Avoid Ai Writing
Skill Verified ActiveAudit 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 detection-only mode that flags patterns without rewriting.
To help users refine their writing by removing AI-generated patterns, making content sound more human and natural, and providing detailed feedback on writing quality.
Features
- Audits and rewrites content to remove AI writing patterns
- Supports 'rewrite' (default) and 'detect' (flag-only) modes
- Provides detailed issue reporting, rewrites, and second-pass audits
- Configurable via context profiles to adjust strictness
- Works with Claude Code, OpenClaw, and other agentskills.io compatible agents
Use Cases
- Editing blog posts, articles, or social media to sound less AI-generated
- Auditing content to identify AI writing patterns without altering the text
- Refining technical documentation or marketing copy for clarity and human voice
- Ensuring published content maintains a consistent and authentic authorial voice
Non-Goals
- Rewriting content for grammatical errors or typos (focus is on AI patterns)
- Changing the core meaning or factual content of the original text
- Providing stylistic suggestions outside the scope of AI-ism detection
Installation
npx skills add conorbronsdon/avoid-ai-writingRuns the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.
Quality Score
VerifiedTrust Signals
Similar Extensions
De Ai Ify
100Remove AI-generated jargon and restore human voice to text. Built from analyzing 1,000+ AI vs human content pieces.
Article Writing
100Write blog posts, guides, tutorials, and long-form content. Sounds like a real person, not AI. Use when the user wants polished written content.
Grammar Check
99Identify grammar, logical, and flow errors in text and suggest targeted fixes without rewriting the entire text. Use when proofreading content, checking writing quality, or reviewing a draft.
LinkedIn Humanizer
100Scrub AI tells from any text draft OR audit a finished post against the 2026 algorithm heuristic checklist. Tier-based rewriter (forensic / strict / aesthetic / all) plus `--mode audit` for detection-only pass-fail review covering length, hook, CTA, format penalties, AI vocab. Sub-tools: emoji-pattern detector, multi-detector spread tester (GPTZero, Originality.ai, ZeroGPT, Sapling, Copyleaks), rule explainer. Triggers on "humanize", "de-AI", "review this draft", "audit before posting", "is this ready".
Unslop Review
100Rewrites code review comments so they read like a human teammate wrote them. Cuts corporate-AI throat-clearing ("I noticed...", "I was wondering if perhaps...", "It might be worth considering..."). Each comment is direct: location, the issue, a concrete fix. Use when user says "humanize review", "de-slop PR comment", "make this feedback sound human", "review this PR", "code review", "/review", "/unslop-review". Auto-triggers when reviewing PRs.
Image Transformation API
100Transform images with resize, crop, smart crop, upscale, remove background, and 20+ operations.