Part of Run GTM Workflows With AI Agent Skills
Productivity Blueprint
Safety checkedTrain Voice Profiles From Writing Samples
Analyzes real writing samples and generates a reusable voice profile that email-writer and other skills can apply for tone consistency.
What problem does this solve?
Creates a voice profile from your actual writing by scanning samples across emails, tweets, Slack messages, LinkedIn posts, or any writing type you provide. The skill runs an 8-pass analysis to extract tone, word choice, rhythm, phrases you use repeatedly, and anti-patterns you avoid. It then saves a structured profile to .agents/voice-profiles/{name}.md that email-writer reads automatically, so every email the agent drafts in your voice follows your patterns, not a generic tone.
How does it work?
You provide 5-30 writing samples (ideally across multiple types: emails, tweets, Slack). The skill reads all of them, runs 8 analysis passes to identify tone, punctuation patterns, favorite phrases, anti-patterns, and context-specific variations (how you sound in cold vs warm email vs informal Slack). It assembles a profile with sections for tone principles, phrase preferences, anti-patterns to avoid, and tone variations by context. The profile saves to .agents/voice-profiles/{name}.md. On future runs, email-writer loads this profile and applies the patterns so emails sound like you, not an AI generic.
Included Skills
No skills in this group
What's required to run this?
No API keys required. Saves profiles to .agents/voice-profiles/{name}.md. Reads reference files from the installed skill directory: analysis-framework.md (the 8-pass extraction logic) and profile-template.md (output structure). Email-writer automatically discovers and loads profiles from .agents/voice-profiles/ if they exist.
Key Features
8-Pass Analysis Engine
Systematic extraction across tone, word choice, punctuation, rhythm, phrases, anti-patterns, context variations, and meta-patterns. Each pass catches different signals.
Multi-Format Support
Works with any writing type: emails, tweets, Slack messages, LinkedIn posts, memos, customer service replies. Extracts patterns from all of them.
Tone by Context
Identifies how you sound differently in cold outreach vs warm email vs informal channels, and captures those variations in the profile.
Profile Updates
Retrain with new samples to update an existing profile. The skill merges new findings with old, keeps patterns that persist, drops contradicted ones.
About This Blueprint
- Industry
- Technology
More Blueprints to explore
⭐ Ask Nicely : Find your next reviewers
Pick promoters from your CRM, remove accounts with open escalations, overdue billing or a recent review, then create the G2 review campaign after you approve the list, send method and any incentive.
G2CRMSurvey or CS platform+4 moreCharlie Albuery
🤝 You Said We Did : Align your roadmap to real user feedback
Group recent G2 reviews into themes, check each theme against tickets in your work tracker, and return a ranked one-page brief that lists the themes with no ticket first.
G2Work trackerResearch repository+3 moreCharlie Albuery
👀 Wandering Eyes : Identify churn risk early
Match accounts renewing soon in your CRM to G2 buyer intent on competitors and your category, check usage, support and meetings, then rank the accounts and brief the CSM. Runs as a weekly sweep or on one named account.
G2CRMProduct usage analytics+4 moreCharlie Albuery