Claude Skill
conorbronsdon/avoid-ai-writing
A Claude Skill that audits and rewrites content to remove AI writing patterns. Compatible with Claude Code, OpenClaw, and Hermes for more natural, human-like text.
Overview
Repository
Install this Skill
git clone https://github.com/conorbronsdon/avoid-ai-writing ~/.claude/skills/avoid-ai-writingRegistry
git clone https://github.com/conorbronsdon/avoid-ai-writing ~/.claude/skills/avoid-ai-writinggit clone https://github.com/conorbronsdon/avoid-ai-writing ~/.openclaw/skills/avoid-ai-writing
Summary
A Claude Skill that audits and rewrites content to eliminate AI writing patterns, making text sound more natural and human-like. Compatible with Claude Code, OpenClaw, and Hermes agents.
用于审计和重写内容以去除AI写作模式的技能。可与您喜爱的代理工具(包括Claude Code、OpenClaw和Hermes)配合使用。
Key features
- Audits text for common AI writing patterns
- Rewrites content to sound more human-like
- Compatible with Claude Code, OpenClaw, and Hermes
- Designed for use with LLM agents and prompt engineering
- Focuses on natural language improvement
Use cases
- Polishing AI-generated drafts for publication
- Removing robotic phrasing from business communications
- Humanizing content for blogs and articles
- Improving naturalness in agent-generated responses
- Ensuring writing passes AI-detection checks
README excerpt
<div align="center"> # avoid-ai-writing Audit & rewrite content to remove AI writing patterns. A practical skill for any AI agent. Supports detect-only and edit-in-place modes, plus voice profiles. [](https://github.com/conorbronsdon/avoid-ai-writing/stargazers) [](LICENSE) [](https://x.com/ConorBronsdon) </div> --- A portable writing skill for [Claude Code](https://docs.anthropic.com/en/docs/claude-code), [OpenClaw](https://github.com/openclaw/openclaw), [Hermes](https://github.com/NousResearch/hermes-agent), and any other [agentskills.io](https://agentskills.io)-compatible agent. Audits and rewrites content to remove AI writing patterns ("AI-isms"). **Three modes:** - **Rewrite** (default) — flags AI patterns and rewrites the text to fix them. A built-in second pass catches patterns that survived the first edit. - **Detect** — flags AI patterns without rewriting. Shows which flags are real problems vs. judgment calls. Useful when patterns might be intentional, when auditing content you don't want altered, or when you just want a quick scan. - **Edit** — edits a file in place (via the Edit tool) with minimal, targeted changes, preserving passages that are already human. Returns an edits-made + verification report, not the full file. An optional **voice profile** (casual / professional / technical / warm / blunt) sets how the prose should sound, independent of the audience context profile. ## Quick demo **Input:** > Certainly! Acme Analytics, a vibrant startup nestled in the heart of Boulder's thriving