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-videogit 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-video)<a href="https://agentmods.dev/skills/zubair-trabzada/ai-ads-claude/ads-video"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-ads-claude/ads-video/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-video"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-ads-claude/ads-video.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 | $0.00055 | $0.04826 |
| Opus 5 | $0.00028 | $0.02413 |
| Sonnet 5 | $0.00011 | $0.00965 |
| Haiku 4.5 | $0.00006 | $0.00483 |
Grade A, and why
Video Ad Script Writer 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.
How it starts
The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Ad Script Writer
Skill Purpose
Generate complete, production-ready video ad scripts for three standard ad lengths: 15-second (TikTok/Reels/Bumper), 30-second (Pre-roll/Stories), and 60-second (YouTube/Facebook). Each script includes a shot-by-shot breakdown with exact timing, voiceover transcript, on-screen text overlays, B-roll suggestions, music/mood direction, and CTA placement. Scripts are written using three proven video ad frameworks and include a storyboard outline that a video editor or motion designer can follow without additional briefing.
When to Use
- User runs
/ads video <product> - User asks for video ad scripts, video creative, or video content for ads
- Called as a subagent from
/ads strategy(the main orchestrator) - User needs scripts for TikTok ads, YouTube pre-roll, Instagram Reels, Facebook video ads, or Stories
- User wants to brief a video editor or freelancer on ad creative
Input Requirements
- Required: Product or service to advertise (name, description, or URL)
- Optional: Target audience persona, brand guidelines, existing footage/assets, desired tone, specific platform focus, offer details
How to Execute
Step 1: Gather Product & Brand Context
If a URL is provided, fetch it using WebFetch and extract:
- Product/service name and description
- Key features and benefits
- Price point and offer structure
- Target audience indicators
- Brand tone and visual style
- Existing video content (YouTube channel, social media)
- Testimonials or case studies
- Competitor positioning
Run supplementary research:
WebSearch: "[Product/Brand]" video ad
WebSearch: "[Industry]" best video ad examples
WebSearch: "[Industry]" TikTok ad examples viral
WebSearch: "[Product category]" YouTube ad examples
Establish the video brief:
## Video Brief
**Product/Service:** [Name]
**Business:** [Company name]
**What it does:** [1-sentence description]
**Who it's for:** [Target persona in 1 sentence]
**Core benefit:** [The #1 reason someone buys this]
**Key differentiator:** [What makes it different from alternatives]
**Price/Offer:** [Current pricing, discount, free trial]
**Desired action:** [What should the viewer DO after watching]
**Tone:** [Professional / Casual / Energetic / Bold / Warm / Edgy / Playful]
**Brand colors:** [Primary and secondary if known]
**Existing assets:** [Footage, product photos, testimonials available]
**Competitors to reference:** [Who they're competing against for attention]
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 · 410 lines · 55 tokens per session scan A d0dc4a9f9f47
Video Ad Script Writer is a skill published in the GitHub repository zubair-trabzada/ai-ads-claude (246 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 4,826 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…