Skip to content

Claude/cowork plugin conversion twf64 #36

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
teslaproduuction wants to merge 3 commits into
base: main
Choose a base branch
from
+848 −99
Open

Claude/cowork plugin conversion twf64 #36

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2dc46d1
Add Russian language adaptation for humanizer skill
claude Jan 23, 2026
d570b9d
Merge pull request #1 from teslaproduuction/claude/russian-language-a…
teslaproduuction Jan 23, 2026
328a137
Convert to Claude Desktop cowork plugin v3.0.0
claude Feb 14, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions .claude-plugin/plugin.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
{
"name": "humanizer",
"version": "3.0.0",
"description": "Remove signs of AI-generated writing from text. Supports English and Russian.",
"author": {
"name": "teslaproduuction",
"url": "https://github.com/teslaproduuction"
},
"repository": "https://github.com/teslaproduuction/humanizer_ru",
"license": "MIT",
"keywords": ["humanizer", "ai-writing", "text-editing", "russian", "канцелярит"]
}
109 changes: 55 additions & 54 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,52 +1,56 @@
# Humanizer

A Claude Code skill that removes signs of AI-generated writing from text, making it sound more natural and human.
A Claude Desktop plugin that removes signs of AI-generated writing from text, making it sound more natural and human. Supports English and Russian.

**[Russian version / Русская версия](README_RU.md)**

## Installation

### Recommended (clone directly into Claude Code skills directory)
### As a Claude Desktop plugin (recommended)

```bash
mkdir -p ~/.claude/skills
git clone https://github.com/blader/humanizer.git ~/.claude/skills/humanizer
claude plugin add github:teslaproduuction/humanizer_ru
```

### Manual install/update (only the skill file)

If you already have this repo cloned (or you downloaded `SKILL.md`), copy the skill file into Claude Code’s skills directory:
### Manual installation (legacy Claude Code skills)

```bash
mkdir -p ~/.claude/skills/humanizer
cp SKILL.md ~/.claude/skills/humanizer/
git clone https://github.com/teslaproduuction/humanizer_ru.git /tmp/humanizer_ru
cp /tmp/humanizer_ru/skills/humanizer/SKILL.md ~/.claude/skills/humanizer/
cp -r /tmp/humanizer_ru/skills/humanizer-ru ~/.claude/skills/
```

## Usage

In Claude Code, invoke the skill:
In Claude Desktop or Claude Code, invoke the commands:

```
/humanizer
/humanizer [paste your text here]
```

[paste your text here]
```
/humanizer-ru [вставьте ваш текст на русском]
```

Or ask Claude to humanize text directly:
Or ask Claude directly:

```
Please humanize this text: [your text]
Очеловечь этот текст: [ваш текст]
```

## Overview

Based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing) guide, maintained by WikiProject AI Cleanup. This comprehensive guide comes from observations of thousands of instances of AI-generated text.

### Key Insight from Wikipedia
### Key insight

> "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."

## 24 Patterns Detected (with Before/After Examples)
## 24 Patterns detected (English)

### Content Patterns
### Content patterns

| # | Pattern | Before | After |
|---|---------|--------|-------|
Expand All @@ -57,7 +61,7 @@ Based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikip
| 5 | **Vague attributions** | "Experts believe it plays a crucial role" | "according to a 2019 survey by..." |
| 6 | **Formulaic challenges** | "Despite challenges... continues to thrive" | Specific facts about actual challenges |

### Language Patterns
### Language patterns

| # | Pattern | Before | After |
|---|---------|--------|-------|
Expand All @@ -68,70 +72,67 @@ Based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikip
| 11 | **Synonym cycling** | "protagonist... main character... central figure... hero" | "protagonist" (repeat when clearest) |
| 12 | **False ranges** | "from the Big Bang to dark matter" | List topics directly |

### Style Patterns
### Style patterns

| # | Pattern | Before | After |
|---|---------|--------|-------|
| 13 | **Em dash overuse** | "institutions—not the people—yet this continues—" | Use commas or periods |
| 13 | **Em dash overuse** | "institutions--not the people--yet this continues--" | Use commas or periods |
| 14 | **Boldface overuse** | "**OKRs**, **KPIs**, **BMC**" | "OKRs, KPIs, BMC" |
| 15 | **Inline-header lists** | "**Performance:** Performance improved" | Convert to prose |
| 16 | **Title Case Headings** | "Strategic Negotiations And Partnerships" | "Strategic negotiations and partnerships" |
| 17 | **Emojis** | "🚀 Launch Phase: 💡 Key Insight:" | Remove emojis |
| 18 | **Curly quotes** | `said “the project”` | `said "the project"` |
| 17 | **Emojis** | "Launch Phase: Key Insight:" | Remove emojis |
| 18 | **Curly quotes** | `said \u201cthe project\u201d` | `said "the project"` |

### Communication Patterns
### Communication patterns

| # | Pattern | Before | After |
|---|---------|--------|-------|
| 19 | **Chatbot artifacts** | "I hope this helps! Let me know if..." | Remove entirely |
| 20 | **Cutoff disclaimers** | "While details are limited in available sources..." | Find sources or remove |
| 21 | **Sycophantic tone** | "Great question! You're absolutely right!" | Respond directly |

### Filler and Hedging
### Filler and hedging

| # | Pattern | Before | After |
|---|---------|--------|-------|
| 22 | **Filler phrases** | "In order to", "Due to the fact that" | "To", "Because" |
| 23 | **Excessive hedging** | "could potentially possibly" | "may" |
| 24 | **Generic conclusions** | "The future looks bright" | Specific plans or facts |

## Full Example

**Before (AI-sounding):**
> Great question! Here is an essay on this topic. I hope this helps!
>
> AI-assisted coding serves as an enduring testament to the transformative potential of large language models, marking a pivotal moment in the evolution of software development. In today's rapidly evolving technological landscape, these groundbreaking tools—nestled at the intersection of research and practice—are reshaping how engineers ideate, iterate, and deliver, underscoring their vital role in modern workflows.
>
> At its core, the value proposition is clear: streamlining processes, enhancing collaboration, and fostering alignment. It's not just about autocomplete; it's about unlocking creativity at scale, ensuring that organizations can remain agile while delivering seamless, intuitive, and powerful experiences to users. The tool serves as a catalyst. The assistant functions as a partner. The system stands as a foundation for innovation.
>
> Industry observers have noted that adoption has accelerated from hobbyist experiments to enterprise-wide rollouts, from solo developers to cross-functional teams. The technology has been featured in The New York Times, Wired, and The Verge. Additionally, the ability to generate documentation, tests, and refactors showcases how AI can contribute to better outcomes, highlighting the intricate interplay between automation and human judgment.
>
> - 💡 **Speed:** Code generation is significantly faster, reducing friction and empowering developers.
> - 🚀 **Quality:** Output quality has been enhanced through improved training, contributing to higher standards.
> - ✅ **Adoption:** Usage continues to grow, reflecting broader industry trends.
>
> While specific details are limited based on available information, it could potentially be argued that these tools might have some positive effect. Despite challenges typical of emerging technologies—including hallucinations, bias, and accountability—the ecosystem continues to thrive. In order to fully realize this potential, teams must align with best practices.
>
> In conclusion, the future looks bright. Exciting times lie ahead as we continue this journey toward excellence. Let me know if you’d like me to expand on any section!

**After (Humanized):**
> AI coding assistants speed up some tasks. In a 2024 study by Google, developers using Codex completed simple functions 55% faster than a control group, but showed no improvement on debugging or architectural decisions.
>
> The tools are good at boilerplate: config files, test scaffolding, repetitive refactors. They are bad at knowing when they are wrong. I have mass-accepted suggestions that compiled, passed lint, and still did the wrong thing because I stopped paying attention.
>
> Mira, an engineer at a fintech startup I interviewed, said she uses Copilot "like autocomplete for boring code" but reviews every line before committing. Jake, a senior dev at a larger company, disabled it after it kept suggesting patterns from a deprecated internal library.
>
> The productivity claims are hard to verify. GitHub says Copilot users "accept 30% of suggestions," but acceptance is not correctness, and correctness is not value. The 2024 Uplevel study found no statistically significant difference in pull-request throughput between teams with and without AI assistants.
>
> None of this means the tools are useless. It means they are tools. They do not replace judgment, and they do not eliminate the need for tests. If you do not have tests, you cannot tell whether the suggestion is right.
## Russian language support (25 patterns)

The Russian skill includes all patterns above adapted for Russian, plus unique patterns:

- **Verbal nouns** - the primary marker of AI text in Russian
- **Bureaucratic cliches** - "in the present time", "within the framework of"
- **Genitive case chains** - uniquely Russian readability problem
- **Passive constructions** - hiding the actor
- **Unnecessary foreign words** - borrowings where Russian alternatives exist
- **Template transitions** - "It is important to note that..."
- **Hard prohibitions** - automatic rejection of negative parallelisms, long dashes, rhetorical questions

See [full Russian documentation](README_RU.md)

## Plugin structure

```
.claude-plugin/plugin.json Plugin manifest
skills/humanizer/SKILL.md English skill (24 patterns)
skills/humanizer-ru/SKILL.md Russian skill (25 patterns)
commands/humanizer.md /humanizer slash command
commands/humanizer-ru.md /humanizer-ru slash command
```

## References

- [Wikipedia: Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing) - Primary source
- [WikiProject AI Cleanup](https://en.wikipedia.org/wiki/Wikipedia:WikiProject_AI_Cleanup) - Maintaining organization
- [Wikipedia: Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing)
- [WikiProject AI Cleanup](https://en.wikipedia.org/wiki/Wikipedia:WikiProject_AI_Cleanup)
- [smixs/humanizer-ru](https://github.com/smixs/humanizer-ru) - additional Russian patterns
- [blader/humanizer](https://github.com/blader/humanizer) - original project

## Version History
## Version history

- **3.0.0** - Converted to Claude Desktop cowork plugin, incorporated improvements from smixs/humanizer-ru (genitive chains, passive voice, foreign words, template transitions, hard prohibitions, style rules)
- **2.1.1** - Fixed pattern #18 example (curly quotes vs straight quotes)
- **2.1.0** - Added before/after examples for all 24 patterns
- **2.0.0** - Complete rewrite based on raw Wikipedia article content
Expand Down
142 changes: 142 additions & 0 deletions README_RU.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,142 @@
# Humanizer RU

Плагин для Claude Desktop, который удаляет признаки AI-генерации, канцелярит и воду из текста на русском и английском языках.

## Установка

### Как плагин Claude Desktop (рекомендуется)

```bash
claude plugin add github:teslaproduuction/humanizer_ru
```

### Ручная установка (legacy Claude Code skills)

```bash
mkdir -p ~/.claude/skills/humanizer-ru
git clone https://github.com/teslaproduuction/humanizer_ru.git /tmp/humanizer_ru
cp /tmp/humanizer_ru/skills/humanizer-ru/SKILL.md ~/.claude/skills/humanizer-ru/
```

## Использование

В Claude Desktop или Claude Code:

```
/humanizer-ru [вставьте ваш текст]
```

Или просто попросите:

```
Очеловечь этот текст: [ваш текст]
Убери воду: [ваш текст]
Сделай живым: [ваш текст]
```

## Обзор

Основано на [Wikipedia: Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing) и исследованиях русскоязычных признаков AI-текста.

### Ключевая идея

> "LLM используют статистические алгоритмы, чтобы угадать, что должно быть следующим. Результат стремится к наиболее статистически вероятному результату."

## 25 паттернов AI-текста на русском

### Канцелярит (1-6)

| # | Паттерн | До | После |
|---|---------|-----|-------|
| 1 | **Отглагольные существительные** | "осуществлять внедрение" | "внедрить" |
| 2 | **Канцелярские клише** | "в настоящее время в рамках проекта" | "сейчас проект" |
| 3 | **Цепочки родительных падежей** | "процесс развития движения за укрепление..." | "сотрудничество развивается" |
| 4 | **Copula Avoidance** | "является, представляет собой" | "это, есть" |
| 5 | **Пассивные конструкции** | "решение было принято руководством" | "руководство решило" |
| 6 | **Ненужные заимствования** | "имплементировать, фидбек" | "внедрить, отзыв" |

### AI-словарь и раздувание (7-13)

| # | Паттерн | До | После |
|---|---------|-----|-------|
| 7 | **Перегруженные слова** | "ключевой, демонстрирует, способствует" | Убрать или упростить |
| 8 | **Раздувание значимости** | "ознаменовав поворотный момент" | Конкретные факты |
| 9 | **Причастные обороты** | "символизируя... отражая... демонстрируя..." | Убрать или расшифровать |
| 10 | **Рекламный язык** | "расположенный в захватывающем дух регионе" | "город в регионе Гондэр" |
| 11 | **Weasel Words** | "по мнению экспертов" | "по данным исследования [источник]" |
| 12 | **Шаблонные переходы** | "важно отметить, что..." | Сказать прямо |
| 13 | **Формульные вызовы** | "несмотря на вызовы... продолжает процветать" | Конкретные проблемы и факты |

### Структурные (14-17)

| # | Паттерн | До | После |
|---|---------|-----|-------|
| 14 | **Негативные параллелизмы** | "не просто X, а Y" | Сказать суть напрямую |
| 15 | **Правило трёх** | "инновации, вдохновение и инсайты" | Естественное число элементов |
| 16 | **Synonym Cycling** | "протагонист... главный герой... центральная фигура" | Одно слово |
| 17 | **Ложные диапазоны** | "от анализа до планирования, от маркетинга до продаж" | Перечислить |

### Стиль (18-20)

| # | Паттерн | До | После |
|---|---------|-----|-------|
| 18 | **Злоупотребление тире** | "институтами - не людьми - однако -" | Запятые или точки |
| 19 | **Жирный + эмодзи + списки** | "**Скорость:** Скорость выше" | Проза без украшений |
| 20 | **Кавычки** | "сказал \"проект\"" | "сказал «проект»" |

### Тон и коммуникация (21-22)

| # | Паттерн | До | После |
|---|---------|-----|-------|
| 21 | **Подобострастный тон** | "Отличный вопрос! Вы правы!" | Ответить напрямую |
| 22 | **Артефакты чатбота** | "Надеюсь, поможет! Дайте знать!" | Удалить |

### Вода и хеджирование (23-25)

| # | Паттерн | До | После |
|---|---------|-----|-------|
| 23 | **Водянистые фразы** | "для того чтобы", "в связи с тем что" | "чтобы", "потому что" |
| 24 | **Хеджирование** | "можно предположить, что возможно" | "может" |
| 25 | **Общие заключения** | "будущее выглядит ярким" | Конкретные планы |

## Жёсткие запреты

Автоматически отклоняются:
- "не просто X, а Y" / "не только X, но и Y"
- длинное тире "-" (только короткое "-")
- риторические вопросы
- излишняя академичность

## Пример

**До:**
> Важно отметить, что в современном мире цифровая трансформация представляет собой ключевой фактор развития бизнеса. Наша компания является лидером рынка и осуществляет предоставление высококачественных услуг. Надеемся, данная информация была полезной!

**После:**
> Мы автоматизируем бизнес-процессы. За 2025 год внедрили CRM в 40 компаний - в среднем это сократило время на рутину на 30%. Клиенты возвращаются: 70% заказывают повторно.

## Структура плагина

```
.claude-plugin/plugin.json Манифест плагина
skills/humanizer/SKILL.md Английский навык (24 паттерна)
skills/humanizer-ru/SKILL.md Русский навык (25 паттернов)
commands/humanizer.md Команда /humanizer
commands/humanizer-ru.md Команда /humanizer-ru
```

## Источники

- [Wikipedia: Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing)
- [WikiProject AI Cleanup](https://en.wikipedia.org/wiki/Wikipedia:WikiProject_AI_Cleanup)
- [smixs/humanizer-ru](https://github.com/smixs/humanizer-ru) - дополнительные паттерны
- [blader/humanizer](https://github.com/blader/humanizer) - оригинальный проект

## История версий

- **3.0.0** - Конвертация в плагин Claude Desktop, улучшения из smixs/humanizer-ru (цепочки падежей, пассив, заимствования, шаблонные переходы, жёсткие запреты, правила стиля)
- **1.0.0** - Первый релиз русской версии

## Лицензия

MIT
Loading