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 naveedharri/benai-skills --skill ads-landinggit clone --depth 1 https://github.com/naveedharri/benai-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/naveedharri/benai-skills/ads-landing)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/ads-landing"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/ads-landing/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/naveedharri/benai-skills/ads-landing"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/ads-landing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00063 | $0.01410 |
| Opus 5 | $0.00032 | $0.00705 |
| Sonnet 5 | $0.00013 | $0.00282 |
| Haiku 4.5 | $0.00006 | $0.00141 |
Grade A, and why
ads-landing 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 13d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- ads-landing — 100% identical, 0 lines differ
- ads-landing — 95% identical, 15 lines differ
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Landing Page Quality for Ad Campaigns
Process
- Collect landing page URLs from active ad campaigns
- Read
ads/references/benchmarks.mdfor conversion rate benchmarks - Read
ads/references/conversion-tracking.mdfor pixel/tag verification - Assess each landing page for ad-specific quality factors
- Score landing pages and identify improvement opportunities
- Generate recommendations prioritized by conversion impact
Message Match Assessment
The #1 landing page issue in ad campaigns — does the page match the ad?
What to Check
- Headline match: landing page H1 reflects ad copy headline/keyword
- Offer match: promoted offer (price, discount, trial) is visible above fold
- CTA match: landing page CTA matches ad's promised action
- Visual match: consistent imagery between ad creative and page
- Keyword match: search keyword appears naturally in page content
Message Match Scoring
| Level | Description | Score |
|---|---|---|
| Exact match | Headline, offer, CTA all align perfectly | 100% |
| Partial match | Headline matches but offer/CTA differs | 60% |
| Weak match | Generic page, loosely related to ad | 30% |
| Mismatch | Page content doesn't reflect ad promise | 0% |
Page Speed Assessment
Slow pages kill conversion rates. For every 1s delay, CVR drops ~7%.
Thresholds (Ad Landing Pages)
| Metric | Pass | Warning | Fail |
|---|---|---|---|
| LCP | <2.5s | 2.5-4.0s | >4.0s |
| FID/INP | <100ms | 100-200ms | >200ms |
| CLS | <0.1 | 0.1-0.25 | >0.25 |
| Time to Interactive | <3.0s | 3.0-5.0s | >5.0s |
| Page weight | <2MB | 2-5MB | >5MB |
Common Speed Issues in Ad Pages
- Hero images not compressed (use WebP/AVIF)
- Too many third-party scripts (chat widgets, analytics, heatmaps)
- Render-blocking CSS/JS above fold
- No lazy loading for below-fold content
- Font files not preloaded
Mobile Experience
75%+ of ad clicks come from mobile. Mobile experience is critical.
Mobile Checklist
- Tap targets: ≥48x48px with ≥8px spacing
- Font size: ≥16px body text (no pinch-to-zoom needed)
- Form fields: properly sized, keyboard type matches input (email, phone, number)
- CTA button: full-width on mobile, visible without scrolling
- No horizontal scroll
- Images responsive and properly sized
- Phone number clickable (tel: link)
- No interstitials or popups blocking content on load
What ships with it
4 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.
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.
- 13d ago First seen · 160 lines · 63 tokens per session scan A c77bd9ed85d2
ads-landing is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 1,410 once invoked, about $0.0003 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
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
design-tokens-transformer
A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.
media-higgsfield-explainer
A Higgsfield workflow for making non-photorealistic narrated explainer videos. It pairs each narration line with a 10-second animated clip and joins the clips into one finished video.