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 LeadMagic/gtm-skills --skill a-b-testinggit clone --depth 1 https://github.com/LeadMagic/gtm-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/leadmagic/gtm-skills/a-b-testing)<a href="https://agentmods.dev/skills/leadmagic/gtm-skills/a-b-testing"><img src="https://agentmods.dev/badge/skills/leadmagic/gtm-skills/a-b-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/leadmagic/gtm-skills/a-b-testing"><img src="https://agentmods.dev/badge/skills/leadmagic/gtm-skills/a-b-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00066 | $0.06006 |
| Opus 5.5 | $0.00026 | $0.02402 |
| Sonnet 5.5 | $0.00013 | $0.01201 |
| Haiku 4.5 | $0.00007 | $0.00601 |
Grade A, and why
a-b-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 23d 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 — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A/B Testing
Overview
A/B Testing brings experimental rigor to GTM optimization. The core principle: most "optimizations" are guesswork dressed as strategy. Teams change subject lines because someone "feels" they're better, rewrite copy based on a single positive reply, or abandon channels because of one bad week. This skill prevents the waste of optimizing based on noise rather than signal.
The non-obvious rule: statistical significance is necessary but insufficient. A statistically significant 10% improvement in open rate that produces 0% more meetings is a distraction. Optimize for downstream revenue metrics — reply rate, meeting rate, conversion rate — not vanity metrics. Every test must trace its impact through the full funnel.
This skill produces: an Experiment Design Document with hypothesis, success metrics, power analysis, and methodology; a prioritized ICE/PIE test backlog; a 30/60/90-day testing roadmap; and a Results Analysis Report with statistical tests, confidence intervals, and scale/stop/kill recommendations.
When to Use
- User says "A/B test" or "split test" → activate this skill
- User mentions "test subject lines" or "test email copy" → use for experimental design
- User asks "is this statistically significant" or "what sample size do I need" → activate for statistical guidance
- User says "experiment design" or "test plan" → use this skill
- User asks "how do I prioritize tests" or "what should I test next" → use ICE/PIE scoring
- User mentions "testing roadmap" or "experiment cadence" → plan the roadmap
- Trigger phrases: A/B testing, split testing, experiment, statistical significance, confidence interval, sample size, test variant, control group, multivariate test
Do NOT use for:
- Analyzing existing campaign performance without test design → use campaign-analytics
- Writing copy variants → use cold-email-copywriting (run after this skill for variant creation)
- General campaign analytics and benchmarking → use campaign-analytics
- Setting up sequences or cadences → use cold-email-strategy
- Landing page CRO (broader scope) → use landing-pages
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 23d ago Changed 8b9a245d5b1f
- 1mo ago Changed 6e07c57872a7
- 1mo ago First seen · 392 lines · 66 tokens per session scan A 263ff164ae97
a-b-testing is a skill published in the GitHub repository LeadMagic/gtm-skills (67 stars, last pushed 11d ago), licensed MIT. It adds 66 tokens to every session and 6,006 once invoked, about $0.0003 per session on Opus 5.5. 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
ai-gtm-transformation-audit
Use this skill when a GTM leader (CRO, CMO, VP Sales, RevOps, CS leader, founder) wants to know where their organization really stands on its AI GTM transformation, what is holding it there, and what to do in the next 30 days to move up. It runs a short structured interview, places the org on one of four levels…
event-lead-ingestion
Use this skill when a teammate pastes a LinkedIn URL or work email for someone they just met at a booth, dinner or conference hallway and wants that lead captured the same way every time. It resolves the person and company, checks relationship history before scoring, writes the CRM record and a structured conversation…
competitor-monitoring
Use this skill when you need to know what rival companies are doing — "what are my competitors doing", "competitor update", "competitor news", "competitive landscape", "market intel", "what's new with [company]", "track [company]", "competitor briefing", "who's making moves", "we keep losing deals to [company]" — or…
event-room-intelligence
Use this skill 1 to 3 days before any face-to-face event where you hold a registration export (a talk, conference, dinner, booth) and the question is 'I have the attendee CSV, who should I talk to?'. It maps every registrant to a company, joins the list against the live CRM, LinkedIn-verifies every person's title and…
multichannel-campaign-builder
Use this skill when someone needs a complete outbound sequence written — every touch across LinkedIn and email, not a single cold email. Produces three distinct angles to choose from, then the full sequence with each message ready to send, calibrated to the campaign type and channel mix and self-checked against a…
event-account-plan
Use this skill in the weeks before a conference, trade show, or field event, when an attendee or registration list exists and the question is which companies to work, who to talk to at each one, and what to say. Trigger on "we have the attendee list for the show", "who should we target at this conference", "build the…