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 novoads/agent-skills --skill meta-ad-buildergit clone --depth 1 https://github.com/novoads/agent-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/novoads/agent-skills/meta-ad-builder)<a href="https://agentmods.dev/skills/novoads/agent-skills/meta-ad-builder"><img src="https://agentmods.dev/badge/skills/novoads/agent-skills/meta-ad-builder.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Supply Chain · line 254 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- medium Output Handling · line 154 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 | $0.00157 | $0.03530 |
| Opus 5 | $0.00078 | $0.01765 |
| Sonnet 5 | $0.00031 | $0.00706 |
| Haiku 4.5 | $0.00016 | $0.00353 |
Grade A, and why
meta-ad-builder scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`deploy-ad.py` prints every orphan with a ready-to-run `curl` cleanup line and How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta ad builder
Turn a finished creative — typically the output of a generative-AI skill in this workspace — into a live Meta ad. The skill covers three phases: research (optional) → copy → deploy. It talks to the Meta Marketing API directly via ported, parameterized Python scripts.
Meta credentials required before any deploy work. Run
bash scripts/check-meta-env.shfirst — before uploading a creative, before creating anything in the ad account, before the first Meta call of any phase. On a non-zero exit, stop and ask the user for what it printed. It has already uncommented the two required lines in.envand opened the file, so the ask is "paste these two values", not "go find the docs". Read its Live-app warning out to them: a development-mode app passes every check and then fails at ad creation. Until the check passes, nothing is uploaded, no partial ad or creative exists and nothing is charged — which is exactly why it runs first, since a deploy that dies halfway orphans uploaded assets in a live ad account. This key is deliberately lazy: the pack asks for it here, at the moment someone wants to publish, and never during setup.
When to use this skill
Trigger on phrases like:
- "deploy this video to Meta" / "publish this as a Facebook ad"
- "build/launch a Meta ad" / "push this creative into "
- "create a Meta ad with this image and copy"
- "pull my top-performing ads" / "what are my best ads by ROAS"
- "research competitor ads" / "pull 's ads from the Ad Library"
Do not use this skill to generate creative — that's pixar-ad,
claymation-ad, chatgpt-image-ad, nano-banana-image-ad,
generate-youtube-thumbnail, etc. Do not use it to write ad-table rows. This
skill is the direct Meta Marketing API deployment step.
Read order
- This file — workflow, decision tree, safety rules.
- prompting/copy-guide.md — the 5-body / 5-title /
3-description frameworks and the
--copy-fileJSON shape. - reference/deploy-patterns.md — creative spec mechanics, video polling, retry, failure modes.
- reference/meta-api-cheatsheet.md — the full Meta Marketing API reference (campaigns, ad sets, ads, enums, gotchas, Ad Library). Consult as needed; don't read end-to-end.
What ships with it
11 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.
- evals.md 10 KB
- prompting/copy-guide.md 3.9 KB
- reference/deploy-patterns.md 7.9 KB
- reference/meta-api-cheatsheet.md 44 KB
- routing-eval.jsonl 1.9 KB
- scripts/check-meta-env.sh 22 KB runs code
- scripts/deploy-ad.py 21 KB runs code
- scripts/lib/meta_api.py 10 KB runs code
- scripts/pull-competitor-ads.py 7.3 KB runs code
- scripts/pull-top-ads.py 7.0 KB runs code
- scripts/requirements.txt 385 B
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.
- 8d ago First seen · 272 lines · 157 tokens per session scan A 67556001059c
meta-ad-builder is a skill published in the GitHub repository novoads/agent-skills (14 stars, last pushed 12d ago), licensed MIT. It adds 157 tokens to every session and 3,530 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
xiaohongshu-auto-posting
Automates the complete Xiaohongshu (XHS / Little Red Book) content operation workflow: pain-point topic collection → style case collection → topic selection → content writing → publishing → performance tracking. Use when user mentions xiaohongshu auto posting, xhs auto post, little red book posting, xiaohongshu post…
muapi-seedance-2
Expert Cinema Director skill for Seedance 2.0 (ByteDance) — high-fidelity video generation across Chinese, Global, and VIP tiers. Supports text-to-video, image-to-video, first-last-frame, omni reference, character training, omni-reference training, video editing, and watermark removal.
video-shotcraft
Create cinematic product videos from shot recipe cards, a validated template, and code/audio assets (Remotion + real page screenshots + 2.5D camera moves + beat-synced cuts + sound design). Use when the user asks to turn a frontend project or webpage into a product video, says "use video-shotcraft to make a…
muapi-social-media-video
Brand-aware social media video creator. Reads brand-identity.md, ICP.md, and messaging.md to write a post/storyboard, craft an optimized Seedance 2.0 Director prompt, generate reference frames with the best available image model, and produce platform-ready video.
muapi-ai-clipping
Turn a long video into N viral-ready short clips with a single managed API call. Wraps muapi.ai's /ai-clipping endpoint, which handles transcription, highlight ranking through a virality framework (hook / emotional peak / opinion bomb / revelation / conflict / quotable / story peak / practical value), overlap dedupe…
muapi-youtube-shorts
Auto-generate viral 9:16 YouTube Shorts (or TikTok / Reels clips) from a long-form video. Thin platform-aware wrapper around the AI Clipping skill — picks sensible defaults for short-form social platforms (9:16, 30–60s sweet spot) and delegates the actual highlight extraction + crop to muapi.ai's /ai-clipping endpoint.