Anti-AI-Prose: Audit Writing for Machine-Generated Patterns

Detect and fix the linguistic tells that make written English read as machine-generated. The goal is prose that sounds like a specific, thoughtful human wrote it.

This skill applies to any text: documentation, READMEs, wikis (Confluence, Notion, internal), pull request descriptions, commit messages, release notes, blog posts, emails, slide copy, creative writing, and code comments / docstrings. The vocabulary, syntax, tone, and formatting checks are language-domain, not platform-domain.

Based in part on Wikipedia: Signs of AI writing - a field guide compiled by editors who have read enormous volumes of LLM-generated text and know what it actually looks like - on stop-slop (MIT), which contributed the confident-filler check: emphasis crutches, rhetorical setups, and the faux-profundity fragment - and on poteto/plugins pstack/skills/unslop (MIT), which contributed the plain-speech checks, the abstract-metaphor-noun list, chat artifacts, and the voice-restoration guidance.

When to use

• Auditing a README, doc page, or wiki article that feels machine-written, or a PR body, commit message, or release note draft before publishing
• Polishing a blog post, email, script, or creative writing drafted with LLM help, or reviewing docstrings and code comments for the same patterns
• Any time someone says "this sounds like ChatGPT wrote it", or self-checking after heavy LLM drafting
• Filtering your own replies, explanations, and drafts as you write them (inline mode, see below)

When NOT to use