A workflow for analysing Facebook and Instagram advertising campaigns for clients in Spain. It reviews campaign results, ad auction position, account opportunities, unusual spending or performance, and tracking health.

Answering Meta Ads questions and running audits using campaign, hourly, opportunity, auction, anomaly, Pixel, Conversions API, event quality, and learning-state data.

It gathers the main advertising signals and applies Spain-specific benchmarks and European consent requirements, reducing the need to inspect each data source separately.

How Pauesome/Paid-Media-MCP configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Pauesome/Paid-Media-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Pauesome/Paid-Media-MCP/main/.claude/skills/meta-ads/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Pauesome/Paid-Media-MCP

Made for: Claude Code.

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/pauesome/paid-media-mcp/meta-ads/github.svg)](https://agentmods.dev/skills/pauesome/paid-media-mcp/meta-ads)

Your own site

<a href="https://agentmods.dev/skills/pauesome/paid-media-mcp/meta-ads"><img src="https://agentmods.dev/badge/skills/pauesome/paid-media-mcp/meta-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/pauesome/paid-media-mcp/meta-ads"><img src="https://agentmods.dev/badge/skills/pauesome/paid-media-mcp/meta-ads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 677 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	$0.00094	$0.00677
Opus 5	$0.00047	$0.00338
Sonnet 5	$0.00019	$0.00135
Haiku 4.5	$0.00009	$0.00068

Measured 11d ago against content hash 45409ed4c638, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

meta-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 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.

.claude/skills/meta-ads/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meta Ads Analysis — Spain

Entry point for any Meta/Facebook/Instagram Ads request. Delegates the deep audit to the audit-meta agent; this skill resolves inputs, pulls a quick snapshot, and routes.

All thresholds come from .claude/references/benchmarks-spain.md.

Required Inputs

client_id — resolve via list_clients. Best-guess match on label; flag if ambiguous.
date_range_start / date_range_end (ISO) — default last 14 days.
Fail fast with a clear error block on missing input — do not prompt.

Read First

.claude/references/benchmarks-spain.md
.claude/references/compliance-eu-spain.md — Meta EU Consent Policy + CMP requirements

Data Collection (parallel MCP calls)

get_meta_campaign_performance
get_meta_hourly_performance (dayparting + spend concentration)
get_meta_opportunity_score (account-level optimization opportunities)
get_meta_auction_rankings (auction competitiveness)
get_meta_anomaly_signal (spend / performance anomaly detection)

Routing

Quick question: answer inline from pulled data. No report file.
Full audit: launch the audit-meta agent with client_id + date range. It writes the scored report and returns the path.

Critical Checks (severity ×5 — dominate any score)

M-PX1 Pixel installed + firing · M-PX2 CAPI active · M-PX3 Event dedup ≥ 90%
M-PX4 EMQ (Purchase) ≥ 8.0 · M-ST1 Learning Limited < 30% · M-AN1 no severe anomaly flags

Pixel/CAPI/EMQ are account-configuration checks — confirm in Meta Events Manager. The MCP tools surface performance, opportunity, auction, and anomaly signals, not raw pixel diagnostics.

Hard Rules (mirror audit-meta)

Use EU Special Ad Category rules only — never US
Flag Offline Conversions API as FAIL (discontinued May 2025)
Flag missing CMP integration as Critical (Meta EU Consent Policy)
Weight ROAS / CPA above CTR / CVR when metrics disagree

Output

Full audits write to ./reports/<client_id>/<YYYY-MM-DD>-meta-audit/META-ADS-REPORT.md, first line:

Read the full file on GitHub · 72 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.

11d ago First seen · 72 lines · 94 tokens per session scan A 45409ed4c638

Subscribe to this mod's changes

meta-ads is a skill published in the GitHub repository Pauesome/Paid-Media-MCP (1 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 677 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 2026-08-31.

Analytics and metrics Marketing and SEO

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

Paid-Media-MCP: Skill for Claude Code