$npx skillfedfor your agent

writing-anti-ai

This skill identifies and eliminates predictable patterns that mark AI-generated prose, then injects authentic voice and personality back in. It handles both English and Chinese, targeting filler phrases, formulaic structures, undue emphasis, and vague attributions while teaching you to vary rhythm and trust your reader. The result reads like it came from a real person, not a statistical model.

Writing Anti-AI detects and removes AI-generated writing patterns to make text sound natural and human-written.

AI-generated summary based on this skill's SKILL.md

4,854 402 MITupdated by Galaxy-Dawn

Decision gist · record as of 2026-07-17

Writing Anti-AI detects and removes AI-generated writing patterns to make text sound natural and human-written. This skill identifies and eliminates predictable patterns that mark AI-generated prose, then injects authentic voice and personality back in. It handles both English and Chinese, targeting filler phrases, formulaic structures, undue emphasis, and vague attributions while teaching you to vary rhythm and trust your reader. The result reads like it came from a real person, not a statistical model.

manual: git clone https://github.com/Galaxy-Dawn/claude-scholar → cp -r claude-scholar/skills/writing-anti-ai ~/.claude/skills/writing-anti-ai
skills/writing-anti-ai/SKILL.md · version e411dd12

Use it when

  • writing-anti-ai detects common AI writing patterns including filler phrases, formulaic structures, undue emphasis, and vague attributions.
  • Yes.

Verify before relying

Read SKILL.md below before installing (7 files). Open directory: indexed for reading, not audited.

Same gist for agents: .md · .json

Install

Galaxy-Dawn/claude-scholar/writing-anti-ai · repository language: Python

Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How does writing-anti-ai humanize AI text?

writing-anti-ai identifies and eliminates predictable patterns that mark AI-generated prose, then injects authentic voice and personality back in. It targets filler phrases, formulaic structures, undue emphasis, and vague attributions while teaching you to vary rhythm and trust your reader. The result reads like it came from a real person, not a statistical model.

What AI writing patterns does writing-anti-ai remove?

writing-anti-ai detects common AI writing patterns including filler phrases, formulaic structures, undue emphasis, and vague attributions. It recognizes the telltale cadences and hedging language that statistical models produce, then guides you to replace them with natural variation and direct expression that sounds authentically human.

Can writing-anti-ai make text sound more natural?

Yes. writing-anti-ai edits content to eliminate robotic language and add authentic voice by removing AI traces and teaching rhythm variation. It helps you trust your reader instead of over-explaining, resulting in prose that flows naturally and feels genuinely written rather than algorithmically generated.

Does writing-anti-ai support languages other than English?

writing-anti-ai supports both English and Chinese text transformation. It applies the same pattern-detection and humanization techniques across both languages, helping you remove AI traces and inject authentic voice regardless of which language you're writing in.

How can writing-anti-ai help with academic or professional writing?

writing-anti-ai polishes academic and professional writing by removing AI traces that undermine credibility. It eliminates formulaic structures and vague attributions while preserving the formality and precision your field requires, making your work sound like it came from an expert rather than a language model.

SKILL.md

Rendered from the published skill. Quoted content, verbatim.

Writing Anti-AI

Remove AI-generated writing patterns from text to make it sound natural and human-written. Supports both English and Chinese.

Overview

This skill identifies and eliminates predictable AI writing patterns from prose, based on Wikipedia: Signs of AI writing, maintained by WikiProject AI Cleanup.

Core insight: LLMs use statistical algorithms to predict what should come next. The result tends toward the most statistically likely outcome that applies to the widest

(truncated - see the full file via the links below)

File tree — 7 files
skills/writing-anti-ai/SKILL.md
skills/writing-anti-ai/examples/chinese.md
skills/writing-anti-ai/examples/english.md
skills/writing-anti-ai/references/patterns-chinese.md
skills/writing-anti-ai/references/patterns-english.md
skills/writing-anti-ai/references/phrases-to-cut.md
skills/writing-anti-ai/references/wikipedia-source.md

Let your AI agent find skills like this

Example. Real query, live index.

You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.

wish › “Humanize AI-generated text to sound natural and human-written”

Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →

Related skills

Scholar Anti Ai Writing
by catlog22 · catlog22/maestro-flow

This skill scans academic writing for telltale AI patterns—promotional phrasing, superficial analysis, and statistical predictability—then rewrites flagged passages to restore authentic voice. It works with English and Chinese text across papers, reports, and articles, scoring revisions on directness, rhythm, trust, authenticity, and density to ensure scholarly quality.

no license declared → metadata onlyfor claude-code, codexupdated Jul 2026
★ 482repo stars
ai-writing-detection
by mike-coulbourn · mike-coulbourn/claude-vibes

This skill provides a systematic framework for identifying AI authorship through nine layers of analysis, from technical artifact detection to stylometric observation. It catalogs high-signal vocabulary, structural quirks, and model-specific fingerprints across ChatGPT, Claude, Gemini, and other systems, while emphasizing false-positive prevention for non-native speakers and formal writing. Use it to evaluate whether text originates from human or AI sources with confidence scoring and context-aware assessment.

MITupdated Dec 2025
★ 35repo stars
Brief Write
by cycleuser · cycleuser/Skills

Brief Write captures your authentic writing voice—direct, conversational, and genuine—to compose articles and documentation that sound human, not algorithmic. It analyzes your style and rewrites content to match your tone while sidestepping common AI markers. Use it to draft blog posts, technical guides, or personal pieces that read like you.

GPL-3.0updated Jul 2026
★ 9repo stars
writing-clearly-and-concisely
by softaworks · softaworks/agent-toolkit

This skill teaches you to write with clarity and force by applying William Strunk Jr.'s timeless rules for grammar, composition, and word choice. It covers active voice, concrete language, omitting needless words, and identifies common AI writing patterns to avoid—puffery, empty phrases, and overused vocabulary. Load the relevant reference section for your task and apply the rules directly to documentation, commit messages, error messages, or any prose meant for human readers.

MITupdated Mar 2026
★ 2,243repo stars
Humanizer
by trailofbits · trailofbits/skills-curated

Humanizer identifies telltale signs of artificial writing—promotional language, superficial analysis, excessive em dashes, and AI vocabulary—then rewrites them to sound genuinely human. It goes beyond pattern removal to inject personality and voice, helping you edit drafts, review content, and clean up LLM output into prose that reads like it came from a real person.

CC-BY-SA-4.0updated Jul 2026
★ 469repo stars
Humanizer
by zed-industries · zed-industries/zed

Humanizer identifies and rewrites text that bears hallmarks of AI generation, replacing sterile patterns with genuine personality and natural rhythm. It scans for 24 common AI writing signatures—from significance inflation to synonym cycling—then reconstructs passages with opinions, specificity, and human imperfection. The skill goes beyond pattern removal to inject actual voice, ensuring your writing sounds like it came from a thinking person, not an algorithm.

no license declared → metadata onlyupdated Jul 2026
★ 87,615repo stars

More skills Literary Ghostwriter (GPL-3.0) · humanize (MIT) · Inno Humanizer (NOASSERTION) · humanizer (MIT) · humanizer (Apache-2.0)

Tags
text-authenticitypattern-detectionvoice-injectionprose-refinementbilingual-editingcontent-humanizationai-detectionwriting-quality