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-creativegit 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-creative)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/ads-creative"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/ads-creative/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-creative"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/ads-creative.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 | $0.00088 | $0.03344 |
| Opus 5 | $0.00044 | $0.01672 |
| Sonnet 5 | $0.00018 | $0.00669 |
| Haiku 4.5 | $0.00009 | $0.00334 |
Grade A, and why
ads-creative 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 12d 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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Platform Creative Quality Audit
Process
- Brand context check — look for
./branding.md. If not found, run the Brand Info Collection flow below before proceeding. - Collect creative assets or performance data from active platforms
- Read
ads/references/platform-specs.mdfor creative specifications - Read
ads/references/creative-volume.mdfor per-platform volume and refresh requirements - Read
ads/references/benchmarks.mdfor CTR/engagement benchmarks - Read
ads/references/scoring-system.mdfor weighted scoring algorithm - Evaluate creative quality per platform
- Run Brand Consistency Audit using branding.md (advisory, not scored)
- Assess cross-platform creative consistency
- Generate production priority recommendations
- Offer to generate new creatives using
/infographic-v2for any flagged gaps
Brand Info Collection
Run this at the start if ./branding.md does not exist in the project root.
Goal: Extract the brand's actual styling, copy, and identity — primarily from their website — to personalize the creative audit and enable on-brand creative generation via infographic-v2.
Step 1: Ask for brand name and website
"Before I audit your creatives, I need your brand context to check consistency. What's your brand name and website URL?"
Ask for the brand name and website URL first. If the user provides a URL, immediately run the website extraction (step 2) before asking any further questions.
Step 2: Website extraction (when URL provided)
Do not guess or assume anything. Extract the actual values from the live website.
2a — Fetch the homepage
Use WebFetch on the homepage URL. Extract ALL of the following:
Visual identity:
- All colors used prominently: backgrounds, buttons, headers, links, text, borders, footer. Report exact hex values. Identify which is primary (most prominent brand color, usually on CTAs and headers), secondary, accent, background, and text color.
- Font families: read the actual
font-familydeclarations used on headings and body text. Look in CSS,<link>tags for Google Fonts / Typekit / custom font URLs, and inline styles. Report the exact font names (e.g., "Plus Jakarta Sans", "DM Sans", "Geist"), not generic fallbacks like "sans-serif". - Logo: describe the logo from the header/nav. Note if it's text-based, icon-based, or both.
- Visual style: describe what you observe — minimal with whitespace? Bold with saturated colors? Dark mode? Gradient-heavy? Illustration-driven? Corporate?
- Button styles: rounded, square, pill-shaped? What color? What text color on buttons?
- Spacing and density: tight and information-dense, or airy and spacious?
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.
- 12d ago First seen · 341 lines · 88 tokens per session scan A f1e00ab5f2de
ads-creative is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 3,344 once invoked, about $0.0004 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.