

Kaos599/professional-skills

Plugin Claude Code

Bundles 2 skills · 187 tokens together

Professional writing skills for AI coding agents: anti-slop editing that makes drafts sound human, and technical content writing with runtime voice calibration.

not rated 3 +1 11d ago A tokens not measured original MIT

novel-craft

28

chaserr/novel-craft

Plugin Claude Code

Bundles 5 skills, 12 agents · 1,270 tokens together

A project workflow for writing and reviewing long novels in different genres, from setup and chapter drafting to revision and multi-role review. It uses a project-level RTK.md file to set the story’s tone.

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

humanizer-ms

29

edwardxckf/humanizer-ms

Plugin Claude Code

Bundles 1 skill · 150 tokens together

Remove signs of AI-generated writing from Malay (Bahasa Melayu) text: karangan clichés, AI vocabulary, inflated significance, promotional language, em dashes, and more, with a natural rewrite for each.

not rated 2 17d ago A tokens not measured original MIT

de-slop

30

isatimur/de-slop

Plugin Claude Code

Bundles 1 skill · 149 tokens together

Removes AI-slop from prose (empty hedging, listicle stems, smooth transitions, generic filler) and rewrites toward a real point of view — without trading AI-slop for louder slop. Self-scores against an embedded rubric, flags hollow spans instead of fabricating, and reports rather than overwrites. Portable to every AI…

not rated 2 1mo ago A tokens not measured original MIT

sodam-prompt

31

sodam-ai/SoDam-Prompt-Eng

Plugin Claude Code

Bundles 11 skills, 11 commands · 1,198 tokens together

A Claude Code plugin containing ten Korean-language writing skills for beginners. It supports both slash commands and ordinary natural-language requests for tasks such as summaries, messages, study plans, introductions, captions, translations, and speeches.

not rated 2 1mo ago A tokens not measured original Apache-2.0

anti-ai-tell

32

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 2 4d ago A tokens not measured original MIT

alchemy

34

fernforge/alchemy

Plugin Claude Code

Bundles 1 skill · 56 tokens together

Makes the agent write human-quality prose (no LLM tells) whenever it writes docs, READMEs, commits, comments, or replies. Ships the Alchemy ruleset as a skill.

not rated 1 2mo ago A tokens not measured original MIT

declaude

35

tenkenco/declaude

Plugin Claude Code

Bundles 2 skills, 1 hook, 1 MCP server · 98 tokens together

Rewrites Claude-English into plain English: sycophantic openers, hedging filler and padded phrasing out, facts, code blocks, names and numbers untouched. Runs an open-weights model on dedicated GPUs, so text never reaches a commercial AI provider.

not rated 1 5d ago A tokens not measured original MIT

baihua

36

F2077/baihua

Plugin Claude Code

Bundles 1 hook

A Chinese-language plugin focused on making conversations, commits, pull requests, documents, and comments sound more natural and less machine-written. It is described as leaving code logic unchanged and being enabled by default.

not rated 1 2mo ago A tokens not measured original MIT

story

38

zenstory-ai/oh-story-claudecode

Plugin Claude Code

网络小说工具箱主入口。自动路由扫榜、拆文与写作工具,并可通过 /story dashboard 启动本地写作工作台。.

not rated 6.5k yesterday A tokens not measured MIT

story-long-scan

39

zenstory-ai/oh-story-claudecode

Plugin Claude Code

长篇网文扫榜。分析起点、番茄、晋江等平台排行榜数据,提炼市场趋势与热门题材。.

not rated 6.5k yesterday A tokens not measured MIT

story-long-analyze

40

zenstory-ai/oh-story-claudecode

Plugin Claude Code

长篇网文拆文。深度拆解爆款长篇小说的黄金三章、人设架构、爽点设计、节奏控制。.

not rated 6.5k yesterday A tokens not measured MIT

md2wechat

41

geekjourneyx/md2wechat-skill

Plugin Claude Code

Convert Markdown articles to WeChat Official Account HTML, diagnose local readiness, discover and validate advanced layouts, generate previews, and optionally upload drafts.

not rated 3.6k 3d ago A tokens not measured

humanizer

42

codingrajan/humanizer-skills

Plugin Claude Code

Remove AI writing tells from general prose. Cuts em dashes, rule-of-three, significance inflation, and AI vocabulary while preserving voice.

not rated 1 2mo ago A tokens not measured

academic-humanizer

43

codingrajan/humanizer-skills

Plugin Claude Code

De-AI scholarly writing while keeping formal register, warranted hedging, and methods-section passive voice. Never fabricates citations.

not rated 1 2mo ago A tokens not measured

legal-humanizer

44

codingrajan/humanizer-skills

Plugin Claude Code

De-AI legal and professional drafting. Preserves defined terms, enumerations, and shall/may/must; flags substance rather than editing it.

not rated 1 2mo ago A tokens not measured

human-tone

45

tanawitchsaentree/Human-tone

Plugin Claude Code

Makes AI writing sound like a person wrote it, in any language. Bans em dashes, negation scaffolding, label colons, rule-of-three lists, AI vocabulary and bow-tie endings, with a deterministic linter as the delivery gate. Also audits text you did not write: scores it 0-100 on how human it reads, names which patterns…

not rated 1 27d ago A tokens not measured MIT

signs-of-ai

47

peopleworks/SignsofAI

Plugin Claude Code

Examine writing for the signs of AI, compare documents, and produce evidence a person can act on — never a verdict about who wrote it.

not rated 20 2d ago A tokens not measured MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: