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 skills add byadsco/meta-ads-mcp --skill meta-ads-creative-analysisgit clone --depth 1 https://github.com/byadsco/meta-ads-mcpWrote 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/byadsco/meta-ads-mcp/meta-ads-creative-analysis)<a href="https://agentmods.dev/skills/byadsco/meta-ads-mcp/meta-ads-creative-analysis"><img src="https://agentmods.dev/badge/skills/byadsco/meta-ads-mcp/meta-ads-creative-analysis/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.
<a href="https://agentmods.dev/skills/byadsco/meta-ads-mcp/meta-ads-creative-analysis"><img src="https://agentmods.dev/badge/skills/byadsco/meta-ads-mcp/meta-ads-creative-analysis.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00095 | $0.01172 |
| Opus 5.5 | $0.00038 | $0.00469 |
| Sonnet 5.5 | $0.00019 | $0.00234 |
| Haiku 4.5 | $0.00010 | $0.00117 |
Grade A, and why
meta-ads-creative-analysis 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 1mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing a Meta ad creative
A creative review is worth nothing if the reviewer never looked at the ad. This server can put the actual pixels in front of you; start there, then judge.
Look at it first
| You have | Call |
|---|---|
| An ad id, and you want the whole picture | ads_get_ad_dossier — creative, copy, targeting, performance and media in one call |
| An ad or creative id, and you only want to see it | ads_get_creative_media |
| A video | the video-analysis skill: delivery=frames or inline |
| A competitor's ad | ads_library_get_ad_details, from the competitor-research skill |
ads_get_creative_media returns images as blocks a multimodal model reads directly, including carousel cards and video posters. Use image_size: "small" when the question is "what is this ad" and "full" when it is "read the text on it".
Never review from the creative's JSON alone. The copy is in there, but the image is the ad.
The rubric
Score each axis 1 to 5 and say why. A score without a reason cannot be acted on.
Hook. The first thing seen or read. For an image, the visual and the first line of primary text; for video, the first three seconds. Does it stop the scroll, and does it stop the right person?
Clarity. Can someone tell what is being sold, to whom, within two seconds? Ambiguity is the most common cause of a high CTR with no conversions.
Offer. What is actually promised, and is it specific? "30% off until Sunday" beats "great deals". If there is no offer, say so: that is often the finding.
Call to action. Present, visible, and matching the landing page. A "Shop now" that lands on a blog post is a broken ad regardless of its creative quality.
Sound-off and thumb-stop. Most of the feed is silent and fast. Captions, legible text, high contrast, a subject that reads at thumbnail size.
Format fit. 9:16 for Stories and Reels, 4:5 or 1:1 for the feed. Text or faces inside the safe zones, not under the UI. A repurposed 16:9 asset in a vertical placement is a self-inflicted wound.
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.
- 1mo ago First seen · 80 lines · 95 tokens per session scan A aba7e9da01d1
meta-ads-creative-analysis is a skill published in the GitHub repository byadsco/meta-ads-mcp (24 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 1,172 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-18.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…