avoid-ai-writing
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.
npx skills add conorbronsdon/avoid-ai-writing --skill avoid-ai-writing --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
You edit content to remove AI writing patterns (AI-isms) by auditing and rewriting. The skill can operate in three modes: rewrite (default) to flag AI-isms and rewrite the text; detect to flag AI-isms without rewriting; and edit to apply in-place fixes with minimal targeted edits. It 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.
How it works
- The skill is invoked to audit text for AI-isms and rewrite them in rewrite mode. In detect mode, it only flags AI-isms and assesses their impact. In edit mode, it reads a specified file, applies minimal targeted fixes to flagged spans, then re-reads to verify resolution.
- It defines three modes with explicit triggers: rewrite (default), detect, and edit. It supports optional voice configuration and an optional iteration parameter (iterate) for convergence, capped at 2 passes.
- When rewriting, it identifies every AI-ism, and returns a clean version with AI-like patterns removed, while preserving quoted material, code blocks, and tables from modification.
- It provides a diff summary of changes in rewrite mode, detailing what was changed and why.
When to use it
Use this skill when you want to improve writing quality by removing AI-like patterns, or when you need to audit for AI patterns. Trigger modes via: rewrite (default), detect, or edit. The Iterate behavior is used when convergence is requested (e.g., keep rewriting until no patterns remain or N passes reached).
What it can touch
The skill operates on textual content and supports editing in place for a file when in edit mode. It flags AI-isms and performs rewrites accordingly. It maintains structure by preserving quoted text, code blocks, tables, and text attributed to others; those are not rewritten.
Caveats
The description notes that the skill is a writing-quality tool, not a verdict, and emphasizes context when evaluating AI patterns. It discusses potential false positives and the usefulness of signals rather than proof. It specifies three operational modes, iteration limits, and safe handling of code and tables during edits.
# 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. Independent audits of commercial AI detectors have found false-positive rates above 60% on non-native English writers (Liang et al., Stanford, *Patterns* 2023) and overall misclassification rates above 70% on open-source detectors (Jabarian & Imas, BFI Working Paper 2025-116, 2025). Adversarial paraphrase reduces detection accuracy by ~88% across every method tested (arXiv:2506.07001, 2025). The patterns are useful as a signal — both for cleaning up your own writing and for assessing whether a piece reads as AI-generated. Just don't make them the sole basis for a consequential decision (academic integrity, hiring, publication, attribution). Several rules here also fire on second-language writing, deadline-pressed humans, and technical genres that com
- What this skill is and isn't
- Modes
- What to remove or fix
- Formatting
- Sentence structure
- Words and phrases to replace
- Template phrases (avoid)
- Transition phrases to remove or rewrite
- Structural issues
- Significance inflation
- Aphorism formulas
- Generic future-narrative closers
- Hedge-stacked predictions
- "Real/actual" adjective inflation
node detector/validate.js <original> <rewritten>
What does the avoid-ai-writing skill do?
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.
How do I install it?
Run `npx skills add conorbronsdon/avoid-ai-writing --skill avoid-ai-writing --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From conorbronsdon/avoid-ai-writing, a repository with 2,794 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.