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.
npx agentmods add skills/rampstackco/claude-skills/ads-performance-analyticsnpx skills add rampstackco/claude-skills --skill ads-performance-analyticsgit clone --depth 1 https://github.com/rampstackco/claude-skillsWrote 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.
[](https://agentmods.dev/skills/rampstackco/claude-skills/ads-performance-analytics)<a href="https://agentmods.dev/skills/rampstackco/claude-skills/ads-performance-analytics"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/ads-performance-analytics.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00147 | $0.05133 |
| Opus 5 | $0.00073 | $0.02567 |
| Sonnet 5 | $0.00029 | $0.01027 |
| Haiku 4.5 | $0.00015 | $0.00513 |
Grade A, and why
ads-performance-analytics 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ads Performance Analytics
A data-team-mentor's playbook for interpreting paid media dashboards without fooling yourself.
The dashboard is the moment of truth for paid media decisions. The numbers on it determine whether you scale, hold, or kill. They also expose every platform's self-attribution bias, every modeled-conversion shortcut, every cross-platform double-count. Most "scale this campaign" decisions trace back to misreading the dashboard.
This skill is the discipline that prevents misreading. It assumes the campaign was strategically sound (see paid-media-strategy). It assumes the creative was tested properly (see ads-creative-development). The hard part is knowing what each number actually means, what it does not, and how to reconcile platform-reported metrics with the truth in your warehouse.
When to use this skill: any time you are about to scale, kill, or rebudget a campaign based on platform metrics; reconciling platform reports with revenue data; evaluating an agency's reporting; or building a paid media dashboard that will not lie to you.
What this skill is for
This skill spans paid media result interpretation. It does not cover paid media strategy (use paid-media-strategy), creative production (use ads-creative-development), or platform-specific tooling (covered in the integrations microsites). Pair this skill with the relevant integrations microsite for platform-specific MCP commands and example prompts.
The audience is a marketer, growth analyst, agency analyst, or founder evaluating paid media reports. The voice is patient and clinical. There is no "trust the platform's number" or "ignore the platform entirely." Both are wrong. The discipline is knowing which numbers from which platform mean what, and what to reconcile against to make the actual decision.
The result panel: what every paid media platform should expose
A trustworthy result panel exposes nine things. Anything missing is a signal to treat reported numbers with extra skepticism.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/attribution-model-comparison.md 7.3 KB
- references/cohort-analysis-templates.md 6.4 KB
- references/common-interpretation-failures.md 8.9 KB
- references/dashboard-reconciliation-patterns.md 6.5 KB
- references/incrementality-testing-playbook.md 7.0 KB
- references/metric-definitions-glossary.md 6.5 KB
- references/platform-reporting-quirks.md 8.8 KB
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.
- 6d ago First seen · 282 lines · 147 tokens per session scan A 1d37faa69f77
ads-performance-analytics is a skill published in the GitHub repository rampstackco/claude-skills (817 stars, last pushed 8d ago), licensed MIT. It adds 147 tokens to every session and 5,133 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 2026-08-30.
Other skills, from other repositories
market-ads
Tu es le moteur de création publicitaire pour /market ads . Tu génères des campagnes publicitaires complètes sur toutes les plateformes avec des variations de texte, des stratégies de ciblage d'audience, des recommandations budgétaires et des spécifications créatives. Chaque annonce est prête pour la production ou la…
market-launch
Générer un plan de lancement complet, semaine par semaine, pour tout lancement de produit, service ou fonctionnalité. Ce skill produit un plan tactique avec des modèles, checklists, séquences d'emails, publications sociales et suivi des métriques — tout le nécessaire pour exécuter un lancement réussi.
market-proposal
Générer une proposition de services marketing professionnelle et prête pour le client. Ce skill produit un document de proposition complet qui positionne l'agence/consultant comme le choix évident, cadre la tarification avec ancrage et options à paliers, et inclut des projections ROI pour justifier l'investissement.
market-seo
Effectuer un audit SEO complet d'une page web ou d'un site, couvrant le SEO on-page, la qualité du contenu (E-E-A-T), l'analyse de mots-clés, le SEO technique et la stratégie de contenu. Ce skill combine une analyse automatisée via scripts/analyzepage.py avec une revue manuelle de niveau expert pour produire un…
market-landing
Effectuer une analyse complète d'Optimisation du Taux de Conversion (CRO) sur toute page d'atterrissage. Ce skill produit un démontage section par section avec des corrections prioritaires et actionnables ayant un impact direct sur les taux de conversion.
market-report-pdf
Générer un rapport marketing PDF professionnel et visuellement soigné à l'aide du script Python scripts/generatepdfreport.py. Ce skill collecte toutes les données d'audit et d'analyse disponibles, les structure au format JSON attendu, invoque le script et produit un PDF de marque avec jauges de score, graphiques en…