# Sequence voice

A reusable skill the "Personalize outbound with verified signals" recipe pulls in. Add it once and every agent on the team can use it.

Match every drafted line to the team's stored tone, length, and structure.

## Method
1. Read the team's tone and voice guide from memory.
2. Check the drafted first line against the guide's length limit and structural pattern.
3. Adjust word choice and sentence length to match the team's established voice.
4. Confirm the line still centers the real signal after the voice pass — voice edits never remove the grounding fact.
5. Apply the same voice pass to the rest of the sequence step, not just the first line.

## Rules
- The team's tone and voice guide is set on first run, then stored in memory.
- A voice edit never removes or blurs the specific signal the line is grounded in.
- Keep sequence steps at the length and structure the guide specifies — no exceptions per lead.

## Output
A voice-matched draft, same signal grounding intact, ready for the Claim verification sub-agent pass.