BMAD-METHOD/src/modules/content-creator/tasks/style-analyzer.xml

<task>
  <metadata>
    <id>{bmad_folder}/content-creator/tasks/style-analyzer.xml</id>
    <name>Style Analyzer</name>
    <description>Deep analysis of writing style patterns, characteristics, and unique voice markers</description>
    <module>content-creator</module>
  </metadata>

  <instructions>
    <![CDATA[
# Style Analyzer Task

You are a writing style analysis expert performing deep analysis of writing samples to extract detailed style characteristics.

## Analysis Process

### 1. Input Processing
- Accept writing sample (text or file path)
- Validate minimum length (200+ words)
- Clean and prepare text for analysis

### 2. Quantitative Analysis

**Sentence Metrics:**
- Total sentences
- Average words per sentence
- Shortest/longest sentences
- Sentence length distribution
- Standard deviation (consistency measure)

**Word Metrics:**
- Total words
- Unique words
- Type-Token Ratio (vocabulary diversity)
- Average word length
- Syllables per word average

**Readability Scores:**
- Flesch Reading Ease
- Flesch-Kincaid Grade Level
- Gunning Fog Index
- SMOG Index

**Structural Metrics:**
- Total paragraphs
- Average sentences per paragraph
- Average words per paragraph
- Paragraph length variance

### 3. Qualitative Analysis

**Sentence Structure:**
Analyze sentence types:
- Simple: [% of total]
- Compound: [% of total]
- Complex: [% of total]
- Compound-complex: [% of total]

Identify patterns:
- Common sentence starters
- Sentence connectors used
- Parallel structure usage
- Fragment usage (if any)

**Vocabulary Analysis:**
Extract and categorize:
- Most frequent words (excluding stop words)
- Power words and strong verbs
- Adjectives and adverbs usage
- Transitional phrases
- Technical terminology
- Industry jargon
- Unique expressions

**Tone Indicators:**
Identify markers for:
- Formality level (vocabulary, contractions, slang)
- Expertise level (technical depth, explanations)
- Confidence (hedging vs. assertive language)
- Empathy (inclusive language, understanding)
- Enthusiasm (exclamations, superlatives)

**Voice Elements:**
Analyze usage of:
- First person (I, we, my, our)
- Second person (you, your)
- Third person (he, she, they, it)
- Active vs. passive voice ratio
- Questions (types and frequency)
- Imperatives (commands)

**Rhetorical Devices:**
Identify usage of:
- Metaphors and similes
- Analogies
- Repetition for emphasis
- Alliteration
- Rhetorical questions
- Anecdotes and stories
- Data and statistics
- Examples and illustrations

**Formatting Patterns:**
Document preferences for:
- List usage (bullets, numbers, both)
- Emphasis markers (bold, italics, caps)
- Parenthetical asides
- Dash usage (em dash, en dash)
- Colon and semicolon usage
- Quotation usage

### 4. Pattern Recognition

**Signature Patterns:**
Identify unique characteristics:
- Repeated phrases or expressions
- Characteristic opening/closing patterns
- Favorite transitional devices
- Unique structural choices
- Idiosyncratic word choices

**Stylistic Fingerprints:**
Document what makes this voice unique:
- Unusual word combinations
- Distinctive rhythm or cadence
- Unique perspective or framing
- Memorable turns of phrase

### 5. Contextual Analysis

**Content Type Indicators:**
Determine if sample is:
- Informative/educational
- Persuasive/argumentative
- Narrative/storytelling
- Descriptive/analytical
- Conversational/personal

**Audience Level:**
Infer intended audience:
- General public
- Industry professionals
- Experts/specialists
- Academic
- Mixed

**Purpose Indicators:**
Identify primary purpose:
- Teach/educate
- Persuade/convince
- Entertain/engage
- Inform/update
- Inspire/motivate

## Output Format

```
STYLE ANALYSIS REPORT
====================

Sample: [Title/Source]
Words: [X] | Sentences: [X] | Paragraphs: [X]

--- QUANTITATIVE METRICS ---

Sentence Metrics:
- Avg Length: [X] words (Range: [min]-[max])
- Consistency: [Low/Medium/High] (SD: [X])
- Complexity: Simple [X]%, Compound [X]%, Complex [X]%

Vocabulary Metrics:
- Unique Words: [X] ([X]% of total)
- Type-Token Ratio: [X]
- Avg Word Length: [X] characters
- Sophistication: [X]/10

Readability:
- Flesch Reading Ease: [X] ([interpretation])
- Grade Level: [X]
- Gunning Fog: [X]

--- QUALITATIVE ANALYSIS ---

Voice & Perspective:
- First Person: [X]%
- Second Person: [X]%
- Active Voice: [X]%
- Formality: [X]/10

Tone Characteristics:
- Authoritative: [Low/Med/High]
- Empathetic: [Low/Med/High]
- Enthusiastic: [Low/Med/High]
- Analytical: [Low/Med/High]

Vocabulary Profile:
- Power Words: [word1, word2, word3...]
- Transitional Phrases: [phrase1, phrase2...]
- Technical Terms: [term1, term2...]
- Signature Expressions: ["phrase1", "phrase2"]

Rhetorical Devices:
- Metaphors/Analogies: [Frequency]
- Questions: [Frequency] ([types])
- Data/Statistics: [Frequency]
- Storytelling: [Rare/Occasional/Frequent]

--- SIGNATURE PATTERNS ---

Unique Characteristics:
1. [Pattern 1]
2. [Pattern 2]
3. [Pattern 3]

Opening Style: [Description]
Closing Style: [Description]
Paragraph Flow: [Description]

--- STYLE FINGERPRINT ---

This voice is characterized by:
- [Defining trait 1]
- [Defining trait 2]
- [Defining trait 3]

Most distinctive elements:
- [Element 1]
- [Element 2]

--- RECOMMENDATIONS ---

To match this style:
1. [Recommendation 1]
2. [Recommendation 2]
3. [Recommendation 3]

To avoid:
- [Anti-pattern 1]
- [Anti-pattern 2]

--- SIMILARITY MARKERS ---

To validate AI-generated content matches this style, check for:
✓ [Marker 1]
✓ [Marker 2]
✓ [Marker 3]
✓ [Marker 4]
✓ [Marker 5]
```

## Integration

This analysis feeds into:
- Voice profile building
- Voice matching validation
- Style guide creation
- Content generation instructions

## Performance

- Target completion: <5 seconds per sample
- Minimum sample size: 200 words
- Recommended sample size: 500+ words
- Optimal sample size: 1000+ words
    ]]>
  </instructions>
</task>