Style Learner

Style Learning Skill

**A style profile is metrics plus exemplars. Either alone

is too weak to reproduce a voice.**

Extract style from exemplar text and codify it as a profile

that downstream skills (scribe:doc-generator,

scribe:voice-generate) can apply consistently.

When NOT To Use

• Extracting a person's voice from their samples (use

scribe:voice-extract)

• Reviewing text against a profile (use scribe:voice-review)

Approach: Feature Extraction and Exemplar Reference

The skill combines two methods because each fails alone:

• Feature Extraction: quantifiable metrics (sentence

length distribution, vocabulary complexity, structural

patterns). Reproducible but soulless.

• Exemplar Reference: specific passages that

demonstrate the target style. Vivid but hard to apply

at scale.

Together they form a profile precise enough to score new

text and rich enough to guide rewrites. Metrics catch what

exemplars miss. Exemplars carry what metrics flatten.

Required TodoWrite Items

• style-learner:exemplar-collected - Source texts gathered
• style-learner:features-extracted - Quantitative metrics computed
• style-learner:exemplars-selected - Representative passages identified
• style-learner:profile-generated - Style guide created
• style-learner:validation-complete - Profile tested against new content

Step 1: Collect Exemplar Text

Gather representative samples of the target style.

Minimum requirements:

• At least 1000 words of exemplar text
• Multiple samples preferred (shows consistency)
• Same genre/context as target output

## Exemplar Sources

| Source | Word Count | Type |
|--------|------------|------|
| README.md | 850 | Technical |
| blog-post-1.md | 1200 | Narrative |
| api-guide.md | 2100 | Reference |

Step 2: Feature Extraction

Load: @modules/feature-extraction.md

Vocabulary Metrics

| Metric | How to Measure | What It Indicates |

|--------|----------------|-------------------|

| Average word length | chars/word | Complexity level |

| Unique word ratio | unique/total | Vocabulary breadth |

| Jargon density | technical terms/100 words | Audience level |

| Contraction rate | contractions/sentences | Formality |

Sentence Metrics

| Metric | How to Measure | What It Indicates |

|--------|----------------|-------------------|

| Average length | words/sentence | Complexity |

| Length variance | std dev of lengths | Natural variation |

| Question frequency | questions/100 sentences | Engagement style |

| Fragment usage | fragments/100 sentences | Stylistic punch |

Structural Metrics

| Metric | How to Measure | What It Indicates |

|--------|----------------|-------------------|

| Paragraph length | sentences/paragraph | Density |

| List ratio | bullet lines/total lines | Format preference |

| Header depth | max header level | Organization style |

| Code block frequency | code blocks/1000 words | Technical density |

Punctuation Profile

| Metric | Normal Range | Style Indicator |

|--------|--------------|-----------------|

| Em dash rate | 0-3/1000 words | Parenthetical style |

| Semicolon rate | 0-2/1000 words | Formal complexity |

| Exclamation rate | 0-1/1000 words | Enthusiasm level |

| Ellipsis rate | 0-1/1000 words | Trailing thought style |

Step 3: Exemplar Selection

Load: @modules/exemplar-reference.md

Select 3-5 passages (50-150 words each) that best represent the target style.

Selection criteria:

• Demonstrates characteristic sentence rhythm
• Shows typical vocabulary choices
• Represents the desired tone
• Avoids atypical or exceptional passages

Exemplar Template

### Exemplar 1: [Label]
**Source**: [filename, lines X-Y]
**Demonstrates**: [what aspect of style]

> [Quoted passage]

**Key characteristics**:
- [Observation 1]
- [Observation 2]

Step 4: Generate Style Profile

Combine extracted features and exemplars into a usable style guide.

Profile Format

# Style Profile: [Name]
# Generated: [Date]
# Exemplar sources: [List]

voice:
  tone: [professional/casual/academic/conversational]
  perspective: [first-person/third-person/second-person]
  formality: [formal/neutral/informal]

vocabulary:
  average_word_length: X.X
  jargon_level: [none/light/moderate/heavy]
  contractions: [avoid/occasional/frequent]
  preferred_terms:
    - "use" over "utilize"
    - "help" over "facilitate"
  avoided_terms:
    - delve
    - leverage
    - comprehensive

sentences:
  average_length: XX words
  length_variance: [low/medium/high]
  fragments_allowed: [yes/no/sparingly]
  questions_used: [yes/no/sparingly]

structure:
  paragraphs: [short/medium/long] (X-Y sentences)
  lists: [prefer prose/balanced/prefer lists]
  headers: [descriptive/terse/question-style]

punctuation:
  em_dashes: [avoid/sparingly/freely]
  semicolons: [avoid/sparingly/freely]
  oxford_comma: [yes/no]

exemplars:
  - label: "[Exemplar 1 label]"
    text: |
      [Quoted passage]
  - label: "[Exemplar 2 label]"
    text: |
      [Quoted passage]

anti_patterns:
  - [Pattern to avoid 1]
  - [Pattern to avoid 2]

Step 5: Validation

Test the profile against new content:

• Generate sample content using the profile
• Compare metrics to extracted features
• Have user evaluate voice/tone match
• Refine profile based on feedback

Validation Checklist

• [ ] Metrics within 20% of exemplar averages
• [ ] No anti-pattern violations
• [ ] Tone matches user expectation
• [ ] Vocabulary aligns with exemplars
• [ ] Structure follows profile guidelines

Usage in Generation

When generating new content, reference the profile:

Generate [content type] following the style profile:
- Voice: [from profile]
- Sentence length: target ~[X] words, vary between [Y-Z]
- Use exemplar passage as tone reference:
  > [exemplar quote]
- Avoid: [anti-patterns from profile]

Module Reference

• See modules/style-application.md for applying learned styles to new content

Integration with slop-detector

After generating content, run slop-detector to verify:

• No AI markers introduced
• Style metrics match profile
• Anti-patterns avoided

Exit Criteria

• Style profile document created
• At least 3 exemplar passages included
• Quantitative metrics extracted
• Anti-patterns from slop-detector integrated
• Validation test passed