Menu
Extract voice patterns from transcripts - speaking style, phrases, vocabulary for authentic author profiles
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | voice-extractor |
| description | Extract voice patterns from transcripts - speaking style, phrases, vocabulary for authentic author profiles |
Extract authentic voice characteristics from transcripts to enhance author profiles.
Transform transcript data (podcasts, interviews, meetings, videos) into actionable writing guidelines that capture an author's authentic voice, making AI-generated content sound natural and personal.
Accept transcripts in these formats:
Speaker: text[00:01:23] Speaker: text or 59:54 Speaker: text[Speaker]: text[17:30, 12/6/2025] Speaker: textIf user provides audio/video without transcript: Suggest transcription services:
# List speakers in transcript
bun run "${CLAUDE_PLUGIN_ROOT}"/scripts/voice-extractor.ts --list-speakers transcript.txt
# Extract for specific speaker
bun run "${CLAUDE_PLUGIN_ROOT}"/scripts/voice-extractor.ts --speaker "Name" transcript.txt
# Multiple transcripts (more data = better profile)
bun run "${CLAUDE_PLUGIN_ROOT}"/scripts/voice-extractor.ts --speaker "Name" t1.txt t2.txt t3.txt
# Output JSON for direct use with author profiles
bun run "${CLAUDE_PLUGIN_ROOT}"/scripts/voice-extractor.ts --speaker "Name" --json transcript.txt
The extracted data enhances these author fields:
| Extracted Data | Maps To |
|---|---|
| Communication style | tone.formality, tone.opinionated |
| Characteristic expressions | phrases.signature |
| Sentence starters | phrases.signature |
| Signature vocabulary | vocabulary.use_freely |
| Speaking style | notes |
After automated extraction, read transcript samples to identify:
# 1. Extract voice data
/article-writer:author analyze --speaker "John" transcripts/*.txt
# 2. Review and confirm extraction
# Claude will show extracted patterns
# 3. Add identity info
/article-writer:author add
# Answer: name, role, expertise, languages
# 4. Merge voice data
# Claude will combine extracted + manual data
# 1. Extract from new transcripts
/article-writer:author analyze --speaker "John" --author-id mwguerra new_podcast.txt
# 2. Review changes
# Claude shows what will be updated
# 3. Confirm merge
# Voice analysis data added to existing profile
{
"voice_analysis": {
"extracted_from": ["podcast_ep1.txt", "interview.txt"],
"sample_count": 156,
"total_words": 12450,
"sentence_structure": {
"avg_length": 14.5,
"variety": "moderate length, conversational",
"question_ratio": 12.3
},
"communication_style": [
{ "trait": "enthusiasm", "percentage": 28.5 },
{ "trait": "analytical", "percentage": 24.1 },
{ "trait": "directness", "percentage": 18.7 }
],
"characteristic_expressions": [
"you know",
"I think",
"the thing is",
"at the end of the day"
],
"sentence_starters": [
"I think",
"So the",
"And then",
"But the"
],
"signature_vocabulary": [
"actually",
"basically",
"approach",
"strategy",
"implementation"
],
"analyzed_at": "2025-01-15T10:00:00Z"
},
"suggested_updates": {
"tone": {
"formality": 5,
"opinionated": 7
},
"phrases": {
"signature": ["you know", "the thing is", "at the end of the day"]
},
"vocabulary": {
"use_freely": ["approach", "strategy", "implementation"]
}
}
}
# Voice Analysis: John Smith
*Analyzed 156 speaking turns, 12,450 words*
## Speaking Style
- **Sentence length**: Moderate (~14 words avg)
- **Questions**: Uses questions occasionally (12%)
- **Vocabulary richness**: 45% unique words
## Communication Style
- **Primary**: Enthusiastic (28%)
- **Secondary**: Analytical (24%)
- **Tertiary**: Direct (19%)
## Characteristic Expressions
- "you know" (used 45x)
- "I think" (used 38x)
- "the thing is" (used 22x)
## Sentence Starters
- "I think..." (28x)
- "So the..." (19x)
- "And then..." (15x)
## Signature Vocabulary
**actually** (67x), **basically** (45x), **approach** (34x)
---
## Recommendations for Author Profile
Based on this analysis:
- Set formality to 5 (conversational but professional)
- Set opinionated to 7 (confident, uses "I think" but states opinions)
- Add signature phrases: "you know", "the thing is"
- Use vocabulary freely: approach, strategy, implementation
Good voice analysis needs:
Low data warning:
⚠️ Limited data: Only 23 speaking turns found.
Results may not fully represent speaking patterns.
Consider adding more transcripts.
Analyze, test, and prepare apps for production with Pest and Playwright testing
This skill should be used when encountering errors during development, when the user mentions an error, when debugging issues, or when asked to "fix an error", "debug this", "why is this failing", "solve this error". Provides intelligent error recognition, solution lookup from past errors, and error logging for future reference.
This skill should be used when the user asks to "manage notes", "update vault", "add to obsidian", "document in vault", "search my notes", "find related notes", or when working with Obsidian vault files. Also triggers when discussing knowledge management, note organization, or when Claude Code auto-captures commits, tasks, or component creation.
This skill should be used when conducting PRD interviews, creating product requirements documents, planning new features, documenting bug fixes, or when using commands like "/prd-builder:prd", "/prd-builder:feature", "/prd-builder:bugfix", or "/prd-builder:refine". Provides comprehensive interview frameworks and question templates for building thorough PRDs.
Execute complete user flow testing with Playwright MCP, testing end-to-end journeys through the application
Systematically test all pages for errors, functionality, and proper rendering using Playwright MCP