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.
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.
npx skills add vercel-labs/marketing-team-eve-template --skill messaginggit clone --depth 1 https://github.com/vercel-labs/marketing-team-eve-templateWrote 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.
[](https://agentmods.dev/skills/vercel-labs/marketing-team-eve-template/messaging)<a href="https://agentmods.dev/skills/vercel-labs/marketing-team-eve-template/messaging"><img src="https://agentmods.dev/badge/skills/vercel-labs/marketing-team-eve-template/messaging/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.
<a href="https://agentmods.dev/skills/vercel-labs/marketing-team-eve-template/messaging"><img src="https://agentmods.dev/badge/skills/vercel-labs/marketing-team-eve-template/messaging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 7 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.00798 |
| Opus 5 | $0.00016 | $0.00399 |
| Sonnet 5 | $0.00006 | $0.00160 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
messaging 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Messaging
Messaging is positioning made reusable. The test of a good messaging set is not whether it reads well but whether someone else can write a page from it without asking you a question.
Positioning has to be settled first. Writing messaging on unsettled positioning produces lines that contradict each other, and nobody can tell why.
The hierarchy
Three levels, each derived from the one above:
- The core message. One sentence on what the product does and for whom. Everything else has to be consistent with it. This is what a customer should be able to repeat after one visit.
- Three or four pillars. The reasons the core message is true. Each pillar is a benefit, not a feature, and each is separable: if two pillars could be merged, you have too many.
- Proof under each pillar. The feature that delivers it, and the evidence that it works.
Three or four pillars, not seven. A pillar nobody can recall isn't doing any work, and past four they stop being distinct.
Writing a claim
Every claim carries a benefit, the mechanism, and proof. Drop the mechanism and it's a boast; drop the proof and it's unfalsifiable.
- Weak: "Dramatically faster reporting."
- Better: "Reports run in seconds because the query hits a materialized view rather than the live table."
- With proof: "...which took one customer's month-end report from four minutes to nine seconds."
Grade every claim before it ships. proven means there's a named customer, a measured number, or a public doc behind it. plausible means it follows from how the product works but nothing external confirms it. assumption means you believe it and can't show it. Write the grade down. The specialists downstream will assert whatever you hand them, so an ungraded assumption becomes a published claim.
Value propositions per audience
One core message, several audiences. The message doesn't change; the benefit you lead with does, because different people are buying different things.
For each audience, write down what they're accountable for, what they lose today, the pillar that matters most to them, and the objection they raise. An economic buyer and a hands-on user get different leads even when the product is identical.
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.
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.
- 11d ago First seen · 54 lines · 32 tokens per session scan A c0298f46cdf3
messaging is a skill published in the GitHub repository vercel-labs/marketing-team-eve-template (435 stars, last pushed 22d ago), licensed MIT. It adds 32 tokens to every session and 798 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.
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…
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…
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…
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…
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…
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…