email-style

email-style is a skill for Claude Code, Codex from vercel-labs/marketing-team-eve-template. It costs 27 tokens per session (873 once invoked), scanned A, original, MIT.

A writing guide for emails, newsletters, and broadcast messages, including subject lines and preview text. It sets rules for making the main point clear in the small amount of text people see first.

In plain words
What is it for?
Use it to write or edit email copy, choose a clear call to action, improve subject lines and preview text, and keep paragraphs easy to scan.
Why use it?
Email readers often decide whether to continue after the subject and opening line. The guide helps remove extra messages, vague wording, fake urgency, and long introductions.

Skill for Claude CodeCodex ✓ vendor

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

Good fit Use it to write or edit email copy, choose a clear call to action, improve subject lines and preview text, and keep paragraphs easy to scan.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vercel-labs/marketing-team-eve-template/email-style
About the project

vercel-labs/marketing-team-eve-template is a deployable team of AI marketing agents led by a coordinating agent that delegates launches, writing, and conversion work to specialists. Teams use it through Slack or a terminal to create blog drafts, social posts, and email campaigns in Notion, Typefully, and Resend, with approval required for irreversible actions. The catalogue skills and instructions define workflows for using this marketing team.

vercel-labs/marketing-team-eve-template · 436 stars · on GitHub · vercel.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 vercel-labs/marketing-team-eve-template --skill email-style
Clone the repo
git clone --depth 1 https://github.com/vercel-labs/marketing-team-eve-template

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-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/vercel-labs/marketing-team-eve-template/email-style/github.svg)](https://agentmods.dev/skills/vercel-labs/marketing-team-eve-template/email-style)
Your own site
<a href="https://agentmods.dev/skills/vercel-labs/marketing-team-eve-template/email-style"><img src="https://agentmods.dev/badge/skills/vercel-labs/marketing-team-eve-template/email-style/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-style

Your own site · 80×15
<a href="https://agentmods.dev/skills/vercel-labs/marketing-team-eve-template/email-style"><img src="https://agentmods.dev/badge/skills/vercel-labs/marketing-team-eve-template/email-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 873 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 $0.00027 $0.00873
Opus 5 $0.00014 $0.00436
Sonnet 5 $0.00005 $0.00175
Haiku 4.5 $0.00003 $0.00087

Measured 12d ago against content hash 2cd76fafe0f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

email-style 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 12d ago.

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.

agent/subagents/email/skills/email-style/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Email voice & style

An email arrives uninvited, in a stack of other mail, and gets a second of attention before someone decides to read or delete. Write for that second first and the body second.

  • One email, one job. Decide the single thing you want the reader to do before you write a word, and cut anything that competes with it. Two calls to action means most readers take neither.
  • Front-load everything. The point goes in the first line of the body, not after a warm-up paragraph. Many people read only the subject and the first line in a preview pane.
  • Short paragraphs, 1 to 3 sentences. More white space than you would use on a web page, because the reading column is narrower and the attention is thinner.
  • Write to one person. "You", not "our users". A newsletter that sounds like a broadcast gets treated like one.
  • No fake urgency, no fake scarcity, and no manufactured personalization. "Quick question" on a mail that is not a question trains people to distrust the sender, and it costs more than the open it buys.
  • Say who this is from and why they are getting it, early, when the list may not remember signing up.
  • Links carry their own meaning. "Read the migration guide", never "click here": link text is what screen readers announce out of context, and it is what a scanner reads instead of the sentence around it.
  • Every informative image needs alt text that describes it, and no image carries information that is not also in text. The Outlook desktop clients are the main remaining blockers of images, so an email whose point lives in a graphic arrives blank for those readers. Alt text describes; it never sells.
  • Always write the plain text version. It is what some clients render and some people prefer, and an autogenerated one reads as broken.

Subject line and preview text

They are one unit and they are the only copy most recipients will ever see. Write them together, after the body, when you know what the mail actually says.

  • Front-load. Put the real message in the first 35 to 40 characters, because that is what survives truncation on a phone. Front-loading is the one thing every source agrees on; the exact character count to aim for is contested, so don't treat one as a rule.
  • The preview text extends the subject; it never repeats it and never restates the headline. Use it for the second most interesting thing in the email.
  • Never leave preview text unset. The client fills the gap with whatever the HTML starts with, which is usually "View this email in your browser".
  • Specific beats clever. A subject that says what is inside outperforms a subject that hints at it, and it keeps its promise, which is what protects the next send.

Read the full file on GitHub · 39 lines

Files

What ships with it

3 files 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. 12d ago First seen · 39 lines · 27 tokens per session scan A 2cd76fafe0f7

Subscribe to this mod's changes

email-style is a skill published in the GitHub repository vercel-labs/marketing-team-eve-template (436 stars, last pushed 23d ago), licensed MIT. It adds 27 tokens to every session and 873 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

writing-quality

Writing-quality guardrails for any prose the agent drafts or edits: blog posts, page copy, Notion drafts, release notes, marketing text. Use this skill whenever writing or revising content meant for humans to read, to keep the prose natural, plain, and free of AI-sounding phrasing. Not needed for code, queries, or…

vercel-labs/sanity-copilot-eve-template · 73 tokens

sanity-best-practices

Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, Blueprints, and framework integrations such as Next.js, Nuxt, Astro, Remix, SvelteKit, Angular, Hydrogen, and the App SDK. Use this skill…

vercel-labs/sanity-copilot-eve-template · 153 tokens

portable-text-serialization

Render and serialize Portable Text to React, Svelte, Vue, Astro, HTML, Markdown, and plain text. Use when implementing Portable Text rendering in any frontend framework, building custom serializers for non-standard block types, converting Portable Text to HTML strings server-side, converting Portable Text to Markdown…

vercel-labs/sanity-copilot-eve-template · 80 tokens

portable-text-conversion

Convert HTML and Markdown content into Portable Text blocks for Sanity. Use when migrating content from legacy CMSs, importing HTML or Markdown into Sanity, building content pipelines that ingest external content, converting rich text between formats, or programmatically creating Portable Text documents. Covers…

vercel-labs/sanity-copilot-eve-template · 89 tokens

seo-aeo-best-practices

SEO and AEO best practices for metadata, Open Graph, sitemaps, robots.txt, hreflang, JSON-LD structured data, EEAT, and content optimized for search engines and AI answer surfaces. Use this skill when implementing page SEO, technical SEO, schema markup, international SEO, AI-overview readiness, or improving content…

vercel-labs/sanity-copilot-eve-template · 82 tokens

content-experimentation-best-practices

Content experimentation and A/B testing guidance covering experiment design, hypotheses, metrics, sample size, statistical foundations, CMS-managed variants, and common analysis pitfalls. Use this skill when planning experiments, setting up variants, choosing success metrics, interpreting statistical results, or…

vercel-labs/sanity-copilot-eve-template · 60 tokens