SituationalMITOriginal

Ghostwrite In Voice

Drafts in a specific author's voice after reading 3-5 of their pieces — attribution-safe for transparency.

Entry verified April 20, 2026

The short answer

For agencies, ghostwriters, and internal comms teams. Reads sample pieces, extracts voice DNA, drafts new content that reads like the author wrote it. The ethical use is stated-up-front ghostwriting — not deception.

When to use it

Client ghostwriting. Executive comms. Translating between a brand's founder voice and a new team member's draft.

Setup

  1. 1

    Save as ~/.claude/commands/ghostwrite.md.

  2. 2

    Feed sample pieces. Skill produces a voice brief + draft.

  3. 3

    Add disclosure language to the output — 'draft ghostwritten per client brief'.

Example

You: /ghostwrite — attached: 3 Medium posts. Target: 1,200-word piece on vibe coding.
Claude: [analyses voice → writes draft that matches cadence, vocab, punctuation habits]

Source & attribution

Author
Bryan Collins (adapted from brand-voice pattern)
Licence
MIT
Type
Original

Original pattern published under MIT — attribution preserved by convention, not licence requirement.

Caveats

Ethical concerns — use only where ghostwriting is known and consented. Never for impersonation.

Browse more skills

47 skills across 10 categories, all licence-verified.