Avoid AI Writing

Name: Avoid AI Writing (Claude Skill)
Author: conorbronsdon

автор conorbronsdon · conorbronsdon/avoid-ai-writing

Audit and rewrite content to remove AI-tell patterns (em-dashes, 'delve', etc.).

A skill that audits your draft against 21 known AI-writing tells — em-dashes everywhere, 'delve', 'in the realm of', 'it's important to note' — and rewrites to sound human. Use it as a post-pass on anything you ship.

▶ Смотреть демо 📦 Установить 💡 Сценарии

Зачем использовать

Ключевые функции

21 categories of AI-tell patterns documented and detected
Auto-rewrite mode with a 'show diff' preview
Style controls (formal vs casual)
Tracks patterns over time so you can see your own AI drift
Compatible with Claude Code, OpenClaw, Hermes

Живое демо

Как выглядит на практике

avoid-ai-writing-skill.replay ▶ готово

0/0

Установка

Репозиторий автора · Официальная документация Claude Skills

Сценарии использования

Реальные сценарии: Avoid AI Writing

Strip AI tells from a blog post before publishing

👤 Anyone shipping AI-assisted writing ⏱ ~15 min intermediate

Когда использовать: Right before you hit publish.

Предварительные требования

Server/skill installed and authenticated — See repo README

Поток

Audit

Run the avoid-ai-writing skill on /drafts/launch-post.md. Show me the offending phrases and counts.✓ Скопировано

→ Inline list of detections
Rewrite

Apply the rewrite in-place but show me a diff first.✓ Скопировано

→ Diff you can accept or reject hunk-by-hunk

Итог: A post that doesn't make readers smell the model.

Подводные камни

Don't run it on someone else's prose — Don't run it on someone else's prose — the rewrite changes voice. Use on your own drafts only.

Стоимость и лимиты

Во что обходится

Квота API: See provider docs for rate limits
Токенов на вызов: Varies by tool
Деньги: See repo README for pricing details
Совет: Cache tool results and avoid repeated identical calls.

Безопасность

Права, секреты, радиус поражения

Хранение учётных данных: Use environment variables; never commit secrets

Исходящий трафик: Tool calls go to the provider's API as documented

Устранение неполадок

Частые ошибки и исправления

skill flags valid em-dashes

Tune the threshold in the skill's config — em-dash usage above 1 per 200 words is the default tell.

Проверить: Reduce density and re-run

rewrites change meaning

Use the diff mode and reject hunks that drift. The skill's confidence score helps prioritize.

Проверить: Compare original vs rewrite per paragraph

Альтернативы

Avoid AI Writing в сравнении

Альтернатива	Когда использовать	Компромисс
Generic linters	You want full style-guide enforcement	Vale is broader; this skill is AI-tell-specific

Ещё

Ресурсы

📖 Читать официальный README на GitHub

🐙 Открытые задачи

🔍 Все 400+ MCP-серверов и Skills