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 zubair-trabzada/ai-ads-claude --skill ads-creativegit clone --depth 1 https://github.com/zubair-trabzada/ai-ads-claudeWrote 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/zubair-trabzada/ai-ads-claude/ads-creative)<a href="https://agentmods.dev/skills/zubair-trabzada/ai-ads-claude/ads-creative"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-ads-claude/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/zubair-trabzada/ai-ads-claude/ads-creative"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-ads-claude/ads-creative.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 | $0.00016 | $0.04474 |
| Opus 5 | $0.00008 | $0.02237 |
| Sonnet 5 | $0.00003 | $0.00895 |
| Haiku 4.5 | $0.00002 | $0.00447 |
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 — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative Brief Generator
Skill Purpose
Generate comprehensive, production-ready creative briefs for designers, video editors, and content creators. Each brief includes visual concept descriptions, text overlay copy, format specifications, aspect ratios per platform, color palette suggestions, mood/tone direction, reference descriptions, shot lists for video, and thumbnail/cover image direction. Produces briefs for 5 ad formats: Static Image, Carousel, Short Video (15s), Long Video (60s), and UGC-Style.
When to Use
- User needs creative direction for ad campaigns
- User wants to brief a designer, video editor, or UGC creator
- User asks for "creative briefs", "ad concepts", "design direction", or "video scripts"
- User wants platform-specific creative specs
- Triggered by
/ads creative <product/service>or/ads creative <url>
How to Execute
Step 1: Gather Business Context
If the user provides a URL, fetch it to understand the business:
WebFetch(url) -> Extract:
- Business name and industry
- Product/service offering
- Brand colors (from website CSS/design)
- Brand voice and tone (from copy style)
- Target audience signals
- Existing imagery style
- Key value propositions
- Pricing information
- Testimonials or social proof
If no URL is provided, ask the user for:
- Product/service name and description
- Target audience
- Key selling points (top 3)
- Brand colors (hex codes if available)
- Competitors to differentiate from
Step 2: Define Brand Visual Identity
Extract or establish the visual identity foundation:
Color Palette Analysis:
| Element | Value | Usage |
|---|---|---|
| Primary Color | #XXXXXX | Headlines, CTAs, key elements |
| Secondary Color | #XXXXXX | Accents, supporting elements |
| Background Color | #XXXXXX | Backgrounds, negative space |
| Text Color | #XXXXXX | Body copy, descriptions |
| Accent Color | #XXXXXX | Highlights, urgency elements |
If no brand colors are available, recommend a palette based on industry:
- SaaS/Tech: Blues, purples, clean whites (#2563EB, #7C3AED, #F8FAFC)
- E-commerce/Retail: Bold oranges, blacks, whites (#F97316, #18181B, #FFFFFF)
- Health/Wellness: Greens, earth tones, soft whites (#059669, #92400E, #FFF7ED)
- Finance/Legal: Navy, gold, charcoal (#1E3A5F, #D4A843, #374151)
- Food/Restaurant: Warm reds, yellows, cream (#DC2626, #EAB308, #FFFBEB)
- Local Services: Trust blues, professional grays (#1D4ED8, #6B7280, #F3F4F6)
- Creator/Education: Vibrant purples, pinks, energetic (#8B5CF6, #EC4899, #F0ABFC)
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 · 455 lines · 16 tokens per session scan A 064aa8cd217c
ads-creative is a skill published in the GitHub repository zubair-trabzada/ai-ads-claude (246 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 4,474 once invoked, about $0.0001 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
frame-data-chart-nyt
NYT-newsroom typography, staggered reveal animation, and editorial-grade charts (line, bar, or range band).
frame-flowchart-sticky
SVG curve connectors, sticky-note nodes, and cursor interaction with a whiteboard-brainstorm feel.
frame-glitch-title
Digital glitch, chromatic offset, and data-corruption title frame for video transitions or cyberpunk heroes.
frame-light-leak-cinema
Film light leaks, grain, 16:9 letterbox, and large serif type for cinematic openings or chapter cards.
frame-logo-outro
Segmented logo assembly, glow bloom, and tagline reveal for video outros or brand closing frames.
vfx-text-cursor
Cursor light trail, chromatic rays, and directional flares for word-by-word quote reveals in video intros.