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 Humblytics/humblytics-marketing-skills --skill ab-test-generatorgit clone --depth 1 https://github.com/Humblytics/humblytics-marketing-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/humblytics/humblytics-marketing-skills/ab-test-generator)<a href="https://agentmods.dev/skills/humblytics/humblytics-marketing-skills/ab-test-generator"><img src="https://agentmods.dev/badge/skills/humblytics/humblytics-marketing-skills/ab-test-generator/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/humblytics/humblytics-marketing-skills/ab-test-generator"><img src="https://agentmods.dev/badge/skills/humblytics/humblytics-marketing-skills/ab-test-generator.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 | $0.00087 | $0.02926 |
| Opus 5 | $0.00044 | $0.01463 |
| Sonnet 5 | $0.00017 | $0.00585 |
| Haiku 4.5 | $0.00009 | $0.00293 |
Grade A, and why
ab-test-generator 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A/B Test Generator
Purpose
Generate data-driven A/B test configurations from Humblytics analytics and heatmap data. This skill creates complete test definitions including hypotheses, variant specifications with CSS/element selectors, success metrics, sample size requirements, and can launch tests directly through the Humblytics MCP.
Live data comes from the Humblytics MCP (server humblytics) — read tools like get_page_details, get_clicks_details, and get_split_test_recommendations, and write tools like create_split_test, update_split_test, and stop_split_test.
When to Use
- Creating A/B tests from conversion data or heatmap insights
- Generating test hypotheses for a specific page or funnel step
- Launching no-code split tests via the Humblytics MCP
- Calculating required sample size and test duration
- Designing multivariate test matrices
- Reviewing and iterating on existing test results
Setup
This skill calls the Humblytics MCP (server humblytics) for all live data and test launches — connect it once and the MCP handles auth, base URL, and property resolution. See the repo README for connection steps. The skill then calls mcp__humblytics__* tools directly; there is no per-run key to export.
Keep the security ethos: never paste API keys directly into chat and never commit a .env — the key now lives in the MCP connection headers, set once. For a single-property key the MCP auto-resolves the property; for a multi-property key call list_properties and pass the propertyId you want.
Before You Start
- Confirm property and page — Which page URL to test (the MCP resolves the property; use
list_propertiesonly for multi-property keys) - Pull current data — Retrieve page analytics, click data, and current conversion rate via the MCP
- Check existing tests — Look for any running tests to avoid conflicts (
list_split_tests) - Understand the goal — What is the primary conversion action on this page?
- Verify traffic volume — Ensure enough traffic for statistical significance within a reasonable timeframe
- Check for context — Look for product briefs, AGENTS.md, or existing CRO documents that inform test direction
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 · 254 lines · 87 tokens per session scan A 36b8f8a49a03
ab-test-generator is a skill published in the GitHub repository Humblytics/humblytics-marketing-skills (84 stars, last pushed 8d ago), licensed MIT. It adds 87 tokens to every session and 2,926 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
ab-test-generator
Generate A/B test variants for affiliate content. Triggers on: "create A/B test", "test my headline", "optimize my CTA", "generate variants", "split test ideas", "improve click-through rate", "test my landing page copy", "headline alternatives", "CTA variations", "which version is better", "optimize conversions"…
creating-online-evaluations
Author continuously-running online evaluations in PostHog AI observability, grounded in real failure modes you've identified. Use when the user wants evaluations that automatically score new generations or whole traces going forward — "create an eval to catch X", "continuously check that responses do Y", "turn these…
exploring-llm-evaluations
Investigate AI observability evaluations — hog (deterministic code-based), llmjudge (LLM-prompt-based), and sentiment (user-message sentiment). Find existing evaluations, inspect their configuration, run them against specific generations, query individual results, and set up scheduled reports on an evaluation. Use…
exploring-llm-traces
Debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/ or /ai-observability/sessions/ ), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect…
querying-canvas-data
Get PostHog data into a canvas correctly: the host-injected ph SDK (loadInsight, query, capture, state, connectors, openExternal, navigate), the data hierarchy (saved insights first, typed query nodes second, inline HogQL last), verifiability (insight-backed metrics link their saved insight in PostHog; ad-hoc queries…
investigating-error-issue
Investigates a single PostHog error tracking issue end-to-end. Use when the user provides an issue ID or pastes an issue URL (/errortracking/ ) and wants to understand the error — who it affects, what triggers it, when it started, whether it correlates with a release, browser, OS, or feature flag, and what the next…