Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Ads Reporter Multi

ASecurity

Use when reporting across multiple ad accounts: aggregate spend, CPA/ROAS, and frequency into one comparative HTML view with keyword-DM funnel events. Triggers on \"multi-ads report\", \"CPA ROAS report\", \"compare ad accounts\", \"keyword DM\". Non-triggers: day-to-day operation of a single account (use ads-operator). Outcome: a comparative multi-account HTML report with keyword-DM funnel events.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsapi

Works with

cliapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill ads-reporter-multi --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ads Reporter Multi?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Ads Reporter Multi
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-ads-reporter-multi/badge)](https://www.skillsdirectory.com/skills/majinmagros-ads-reporter-multi)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: ads-reporter-multi
description: "Use when reporting across multiple ad accounts: aggregate spend, CPA/ROAS, and frequency into one comparative HTML view with keyword-DM funnel events. Triggers on \"multi-ads report\", \"CPA ROAS report\", \"compare ad accounts\", \"keyword DM\". Non-triggers: day-to-day operation of a single account (use ads-operator). Outcome: a comparative multi-account HTML report with keyword-DM funnel events."
metadata:
  origin: ECC
---

# Ads Reporter Multi

One HTML report across many ad accounts: spend, CPA/ROAS, frequency, and
keyword-DM funnel events side by side. Read-only aggregation first; any
account change stays behind an approval gate.

## When To Activate

- The user says multi-ads report, compare accounts, CPA/ROAS overview, or
  keyword DM funnel.
- Data spans two or more accounts or clients.
- Output must be a shareable HTML page, not chat text.
- DM automation is keyword-triggered with UTM and pixel, not a paid chat
  tool.

## Workflow

1. Connect read-only: register each account with read scope, list
   campaigns, and confirm currency and timezone per account.
2. Pull metrics: for a fixed window, fetch spend, impressions, clicks,
   conversions, CPA/ROAS, and frequency per campaign.
3. Normalize: convert currencies when needed, align date windows, and
   flag thin data before comparing.
4. Add funnel events: join keyword-DM triggers (keyword -> DM sent ->
   click with UTM -> pixel event) to the matching campaign rows.
5. Render HTML: one comparative table plus per-account cards with
   thumbnails, top/worst rows, and frequency warnings.
6. Review deltas: mark movers (up/down vs prior window) and attach one
   hypothesis per mover. No silent numbers.
7. Approval gate: any proposed account change from the report needs human
   approval before execution; the report itself never mutates accounts.
8. Archive: save the HTML plus the raw pull per window for trend history.

## Keyword-DM Rule

- A comment or message containing the keyword triggers one DM with the
  tracked link (UTM). Dedupe by user, log opt-outs, and fire the pixel
  event on click. This replaces the paid chat tool with a scripted flow.

## Anti-Patterns

- Comparing accounts across different windows or currencies.
- Reporting CPA/ROAS on thin data with no flag.
- Letting the reporter mutate accounts directly.
- Keyword-DM with no dedupe, no opt-out, and no UTM.
- Chat-only summaries with no archived HTML.
- Frequency blindness: scaling spend while frequency burns the audience.

## Relations

- `ads-operator`: account audits and approved mutations.
- `dashboard-builder`: dashboard structure for operator questions.
- `data-throughput-accelerator`: fast multi-account pulls done right.
- `ads-creative-factory`: creative batches that feed this report.

## Exemplo

```text
3 contas (BRL + USD), janela 7d: spend total R$12,4k, CPA R$31, ROAS 2,8x
Mover: conta B CPA +40% vs janela anterior → hipótese: frequência 6,2 queimou audiência
Gate: nenhuma mudança executada pelo report — proposta vai p/ aprovação em ads-operator
```

## Sources

- Meta Marketing API (insights, campaigns): https://developers.facebook.com/docs/marketing-api/

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →