escrever-variantes-de-copy

escrever-variantes-de-copy is a skill for Claude Code, Codex from gethouston/houston. It costs 96 tokens per session (4,662 once invoked), scanned A, original, MIT.

A copywriting tool that produces alternative headlines, button labels, ad text, or shorter versions of existing copy. Each option is based on a real customer quote or a claim from the positioning document.

In plain words
What is it for?
Use it to create headline pairs, calls to action, ad copy, or line-by-line copy edits. The drafts can be prepared for a named page, campaign, and advertising platform.
Why use it?
It gives you several grounded wording choices without relying on invented claims or generic marketing language. This makes it easier to compare options for a specific page or campaign.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to create headline pairs, calls to action, ad copy, or line-by-line copy edits. The drafts can be prepared for a named page, campaign, and advertising platform.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gethouston/houston/escrever-variantes-de-copy
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 gethouston/houston --skill escrever-variantes-de-copy
Clone the repo
git clone --depth 1 https://github.com/gethouston/houston

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 escrever-variantes-de-copy

README.md
[![agentmods](https://agentmods.dev/badge/skills/gethouston/houston/escrever-variantes-de-copy/github.svg)](https://agentmods.dev/skills/gethouston/houston/escrever-variantes-de-copy)
Your own site
<a href="https://agentmods.dev/skills/gethouston/houston/escrever-variantes-de-copy"><img src="https://agentmods.dev/badge/skills/gethouston/houston/escrever-variantes-de-copy/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 escrever-variantes-de-copy

Your own site · 80×15
<a href="https://agentmods.dev/skills/gethouston/houston/escrever-variantes-de-copy"><img src="https://agentmods.dev/badge/skills/gethouston/houston/escrever-variantes-de-copy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,662 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 $0.00096 $0.04662
Opus 5 $0.00048 $0.02331
Sonnet 5 $0.00019 $0.00932
Haiku 4.5 $0.00010 $0.00466

Measured 9d ago against content hash 2fe6fb0914e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

escrever-variantes-de-copy 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.

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.

store/agents-i18n/pt/marketing/.agents/skills/escrever-variantes-de-copy/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Escrever variantes de copy

Uma skill para toda necessidade de variantes de copy. O parâmetro job escolhe o formato, as regras de fonte e o formato de saída. Regra compartilhada entre todas as tarefas: cada variante fundamentada em uma citação real de cliente ou em uma afirmação do documento de posicionamento - nada de linguagem de marketeiro, nada de invenção.

Parâmetro: job

  • headlines - 10 pares de título + subtítulo para uma página nomeada, cada um citando uma frase textual de cliente, com os 3 melhores para testar primeiro. Saída: headline-variants/{page-slug}-{YYYY-MM-DD}.md.
  • ctas - 5-7 variantes de texto de botão de CTA, cada uma pareada com a objeção que responde e o resultado que sugere. Saída: cta-variants/{page-slug}-{YYYY-MM-DD}.md.
  • ad-copy - 10 títulos + 5 descrições + 3 conceitos criativos para uma campanha e plataforma nomeadas, respeitando os limites de caracteres da plataforma, cada um fundamentado em uma citação de origem. Saída: ad-copy/{campaign-slug}.md.
  • edit - revisão de enxugamento em cinco varreduras sobre um copy existente (clareza, voz, especificidade, comprimento, CTAs) com antes/depois/porquê para cada linha alterada. Saída: copy-edits/{page-slug}-{YYYY-MM-DD}.md.

Você nomeia a tarefa em linguagem simples ("10 títulos para minha página inicial", "um CTA melhor para o cadastro", "copy de anúncio para o lançamento do Q2", "enxugue minha página sobre") -> eu infiro. Ambíguo -> faço UMA pergunta nomeando as quatro tarefas.

Quando usar

headlines:

  • "10 variantes de título para minha página inicial"
  • "Ganchos alternativos de hero para a landing page da campanha {campaign}"
  • "Opções de título para a página de preços"
  • Costuma vir depois de write-my-page-copy ou audit-a-surface (surface=landing-page) quando o título é apontado como a correção.

ctas:

  • "Um CTA melhor para meu botão de cadastro"
  • "Variantes de CTA para a página de preços"
  • "O que o botão de demo deveria dizer?"
  • Costuma vir depois de write-copy-variants (job=headlines) ou write-copy-variants (job=edit) quando o CTA é apontado como fraco.

Read the full file on GitHub · 180 lines

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 · 180 lines · 96 tokens per session scan A 2fe6fb0914e5

Subscribe to this mod's changes

escrever-variantes-de-copy is a skill published in the GitHub repository gethouston/houston (113 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 4,662 once invoked, about $0.0005 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 2026-09-03.

Related

Other skills, from other repositories

magazine-web-ppt

For marketing and gtm work: bind launches, campaigns, events, and brand plans to growth and pipeline outcomes. Built around the core query "annual-marketing-plan", with GTM strategy lead judgment, buyer-ready proof, and this outcome: approve launch plan, campaign budget, or GTM motion.

nexu-io/open-design · 67 tokens

html-ppt-zhangzara-coral

OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.

nexu-io/open-design · 55 tokens

ads

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…

coreyhaines31/marketingskills · 175 tokens

attribution

When the user wants to figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model, or reconcile conflicting numbers across tools. Also use when the user mentions "attribution," "attribution model," "first-touch vs last-touch," "multi-touch," "which channel drives…

coreyhaines31/marketingskills · 220 tokens

co-marketing

When the user wants to find co-marketing partners, plan joint campaigns, or brainstorm partnership opportunities. Use when the user says 'co-marketing,' 'partner marketing,' 'joint campaign,' 'who should we partner with,' 'integration marketing,' 'cross-promotion,' 'collaborate with another company,' 'partnership…

coreyhaines31/marketingskills · 92 tokens

analytics

When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," "tracking plan," "how do I measure this,"…

coreyhaines31/marketingskills · 152 tokens