email-voice-profile

email-voice-profile is a skill for Claude Code, Codex from yc-software/qm. It costs 46 tokens per session (843 once invoked), scanned A, original, MIT.

A writing profile built from the user's own sent Gmail messages. It describes how they normally write so another tool can draft email in that style.

In plain words
What is it for?
Collecting and studying sent emails, separating internal and external writing, and creating or refreshing an email voice profile.
Why use it?
It avoids guessing the user's tone from a short conversation and gives email drafts a reference based on their real messages.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Collecting and studying sent emails, separating internal and external writing, and creating or refreshing an email voice profile.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yc-software/qm/email-voice-profile
About the project

QM is a shared work environment for coding agents that gives each employee and conversation an isolated workspace while allowing collaboration in Slack and on the web. Startups use it to run agents for individuals, teams, and company operations, with selectable harnesses and models. The catalogue entries extend QM with skills, instructions, and settings.

yc-software/qm · 14,693 stars · on GitHub · x.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add yc-software/qm --skill email-voice-profile
Clone the repo
git clone --depth 1 https://github.com/yc-software/qm

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for email-voice-profile

README.md
[![agentmods](https://agentmods.dev/badge/skills/yc-software/qm/email-voice-profile/github.svg)](https://agentmods.dev/skills/yc-software/qm/email-voice-profile)
Your own site
<a href="https://agentmods.dev/skills/yc-software/qm/email-voice-profile"><img src="https://agentmods.dev/badge/skills/yc-software/qm/email-voice-profile/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for email-voice-profile

Your own site · 80×15
<a href="https://agentmods.dev/skills/yc-software/qm/email-voice-profile"><img src="https://agentmods.dev/badge/skills/yc-software/qm/email-voice-profile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 843 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00843
Opus 5 $0.00023 $0.00421
Sonnet 5 $0.00009 $0.00169
Haiku 4.5 $0.00005 $0.00084

Measured 9d ago against content hash cb26398aca3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

email-voice-profile scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/fetch_sent.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills-seed/email-voice-profile/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Email voice profile

Use this when the user asks you to learn how they write email — "learn my voice", "build my email voice profile", "study my sent mail so you can draft for me" — or when email-draft-in-voice needs a profile that doesn't exist yet.

Personal DMs only. Sent mail is private; refuse to run this from a channel or group and offer to continue in the user's DM. The profile you produce lives in their personal workspace, so only their own conversations can read it.

1. Pull the corpus

python3 skills/email-voice-profile/scripts/fetch_sent.py --limit 300

This fetches the user's sent messages (their Google OAuth token is already on your computer; if it's missing, point them at the app-connect flow), strips quoted replies and signatures, drops automated and trivial messages, and writes one JSON line per email to voice/corpus/corpus.jsonl — each tagged internal or external by recipient domain. It prints corpus stats; if fewer than ~50 usable emails survive, tell the user the profile will be rough and ask whether to continue.

2. Study it

Read a deliberate spread, not just the top of the file: oldest and newest, internal and external, one-liners and long emails. You are looking for what is distinctive — patterns a generic professional emailer would not share.

Watch for a signature block: only ---delimited signatures are stripped, so a plain signature (name / title / phone) survives at the end of many bodies. Treat a verbatim recurring trailing block as the mail client's signature, not a chosen sign-off — note it in the profile so drafts never include it (Gmail appends it on send).

3. Write the profile

Write voice/email-voice-profile.md in the workspace with exactly these sections, every claim backed by observed frequency ("uses 'Best,' in 80% of external mail"), with 2–3 verbatim example lines each:

  • Register map — how tone shifts by audience (internal vs external, familiar vs cold), and how their length tracks the situation.
  • Openers & sign-offs — actual greetings and closings with rough frequencies, including when they use none.
  • Rhythm — sentence length, paragraph shape, how they open and end a body, use of fragments, lists, links.
  • Vocabulary & phrases — recurring words, pet phrases, how they hedge, how they say yes and no.
  • Punctuation & formatting quirks — dashes, ellipses, casing, emoji, bolding.
  • Hard rules — things true of nearly every email ("never opens with 'I hope this finds you well'", "always lowercase to teammates").
  • Anti-patterns — what they never do, plus the generic-AI tells to avoid (enthusiastic adjectives, "I'd be happy to", bullet-point answers to plain questions).

Read the full file on GitHub · 73 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 73 lines · 46 tokens per session scan A cb26398aca3f

Subscribe to this mod's changes

email-voice-profile is a skill published in the GitHub repository yc-software/qm (14,693 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 843 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.