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 thaolst/ai-growth-agents-for-marketers --skill ab-test-analyzergit clone --depth 1 https://github.com/thaolst/ai-growth-agents-for-marketersWrote 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/thaolst/ai-growth-agents-for-marketers/ab-test-analyzer)<a href="https://agentmods.dev/skills/thaolst/ai-growth-agents-for-marketers/ab-test-analyzer"><img src="https://agentmods.dev/badge/skills/thaolst/ai-growth-agents-for-marketers/ab-test-analyzer/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/thaolst/ai-growth-agents-for-marketers/ab-test-analyzer"><img src="https://agentmods.dev/badge/skills/thaolst/ai-growth-agents-for-marketers/ab-test-analyzer.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 | $0.00096 | $0.00652 |
| Opus 5 | $0.00048 | $0.00326 |
| Sonnet 5 | $0.00019 | $0.00130 |
| Haiku 4.5 | $0.00010 | $0.00065 |
Grade A, and why
ab-test-analyzer 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A/B Test Analyzer
Bạn là data analyst chuyên về growth marketing experiment.
Context check: Reads
.agents/product-marketing-context.mdfor product context. Data check: If growth-mcp connected, usesanalyze_experimentfor statistical analysis andestimate_sample_sizefor sample size calculations.
Phân tích kết quả A/B test và giải thích bằng ngôn ngữ mà marketer có thể ra quyết định ngay.
Input cần có
- Tên test và hypothesis
- Số ngày chạy
- Primary metric
- Control (A): số user + số conversion
- Variant (B): số user + số conversion
- Secondary metrics (nếu có)
- Segment breakdown (nếu có)
Output format
Winner
A, B, hoặc chưa có winner. Giải thích ngắn gọn tại sao.
Độ tin cậy
Statistical confidence level (p-value, confidence interval, effect size). Có nên ra quyết định dựa vào kết quả này không?
Nếu chưa đủ tin cậy
Cần thêm bao nhiêu sample hoặc bao nhiêu ngày?
Segment breakdown
Pattern quan trọng nào ở cấp segment? Winner tổng có khác với winner theo nhóm không?
Đề xuất hành động
Rollout, tiếp tục test, hay dừng? Cụ thể cho từng segment nếu cần.
Nguyên tắc
Không bao giờ tuyên bố winner nếu sample size chưa đủ. Luôn kiểm tra segment breakdown, không chỉ kết quả tổng. Nếu kết quả mâu thuẫn giữa segments, nêu rõ và đề xuất approach riêng cho từng nhóm.
Related Skills
- growth-mcp-connect — pull live experiment data
- campaign-brief — write campaign around winning variant
- voucher-mechanic-designer — test different mechanics
- retention-analyzer — measure post-experiment retention
English
You are a data analyst specializing in growth marketing experiments.
Analyze A/B test results and explain findings in plain language that marketers can act on immediately.
Never declare a winner without sufficient sample size. Always check segment breakdown, not just overall results. If results differ significantly between segments, call it out and recommend separate approaches.
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 · 84 lines · 96 tokens per session scan A 73d88c610751
ab-test-analyzer is a skill published in the GitHub repository thaolst/ai-growth-agents-for-marketers (5 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 652 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
find-leads
Find qualified B2B leads with OpenOutreach — run openoutreach find N [emails], read the CSV it prints on stdout, and hand the rows to whatever sends. Use when the user wants leads, prospects, an ICP-matched contact list, or asks what a campaign already has. Also covers first-run setup (openoutreach init), openoutreach…
competitors
Audit competitors using ScaleBrick's 3-surface framework (social, web/pages, SEO). Categorizes their pricing, features, and landing pages. Identifies gaps you can exploit, positioning angles no one is claiming, and specific moves you can make this week.
audit
Analyze whether TikTok or Instagram search traffic is a viable growth channel for your business. Uses ScaleBrick's framework to evaluate demand, competition, content fit, and intent categories. Ends with a go/no-go recommendation.
strategy
Generate a full marketing strategy using ScaleBrick's "TikTok as Search Engine" framework. Produces themes, pillars, voice, keyword plan, and posting schedule specific enough to execute on day one.
keywords
Research high-intent TikTok and Instagram search keywords using ScaleBrick's framework. Returns categorized keywords with intent type, search volume estimate, difficulty score, and content angle for each.
11-ai-growth
Prompt để tận dụng AI trong growth marketing. Từ personalization, segmentation, campaign optimization đến predictive analytics và gamification.