toneclone-cli

Write in the user's authentic voice using ToneClone. Generate emails, messages, social posts, and other content that sounds like the user — not generic AI. Use trained personas for different writing styles and knowledge cards for context. Requires ToneClone account and CLI setup at toneclone.ai.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "toneclone-cli" with this command: npx skills add jfox85/toneclone-cli

ToneClone CLI

Generate content in the user's authentic voice using their trained ToneClone personas.

Setup

ToneClone requires an account and trained personas. Get started at https://toneclone.ai

Install CLI (Homebrew):

brew tap toneclone/toneclone
brew install toneclone

Authenticate:

toneclone auth login

Writing Content

toneclone write --persona="<name>" --prompt="<what to write>"

With Knowledge Cards

toneclone write --persona="<name>" --knowledge="<card1>,<card2>" --prompt="<prompt>"

Examples

Chat reply:

toneclone write --persona="Chat" \
  --prompt="Reply to: 'Hey, are you free this weekend?' — say yes, suggest Saturday"

Work email:

toneclone write --persona="Work Email" --knowledge="Work,Scheduling" \
  --prompt="Follow-up email about project timeline, offer to schedule a call"

Social post:

toneclone write --persona="Twitter" \
  --prompt="Announce our new feature launch, keep it punchy"

Providing Context

Pass relevant context in the prompt for better results:

  • Thread/conversation being replied to
  • Background on the topic
  • Recipient info or relationship context

Quick Commands

TaskCommand
Write contenttoneclone write --persona="Name" --prompt="..."
List personastoneclone personas list
List knowledge cardstoneclone knowledge list
Check authtoneclone auth status

Personas vs Knowledge Cards

NeedUse
Different writing styleDifferent persona
Different context/factsDifferent knowledge card

More Info

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

yuqing-bitable-and-label

Incrementally sync data from XiaoAi API to Feishu Bitable and optionally auto-label records with machine-based type and sentiment annotations.

Registry SourceRecently Updated
General

张律师综合套装

张律师法律AI中台 - 中国首个开源法律AI技能库,涵盖刑事辩护、民商事诉讼、合同审查全流程

Registry SourceRecently Updated
General

刑事辩护

刑事辩护全流程AI助手 - 6大阶段21个模板,从接案到执行全覆盖

Registry SourceRecently Updated