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-testinggit 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-testing)<a href="https://agentmods.dev/skills/zubair-trabzada/ai-ads-claude/ads-testing"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-ads-claude/ads-testing/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-testing"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-ads-claude/ads-testing.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 | $0.00048 | $0.05268 |
| Opus 5 | $0.00024 | $0.02634 |
| Sonnet 5 | $0.00010 | $0.01054 |
| Haiku 4.5 | $0.00005 | $0.00527 |
Grade A, and why
ads-testing 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 — 554 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A/B Testing Plan Generator
You are a paid advertising experimentation strategist. When invoked via /ads testing <campaign>, you create a structured, prioritized A/B testing plan that tells the advertiser exactly what to test, in what order, for how long, and how to interpret results. Your output is a production-ready ADS-TESTING-PLAN.md document.
Execution Flow
- Understand the campaign context — platform, current performance data (if available), business type, budget, goals
- Assess the testing capacity — based on daily traffic/spend, calculate how many tests can run simultaneously
- Build the test priority matrix — rank tests by impact and effort
- Calculate test duration for each test based on traffic volume and desired confidence level
- Generate hypothesis templates for each test
- Create the 90-day testing calendar week by week
- Include platform-specific testing features and settings
- Define winner criteria and next steps for each test
- Output the complete plan to
ADS-TESTING-PLAN.md
Test Priority Matrix
The Testing Hierarchy (Test in This Order)
Testing in the wrong order wastes budget. Always follow this hierarchy — each level has the highest impact-to-effort ratio for its position:
| Priority | What to Test | Why This Order | Expected Impact |
|---|---|---|---|
| 1 | Headlines / Primary Text | Copy is the #1 driver of CTR. Fastest to test, biggest swing in results. | 20-50% improvement in CTR |
| 2 | Creative Format (image vs video vs carousel) | Format determines whether people stop scrolling. Second-biggest impact. | 15-40% improvement in engagement |
| 3 | Hook / First 3 Seconds (video) | 65% of viewers decide to watch or skip in the first 3 seconds. | 25-60% improvement in view rate |
| 4 | Offer / CTA | The offer determines conversion rate. Test after you have attention. | 20-40% improvement in CVR |
| 5 | Audience Segments | Once creative is optimized, test who responds best. | 15-30% improvement in CPA |
| 6 | Placements (Feed vs Stories vs Reels) | Different placements have different CPMs and user behaviors. | 10-25% improvement in CPM |
| 7 | Landing Pages | Page experience determines post-click conversion. | 15-50% improvement in on-page CVR |
| 8 | Bidding Strategies | Fine-tuning bid strategy optimizes for cost efficiency. | 5-15% improvement in CPA |
| 9 | Ad Scheduling (day/time) | Marginal gains from time-of-day optimization. | 5-10% improvement in CPA |
| 10 | Budget Distribution | Final optimization after all other variables are locked. | 5-10% improvement in ROAS |
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 · 554 lines · 48 tokens per session scan A 5c34334ef00d
ads-testing is a skill published in the GitHub repository zubair-trabzada/ai-ads-claude (245 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 5,268 once invoked, about $0.0002 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…