Voice DNA Creator
A skill that reads three to ten of your texts and extracts your writing profile: sentence rhythm and length, recurring vocabulary, words you never use, how you open and close. The profile is stored in a file (`context/voice-dna.json` in the original repository) that the other writing skills read before each text. It lives in a community repository of co-writing skills, next to templates for LinkedIn, X or Substack.
Strengths
- Starts from your real texts, not from instructions like 'professional and engaging tone'
- The profile lives in a file read before every draft, so you stop re-pasting your examples
- Also records the words you never use, often more telling than the ones you repeat
Limitations
- Captures style, not substance: a text with the right rhythm can still be empty
- Community repository with no stated licence, designed to be opened in an editor such as Cursor or Claude Code
Best for
- Someone who publishes every week and re-pastes old posts before each draft
- A founder delegating part of their posts who wants the person or agent writing to start from the same profile
- A team publishing under a brand name that wants to pin a shared tone rather than argue about it on every text