ai-writing-detection
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.
AI Writing Detection helps you identify whether text was written by AI or humans using pattern analysis and technical markers.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2025-12-21
AI Writing Detection helps you identify whether text was written by AI or humans using pattern analysis and technical markers. 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.
Use it when
- ai-writing-detection identifies distinctive fingerprints from ChatGPT, Claude, Gemini, and other AI systems.
- ai-writing-detection emphasizes false-positive prevention by accounting for non-native speakers, formal writing conventions.
Verify before relying
Read SKILL.md below before installing (9 files). Open directory: indexed for reading, not audited.
Install
mike-coulbourn/claude-vibes/ai-writing-detection
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 to detect AI written text using ai-writing-detection?
ai-writing-detection provides a nine-layer analysis framework to identify AI authorship. Start by examining technical artifacts, vocabulary patterns, and structural quirks. The skill catalogs high-signal markers across ChatGPT, Claude, Gemini, and other systems. Combine stylometric observation with context-aware assessment to generate confidence scores. Always cross-reference findings against false-positive risk factors, particularly for non-native speakers and formal writing contexts.
What are model-specific AI fingerprints in ai-writing-detection?
ai-writing-detection identifies distinctive fingerprints from ChatGPT, Claude, Gemini, and other AI systems. Each model exhibits characteristic vocabulary choices, structural preferences, and formatting patterns. The skill documents these model-specific markers to help you pinpoint which AI system likely generated a given text. Understanding these fingerprints strengthens your ability to distinguish between different AI sources and recognize their unique stylistic signatures.
How does ai-writing-detection prevent false positives?
ai-writing-detection emphasizes false-positive prevention by accounting for non-native speakers, formal writing conventions, and legitimate stylistic variation. The framework includes context-aware assessment protocols that distinguish genuine human writing from AI-generated content without over-flagging legitimate edge cases. This prevents incorrect accusations and ensures your detection methodology remains reliable across diverse writing contexts and author backgrounds.
What vocabulary and structural patterns does ai-writing-detection teach?
ai-writing-detection catalogs high-signal vocabulary red flags, structural quirks, and formatting patterns characteristic of AI-generated text. You'll learn which word choices, sentence constructions, and organizational markers commonly appear in machine-generated content. The skill also covers citation verification techniques and technical artifacts that reveal AI authorship, enabling you to recognize these patterns across different writing samples and contexts.
Can ai-writing-detection identify ChatGPT generated content?
Yes. ai-writing-detection includes detection markers and artifacts specific to ChatGPT. The skill documents ChatGPT's characteristic vocabulary preferences, structural tendencies, and formatting patterns. By analyzing your text against these model-specific fingerprints alongside the broader nine-layer framework, you can identify whether ChatGPT likely generated the content and assess confidence levels for your conclusion.
What is the ai-writing-detection methodology for text analysis?
ai-writing-detection employs a systematic nine-layer methodology combining technical artifact detection, stylometric analysis, vocabulary assessment, structural pattern recognition, and citation verification. The approach integrates model-specific fingerprinting for ChatGPT, Claude, Gemini, and others with false-positive prevention protocols. This comprehensive framework enables confidence-scored evaluation of whether text originates from human or AI sources while accounting for legitimate writing variation.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
AI Writing Detection Reference
Expert-level knowledge base for detecting AI-generated text, compiled from academic research, commercial detection tools, and empirical analysis.
Quick Reference: High-Confidence Signals
These indicators strongly suggest AI authorship when found together:
Vocabulary Red Flags
High-signal words (50-700x more common in AI text): - "delve", "tapestry", "nuanced", "multifaceted", "underscore" - "intricate interplay", "played a crucial role", "complex and multifaceted" - "paramount", "pivotal", "meticulous", "holistic", "robust" - "stands/serves as", "marking a pivotal moment", "underscores its importance"
Overused phrases: - "It's important to note that..." - "In today's fast-paced world..." - "At its core..." - "Without further ado..." - "Let me explain..."
See
(truncated - see the full file via the links below)
File tree — 9 files
plugins/vibes/skills/ai-writing-detection/SKILL.md
plugins/vibes/skills/ai-writing-detection/reference/citation-patterns.md
plugins/vibes/skills/ai-writing-detection/reference/content-patterns.md
plugins/vibes/skills/ai-writing-detection/reference/false-positive-prevention.md
plugins/vibes/skills/ai-writing-detection/reference/formatting-patterns.md
plugins/vibes/skills/ai-writing-detection/reference/markup-artifacts.md
plugins/vibes/skills/ai-writing-detection/reference/model-fingerprints.md
plugins/vibes/skills/ai-writing-detection/reference/structural-patterns.md
plugins/vibes/skills/ai-writing-detection/reference/vocabulary-patterns.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 › “Detect whether a given text was written by AI or humans”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Human Writing teaches you to write prose that sounds genuinely human by embracing variation and imperfection. It covers vocabulary choices, sentence structure, tone, and editing strategies grounded in measurable differences between human and AI text. Use it for articles, emails, marketing copy, and social content—not code or technical docs.
Humanizer-RU transforms stiff AI-generated Russian into natural human speech by raising perplexity and structural variety—the metrics that detection systems measure. It identifies 54 markers of machine writing (from bureaucratic phrasing to English-influenced calques) and replaces them with less predictable, character-driven alternatives that preserve factual accuracy.
This skill transforms Claude into a comprehensive go-to-market strategist by layering 54 specialized capabilities across search optimization, content creation, sales enablement, and analytics. It bridges traditional SEO with emerging AI search platforms, helping teams build visibility where their audiences actually discover solutions. Designed for Claude Code and compatible with any agent supporting the Agent Skills specification.
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.
Humanizer identifies telltale signs of AI-generated text—including promotional language, superficial analyses, em dash overuse, and artificial vocabulary—then rewrites problematic sections to restore natural voice. Beyond pattern removal, it injects personality and authenticity by varying sentence rhythm, adding opinions, and preserving human complexity that sterile writing lacks.
This skill detects and fixes telltale signs of AI-generated text—from promotional language and rule-of-three patterns to em dash overuse and AI vocabulary. Beyond removing these markers, it injects genuine voice and personality into writing, ensuring your text reads like it came from a real person, not an algorithm.
More skills Inno Humanizer (NOASSERTION)