calibrate-my-voice

Name: calibrate-my-voice
Availability: InStock
Author: akiotanaka847

Extract tone cues from recent sent customer replies to write config/voice.md.

2|Updated May 8, 2026

Search Tags:#writing style #customer support #Composio #tone analysis #voice calibration #inbox integration #support automation

Ready to run

npx skills add https://github.com/akiotanaka847/qaio-desktop --skill calibrate-my-voice

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: calibrate-my-voice
Source: https://github.com/akiotanaka847/qaio-desktop/tree/main/store/agents/support/.agents/skills/calibrate-my-voice
Command: npx skills add https://github.com/akiotanaka847/qaio-desktop --skill calibrate-my-voice

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It eliminates the mismatch between your natural writing style and the tone of future customer replies by learning from your recent sent messages and distilling repeatable voice cues.

Core Features & Use Cases

Inbox-based voice training: Pulls 10–20 of your recent outbound customer replies from a connected inbox (Gmail/Outlook) or helpdesk (Intercom/Help Scout/Zendesk) to learn real phrasing and tone.
Tone and style distillation: Detects greeting patterns, sentence rhythm, formality, sign-offs, and recurring phrases, then extracts a set of “never use” forbidden phrases.
Config + context updates: Writes a voice profile to config/voice.md, updates context/support-context.md to reference it, and logs the calibration in config/context-ledger.json and outputs.json for traceability.
When to use: Run after set-up-my-support-info when the voice section is TBD, and re-run when tone drifted or you want to re-learn from newer replies.

Quick Start

Connect your inbox (or helpdesk) and run the skill “calibrate my voice” to generate config/voice.md and update your support voice settings.

Frequently Asked Questions about calibrate-my-voice

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate customer support writing style calibration from past replies?▼

To calibrate your customer support writing style, this Skill connects to your inbox or helpdesk via Composio, pulls 10–20 recent sent replies, and extracts tone cues like greetings, sentence rhythm, and sign-offs. It then writes a voice profile to config/voice.md for future drafts.

Can I use my Gmail or Intercom inbox to train my support voice?▼

Yes, you can train your support voice using Gmail, Outlook, Intercom, Help Scout, or Zendesk. The Skill requires a connected inbox or helpdesk via Composio to pull your recent outbound customer replies and distill your natural phrasing and tone.

How does tone analysis work for matching future customer support drafts?▼

Tone analysis works by detecting greeting patterns, sentence rhythm, formality, sign-offs, and recurring phrases from your sent messages. It also identifies forbidden phrases to avoid, ensuring future customer support drafts match your actual writing voice.

What is the best way to fix tone drift in customer lifecycle communication?▼

The best way to fix tone drift is to re-run the voice calibration process. The Skill extracts fresh voice cues from your newest sent customer replies, updates the config/voice.md file, and logs the changes in config/context-ledger.json and outputs.json for traceability.

Do I need a connected inbox to analyze my writing voice for support automation?▼

Yes, a connected inbox or helpdesk via Composio is required. The Skill needs to pull 10–20 real outbound customer reply samples to extract your repeatable voice cues and generate an accurate writing style profile.

When should I run support voice calibration after setting up my support info?▼

You should run voice calibration after your support info setup is complete, specifically when the voice section is TBD. Re-running is recommended whenever you notice tone drift in your lifecycle communication or want to re-learn from newer sent replies.