relatorio-ads

relatorio-ads is a skill for Claude Code, Codex from felipenalves/InvOS. It costs 117 tokens per session (1,619 once invoked), scanned A, original, MIT.

Um relatório semanal que analisa dados de anúncios do Google Ads e do Meta Ads, as plataformas de publicidade do Google e da Meta.

In plain words
What is it for?
Serve para comparar semanas, acompanhar impressões, cliques, custos e conversões, encontrar anúncios com melhor desempenho, apontar problemas e sugerir ações para a semana seguinte.
Why use it?
Transforma arquivos exportados ou capturas de tela em uma visão compreensível do desempenho, sem exigir que você navegue pelas plataformas.

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 Serve para comparar semanas, acompanhar impressões, cliques, custos e conversões, encontrar anúncios com melhor desempenho, apontar problemas e sugerir ações para a semana seguinte.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/felipenalves/invos/relatorio-ads
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 relatorio-ads
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.

agentmods badge for relatorio-ads

README.md
[![agentmods](https://agentmods.dev/badge/skills/felipenalves/invos/relatorio-ads/github.svg)](https://agentmods.dev/skills/felipenalves/invos/relatorio-ads)
Your own site
<a href="https://agentmods.dev/skills/felipenalves/invos/relatorio-ads"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/relatorio-ads/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 relatorio-ads

Your own site · 80×15
<a href="https://agentmods.dev/skills/felipenalves/invos/relatorio-ads"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/relatorio-ads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,619 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00117 $0.01619
Opus 5 $0.00059 $0.00809
Sonnet 5 $0.00023 $0.00324
Haiku 4.5 $0.00012 $0.00162

Measured 9d ago against content hash bcb65c4a57b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

relatorio-ads 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.

.agents/skills/relatorio-ads/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/relatorio-ads — Relatório semanal de Google Ads + Meta Ads

Skill que transforma exports brutos das plataformas em relatório executivo que o dono entende sem precisar abrir a interface do Google ou da Meta.

Dependências

  • Contexto: _memoria/empresa.md, _memoria/estrategia.md
  • Tom de voz: _memoria/preferencias.md
  • Inputs: CSVs do Google Ads e/ou Meta Ads Manager. Print também aceito (transcrever)
  • Histórico: marketing/campanhas/relatorios/ (criar se não existir)

Como rodar

Usuário roda o comando e cola/aponta os arquivos:

/relatorio-ads
dados/google-ads-2026-05-12.csv
dados/meta-ads-2026-05-12.csv

Ou simplesmente:

/relatorio-ads

Aí a skill pergunta onde estão os exports da semana.

Workflow

Passo 1 — Ler os exports

Google Ads: colunas mínimas esperadas — Campanha, Grupo, Impressões, Cliques, CTR, CPC médio, Custo, Conversões, CPA, Conv. rate.

Meta Ads: colunas mínimas esperadas — Campanha, Conjunto, Impressões, Alcance, Cliques no link, CTR, CPM, Frequência, Custo, Resultados, Custo por resultado.

Se faltar coluna crítica (Conversões / Resultados), avisar e seguir só com tráfego.

Passo 2 — Comparar com a semana anterior

Buscar em marketing/campanhas/relatorios/ o relatório anterior. Se existir, calcular variação semana vs semana:

  • Investimento total
  • Cliques / Impressões
  • CTR (clique / impressão)
  • CPC / CPM
  • Conversões totais (Google + Meta)
  • CPA (custo / conversão)
  • Custo por canal

Se não existir, é a primeira leitura — sinalizar como baseline.

Passo 3 — Resumo executivo (topo do relatório)

Uma página, leitura de 2 minutos. Estrutura:

# Relatório de Ads — semana <DD/MM> a <DD/MM>

## Resumo executivo

**Investimento:** R$ X.XXX (▼/▲ Y% vs semana anterior)
**Conversões:** N (▼/▲ Y%)
**CPA médio:** R$ X.XX (▼/▲ Y%)

**Canais:**
- Google Ads: R$ X.XXX → N conversões (CPA R$ X.XX)
- Meta Ads:   R$ X.XXX → N conversões (CPA R$ X.XX)

**Headline da semana:** 1 frase do que mais importa (campanha que estourou, criativo que matou,
alerta de orçamento, queda inesperada).

Read the full file on GitHub · 164 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 · 164 lines · 117 tokens per session scan A bcb65c4a57b6

Subscribe to this mod's changes

relatorio-ads is a skill published in the GitHub repository felipenalves/InvOS (5 stars, last pushed 6d ago), licensed MIT. It adds 117 tokens to every session and 1,619 once invoked, about $0.0006 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.