Home / AI Trending / conorbronsdon/avoid-ai-writing

avoid-ai-writing — What is it?

The 'avoid-ai-writing' project is a tool designed to audit and rewrite content to eliminate AI-generated writing patterns, enhancing the authenticity and readability of text produced by AI agents.

⭐ 542 Stars 🍴 49 Forks — MIT Author: conorbronsdon
Source: per README View on GitHub →

Why it matters

This project is gaining attention due to the increasing prevalence of AI-generated content and the need for tools that can distinguish between human and AI writing. Its unique approach to structured audits and two-pass detection stands out, offering a comprehensive solution for content authenticity. The project's compatibility with multiple AI agents and platforms also contributes to its appeal.

Source: Synthesis of README and project traits

Core Features

Structured Audit

Performs a detailed analysis of text, identifying AI-generated patterns and providing a rewrite with a change summary and second-pass audit.

Source: per README
Two-pass Detection

Incorporates a second pass to catch patterns that may have survived the first edit, ensuring a thorough audit.

Source: per README
Word Replacement Table

Utilizes a 109-entry word replacement table across three tiers to provide specific, plainer alternatives for flagged words, reducing false positives.

Source: per README
Pattern Categories

Covers 36 pattern categories, including content, language, structure, communication, and meta patterns, with before/after examples.

Source: per README
Detect Mode

Enables flagging of AI patterns without rewriting, allowing for content auditing and the assessment of flags as real problems or intentional patterns.

Source: per README

Architecture

The architecture of the project is inferred to be modular, with separate components for pattern detection, rewriting, and compatibility with various AI agents. The code structure suggests a clear separation of concerns, with distinct modules for different features.

Source: Code tree

Project Knowledge Graph

Knowledge graph: project (center) + core features (inner hexagons) + key dependencies (outer chips) Not enough information.Not enough inf… Structured Audit Two-pass Detection Word Replacement TableWord Replacement Ta… Pattern Categories Detect Mode avoid-ai-writing Project Core feature Key dependency

Center: project; inner ring: core feature modules; outer ring: key dependencies. Auto-generated from core_features and tech_stack.key_deps.

Tech Stack

LanguageNot enough information.FrameworkNot enough information.
Key dependencies
Not enough information.
Infrastructure / Deployment
Not enough information.
Source: Dependency files + code tree

Quick Start

### Claude Code **Option 1: Clone into skills directory** ```bash git clone https://github.com/conorbronsdon/avoid-ai-writing ~/.claude/skills/avoid-ai-writing ``` **Option 2: Copy the file directly** Download `SKILL.md` and place it in any directory that Claude Code can read. Reference it in your `CLAUDE.md`: ```markdown - Editing for AI patterns → read `path/to/avoid-ai-writing/SKILL.md` ``` **Option 3: Use as a slash command** Create a command file (e.g., `~/.claude/commands/clean-ai-writing.md`): ```markdown --- description: Audit and rewrite content to remove AI writing patterns --- $ARGUMENTS Read and follow the instructions in ~/.claude/skills/avoid-ai-writing/SKILL.md ``` Then use `/clean-ai-writing <your text>` in Claude Code. ### OpenClaw **Option 1: [Install from ClawHub](https://clawhub.ai/conorbronsdon/avoid-ai-writing)** ```bash clawhub install avoid-ai-writing ``` **Option 2: Clone into skills directory** ```bash git clone https://github.com/conorbronsdon/avoid-ai-writing ~/.openclaw/skills/avoid-ai-writing ```
Source: README Installation/Quick Start

Use Cases

The project is suitable for content creators, writers, and AI agents using Claude Code, OpenClaw, and Hermes. It is useful in scenarios where AI-generated content needs to be reviewed for authenticity, such as in content moderation, copywriting, and academic writing.

Source: README

Strengths & Limitations

Strengths

  • Strength 1: Comprehensive AI-ism detection and rewriting
  • Strength 2: Compatibility with multiple AI agents
  • Strength 3: Structured audit and detection modes

Limitations

  • Limitation 1: Lack of information on the primary programming language and tech stack
  • Limitation 2: Limited information on deployment and runtime infrastructure
Source: Synthesis of README, code structure and dependencies

Latest Release

Not enough information.

Source: GitHub Releases

Verdict

The 'avoid-ai-writing' project is a valuable tool for enhancing the authenticity of AI-generated content. Its structured approach and compatibility with multiple AI agents make it a compelling choice for those seeking to improve the readability and trustworthiness of AI-generated text.

Transparency Notice
This page is auto-generated by AI (a large language model) from the following public materials: GitHub README, code tree, dependency files and release notes. Analyzed at: 2026-05-23 19:46. Quality score: 85/100.

Data sources: README, GitHub API, dependency files