Um fluxo de trabalho para pesquisa e planejamento de SEO, a prática de melhorar a presença de um site nos resultados de busca, além de GEO e anúncios no Google.

Serve para pesquisar palavras-chave, analisar concorrentes, planejar conteúdo, otimizar páginas, acompanhar o Google Meu Negócio, melhorar a presença em assistentes de IA e estruturar campanhas do Google Ads.

Ajuda a descobrir o que as pessoas procuram, entender a concorrência e transformar esses dados em ações de conteúdo e publicidade.

seo — Skill for Claude Code and Codex by felipenalves

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 felipenalves/InvOS --skill seo

Clone the repo

git clone --depth 1 https://github.com/felipenalves/InvOS

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/felipenalves/invos/seo.svg)](https://agentmods.dev/skills/felipenalves/invos/seo)

Your own site

<a href="https://agentmods.dev/skills/felipenalves/invos/seo"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/seo.svg" alt="Measured on agentmods" height="20"></a>

Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,002 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00138	$0.03002
Opus 5	$0.00069	$0.01501
Sonnet 5	$0.00028	$0.00600
Haiku 4.5	$0.00014	$0.00300

Measured 7d ago against content hash e799e72bfc46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

seo 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 7d 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.

.agents/skills/seo/SKILL.md · 311 lines

How it starts

The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/seo — SEO completo + GEO + Google Ads

Dependências

Contexto do negócio: _memoria/empresa.md
Tom de voz: _memoria/preferencias.md
Estratégia atual: _memoria/estrategia.md
Ferramentas: WebSearch, WebFetch (nativos)
Outputs vão em: marketing/seo/

Workflow

Passo 1 — DEMANDA: O que as pessoas buscam nesse nicho?

Objetivo: Entender se existe demanda real e como as pessoas buscam.

Ler _memoria/empresa.md pra extrair: produtos/serviços, região, público-alvo, diferenciais
Gerar uma lista inicial de 30-50 termos-semente baseados em:
- Categorias de produto/serviço
- Intenção de busca (informacional, comercial, transacional)
- Localização (cidade, região, estado)
- Uso final / contexto do cliente
Usar WebSearch pra cada grupo de termos:
- Buscar "[termo] site:trends.google.com" pra ver sazonalidade
- Buscar "[termo]" pra ver o que aparece (orgânico, ads, maps)
- Buscar "[termo] related searches" pra expandir a lista
Classificar cada termo por:
- Volume estimado: alto / médio / baixo / micro
- Intenção: informacional, comercial, transacional, navegacional
- Dificuldade: quantos concorrentes fortes aparecem?
- Relevância: direto (produto exato) / indireto (nicho relacionado) / tangencial

Output: Salvar em marketing/seo/01-pesquisa-demanda.md com:

Tabela de termos classificados
Top 10 termos prioritários (volume + intenção transacional + baixa concorrência)
Termos sazonais
Termos descartados e por quê

Passo 2 — CONCORRÊNCIA: Quem aparece pra essas buscas?

Objetivo: Mapear quem domina os resultados e onde estão os gaps.

Pegar os top 10 termos do Passo 1
Pra cada termo, usar WebSearch e analisar:
- Top 5 resultados orgânicos: quem são, que tipo de página (site institucional, marketplace, blog, diretório)
- Resultados do Maps/Local Pack: quem aparece, quantas avaliações, nota
- Google Ads: alguém anuncia? qual a copy?
Pra cada concorrente relevante (máx 5-8), usar WebFetch pra analisar:
- Estrutura do site (páginas, blog, catálogo)
- Meta titles e descriptions das páginas principais
- Conteúdo: falam de quê? com que profundidade?
- Schema markup: usam dados estruturados?
- GMB: perfil completo? fotos? posts? avaliações?
Identificar:
- Gaps: o que nenhum concorrente faz bem
- Oportunidades: termos onde ninguém domina
- Ameaças: concorrentes fortes demais pra competir de frente
- Benchmark: o padrão mínimo que o negócio precisa atingir

Read the full file on GitHub · 311 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.

7d ago First seen · 311 lines · 138 tokens per session scan A e799e72bfc46

Subscribe to this mod's changes

seo is a skill published in the GitHub repository felipenalves/InvOS (5 stars, last pushed 4d ago), licensed MIT. It adds 138 tokens to every session and 3,002 once invoked, about $0.0007 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 2026-08-31.

Marketing and SEO agents ai-memory invos starter-kit

hindsight-architect

Expert memory architect. Understands your application, identifies where memory adds value, and produces an implementation plan with bank config, tag schema, and code.

vectorize-io/hindsight · 35 tokens

create-agent

Create a new Hindsight-powered subagent with long-term memory. Use when the user wants a specialized agent that learns and remembers across sessions.

vectorize-io/hindsight · 31 tokens

hindsight-local

Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).

vectorize-io/hindsight · 32 tokens

hindsight-docs

Complete Hindsight documentation for AI agents. Use this to learn about Hindsight architecture, APIs, configuration, and best practices.

vectorize-io/hindsight · 30 tokens

hindsight-memory

Long-term memory for the agent via Hindsight. Use to recall relevant past context before answering, retain durable facts as you learn them, and reflect over accumulated memory for the "why" behind a decision. Load whenever continuity across sessions matters — the user refers to earlier work, states a lasting…

vectorize-io/hindsight · 74 tokens

hindsight-recall

Search long-term memory for relevant context from past coding sessions using Hindsight MCP tools.

vectorize-io/hindsight · 21 tokens