skills/voice-authenticity/SKILL.md
# Voice Authenticity Reviewer ## Purpose Review any written content for alignment with authentic speaking and writing voice using analyzed patterns from 7 meeting transcripts and strategic memos. ## When to Use This Skill - Before sharing strategic memos with leadership - Before sending important emails - When drafting presentation scripts - When reviewing documentation for external sharing - As part of Writing /produce-memo workflow (Step 6) - Anytime voice authenticity verification is needed
npx skillsauth add jeffvincent/claude-config skills/voice-authenticityInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Review any written content for alignment with authentic speaking and writing voice using analyzed patterns from 7 meeting transcripts and strategic memos.
CRITICAL: Read the complete voice patterns file before doing anything else:
Read: /Users/jvincent/Projects/Personal/Voice-Patterns/analysis/voice-patterns-v1.md
This 665-line analysis is the foundation for the entire review. Do not skim it.
Content can be provided three ways:
If no content provided, ask: "What content would you like me to review for voice authenticity?"
Identify the content type to calibrate the review:
Read: instructions/context-variations.md for detailed guidance per type.
Systematically check all five voice dimensions from instructions/voice-dimensions.md:
For each issue found, record: location + current text + pattern violated + concrete rewrite.
Follow the tone guidelines in instructions/reviewer-tone.md — be direct, constructive, and actionable.
Before finalizing, run the draft through the three reviewer personas in eval/advisory-board.md:
Synthesize their feedback. Adjust priorities if the personas flag something the initial pass missed.
Use the output template in templates/review-output.md to structure the final review. Include:
instructions/confidence-levels.md)Before delivering, run through every item in eval/checklist.md. All items must pass.
After delivering the review, follow the prompt in instructions/evolution-tracking.md to offer logging new voice insights to the refinements tracker.
examples/good/strategic-memo-review.md — annotated example of a thorough, specific reviewexamples/bad/vague-review.md — what to avoidvoice-authenticity/
├── Skill.md ← You are here (orchestrator)
├── instructions/
│ ├── voice-dimensions.md ← 5 analysis dimensions
│ ├── context-variations.md ← Memo vs email vs presentation guidance
│ ├── confidence-levels.md ← High/Medium/Low criteria
│ ├── reviewer-tone.md ← How to deliver feedback
│ └── evolution-tracking.md ← Post-review pattern logging
├── templates/
│ └── review-output.md ← Output format template
├── examples/
│ ├── good/
│ │ └── strategic-memo-review.md ← Annotated good review
│ └── bad/
│ └── vague-review.md ← Anti-pattern to avoid
└── eval/
├── checklist.md ← Pass/fail validation
└── advisory-board.md ← 3 reviewer personas
tools
Render a video clip with captions overlaid, using the Remotion captioner at `/Users/jvincent/Projects/remotion-captioner/`. Use when user provides a video file and wants to add captions/subtitles, mentions "caption this video", "add captions", "burn in subtitles", or provides a video + SRT file pair.
development
Upload video files to Wistia projects using the Data API. Use when user wants to upload videos to their Wistia account for hosting, transcription, or sharing.
development
Transcribe voice memos to text using Whisper. Use when user provides audio/video files (.m4a, .mp3, .mov, etc.) and asks to transcribe them into text and SRT format with timestamps.
data-ai
Analyze customer interview transcripts (SRT or plain text) to generate thematic breakdowns with summary, quotes, topics, timestamps, and full transcript. Use when given video transcripts or asked to create chapter markers.