Avoid AI Writing skill
avoid-ai-writing
A skill that finds typical machine-writing patterns in text and rewrites them, with detect-only and edit-in-place modes
- 5,301 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- The skill is instructions and references; edit mode only changes prose in named files
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/avoid-ai-writingDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill is instructions and references; edit mode only changes prose in named files
This is third-party code. Review the repository files before installing.
What it does
The skill checks text against a catalog of patterns common in language model output: inflated significance, promotional modifiers, unnamed experts, formulaic openers and conclusions, and uniform rhythm. Its replacement vocabulary is tiered so rare marker words are treated differently from plain wordiness. In rewrite mode it returns quoted findings, a clean version, a change summary and a second-pass audit. Detect mode only flags issues and separates clear problems from judgment calls, while edit mode makes targeted prose fixes in a file and leaves code, tables and quotes alone. You can set a voice and a context such as LinkedIn or technical docs.
Who it is for. For writers, editors and marketers working in English who want to strip formulaic patterns from their text.
Good fit when
- You need to clean an English post or article of filler and templates
- You want to audit a draft without rewriting it
- You need targeted fixes in a Markdown docs file
Not a fit when
- The text is not in English; vocabulary and patterns target English
- You need proof that text is AI-written; the author warns these are signals, not proof
Example request
Scan this LinkedIn post for AI tells, flag only, don't rewriteLimitations
The pattern catalog and vocabulary are English only. The author stresses the same patterns appear in human writing, especially from non-native writers, so they should not decide authorship. The full skill directory with references/patterns.md is required; SKILL.md alone is not enough.
How to disable. Delete the avoid-ai-writing folder from the skills directory or uninstall the avoid-ai-writing plugin via /plugin.
FAQ
Why use this instead of a make-it-human prompt?
It checks against a concrete catalog and vocabulary, quotes every finding and runs a second pass on the result.
Does it work in Cursor or Windsurf?
Yes, there is a ready .mdc rule for Cursor and a single-file dist/avoid-ai-writing.md for other tools.
Discussion
No questions or reviews yet.
Related
SkillsA de-AI writing skill: it repairs the narrative architecture of fiction and edits professional documents by their venue rules
Two skills for English prose: humanize rewrites a model draft in a natural voice, and ai-check flags machine-writing tells
A skill that finds AI writing tells, rewrites the text in a chosen voice, and optionally scores it from 0 to 100
A writing rules skill for agents: it strips model boilerplate, varies sentence rhythm and bans invented numbers and quotes
A skill that edits English drafts: strips AI boilerplate, keeps the author's voice, and can also just list what it found without rewriting
A skill that finds AI tells in English prose and edits them surgically; three Python scanners run on their own and the teach command learns your voice
README in short
The README shows a before and after sample, explains the three modes, voice profiles and pass limits. It covers install for Claude Code, Cowork, OpenClaw, Cursor, Hermes and Codex, plus Windsurf, Cline, Copilot and Claude.ai projects. It lists sample catalog patterns with fixes and a bundled deterministic detector. MIT licensed.
README badge
Original SKILL.md
---
name: avoid-ai-writing
description: Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice profile (casual / professional / technical / warm / blunt), and an iterate-to-convergence pass.
version: 3.35.0
license: MIT
compatibility: Any AI coding assistant that supports agentskills.io SKILL.md format (Claude Code, Cursor, VS Code Copilot, Hermes Agent, OpenHands, etc.) or OpenClaw. No external tools or APIs required.
metadata:
author: Conor Bronsdon
repository: https://github.com/conorbronsdon/avoid-ai-writing
tags: writing editing voice quality
agentskills_spec: "1.0"
openclaw:
emoji: "✍️"
---
# Avoid AI Writing — Audit & Rewrite
You are editing content to remove AI writing patterns ("AI-isms") that make text sound machine-generated.
## What this skill is and isn't
This is a **writing-quality tool**, not a verdict. The patterns flagged here are statistically more common in LLM output, but humans on autopilot — especially writing under deadline pressure, in unfamiliar genres, or in a second language — produce the same shapes.
In short: signals, not proof. Worth acting on; not worth ruining someone's day over.
## Modes
This skill operates in one of three modes:
**`rewrite`** (default) — Flag AI-isms and rewrite the text to fix them.
**`detect`** — Flag AI-isms only. No rewriting.