AI Pattern Detection Skill
Purpose
Automatically scan content for AI-generated writing patterns and provide authentic alternatives. This skill activates when Claude generates or reviews text content, ensuring outputs maintain human-like authenticity.
When This Skill Applies
- Generating any prose, documentation, or written content
- Reviewing or editing existing documents
- User mentions "AI detection", "writing quality", "authentic voice"
- User asks to "make it sound more natural" or "less robotic"
- Creating marketing copy, documentation, or communications
Detection Categories
Critical Patterns (Always Flag)
These immediately identify content as AI-generated:
- Corporate Buzzwords: "seamlessly integrates", "cutting-edge", "revolutionary", "next-generation", "comprehensive solution"
- Vague Intensifiers: "dramatically improves", "significantly enhances", "vastly superior"
- Formulaic Transitions: "Moreover,", "Furthermore,", "Additionally,", "In conclusion,"
- Performative Language: "aims to provide", "strives to achieve", "designed to enhance"
- Academic Passive: "It has been observed that...", "It can be argued that..."
Structural Patterns (Flag When Overused)
- Three-item lists: "reliable, scalable, and secure"
- Em-dash overuse: Multiple em-dashes in a paragraph
- Identical paragraph structure: Topic → 3 points → conclusion repeated
- Balanced hedging: "While X has challenges, it also offers opportunities"
Contextual Patterns (Check Frequency)
Words acceptable at 1:1000 ratio but problematic at 1:100:
- manifest, revolutionary, next-generation
- robust, scalable, comprehensive
- synergy, leverage, utilize
Replacement Guidelines
| Instead of | Use |
|---|---|
| "plays a crucial role" | "handles" / "manages" / "does" |
| "seamlessly integrates" | "works with" / "connects to" |
| "cutting-edge" | "new" / "recent" / specific tech name |
| "Moreover," | [just start the next sentence] |
| "comprehensive solution" | [specific description of what it does] |
| "dramatically improves" | [specific metric: "reduces latency by 40%"] |
| "robust" | "handles X requests/second" / "99.9% uptime" |
Authenticity Markers to Include
Strong authentic content includes:
- Specific opinions: "I prefer X because..." not "X is preferred"
- Acknowledged trade-offs: "This approach sacrifices Y for Z"
- Real-world constraints: "Budget limited us to..."
- Uncertainty where appropriate: "We're not sure yet whether..."
- Varied sentence structure: Mix short and long, different openings
- Domain-specific vocabulary: Use actual technical terms, not generic descriptions
Application Process
When generating or reviewing content:
- Scan for critical banned patterns
- Count contextual pattern frequency
- Check structural variety
- Suggest specific replacements
- Verify authenticity markers present
Examples
Before (AI-Detected)
The platform seamlessly integrates cutting-edge technology to dramatically improve workflow efficiency. Moreover, it plays a crucial role in enabling next-generation solutions. In conclusion, this comprehensive approach transforms how teams collaborate.
After (Authentic)
The platform connects to existing tools through standard APIs. Initial tests show 40% faster task completion. Teams report fewer context switches between applications.
Script Reference
For automated scanning, use scripts/pattern_scanner.py which:
- Counts pattern frequencies
- Flags critical violations
- Generates replacement suggestions
- Produces authenticity score (0-100)
Integration
This skill works with:
/writing-validatorcommand for explicit validationwriting-validatoragent for deep analysis- Any content generation task automatically
References
- @$AIWG_ROOT/agentic/code/addons/voice-framework/README.md — Voice framework for target style profiles
- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/instruction-comprehension.md — Parsing content requirements accurately
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/README.md — SDLC framework context for documentation quality
- @$AIWG_ROOT/docs/cli-reference.md — CLI reference for writing-related commands
- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/research-before-decision.md — Research patterns before making writing recommendations