voice-analyze

voice-analyze

Reverse-engineer voice profiles from sample content by analyzing writing patterns. Detects and flags AI writing tells so the resulting profile produces human-sounding output.

Triggers

Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):

• "voice fingerprint" -> voice profile extraction
• "what's my writing style" -> voice analysis

Behavior

When triggered, this skill:

1. Analyzes text samples for:

   • Sentence structure and length patterns
   • Vocabulary sophistication and domain
   • Tone markers (formality, confidence, warmth)
   • Structural patterns (lists, examples, questions)
   • Perspective and voice choices

2. Extracts measurable features:

   • Average sentence length
   • Vocabulary complexity (syllables, word length)
   • Contraction usage
   • Personal pronoun frequency
   • Question density
   • List/bullet usage

3. Scans for AI writing tells (see ../voice-apply/references/ai-tells.md):

   • Flags any banned vocabulary found in the sample (verbs, adjectives, nouns, adverbs from the tells list)
   • Detects banned sentence structures: "It's not X, it's Y" negation patterns, self-posed questions answered immediately, anaphora abuse, present participle trailing clauses
   • Measures em dash frequency (AI models use ~10x more than human writers)
   • Checks for uniform sentence length clustering (the "burstiness problem": AI clusters at 15-20 words, humans swing from 3-word fragments to 40-word sprawls)

Usage Examples

Analyze Existing Documentation

Match Brand Voice

Capture Personal Style

Analysis Methodology

Feature Extraction

AI Tells Detection Pass

Dimension Calibration

Vocabulary Extraction

Output Format

Integration