A structured way to run and judge an A/B test, where two ad variants are compared by changing one thing. It uses a stated hypothesis, fixed test period, sample minimum, and separate result for each variant.

For testing whether one advertising change performs better than another. It helps set the success measure, test duration, sample requirement, and final decision.

It prevents guesses based on noisy results, changing several things at once, or checking too early. An inconclusive result is allowed when the evidence is insufficient.

experiment — Skill by logly

Install

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.

agentmods

npx agentmods add skills/logly/mureo/experiment

Any agent

npx skills add logly/mureo --skill experiment

Clone the repo

git clone --depth 1 https://github.com/logly/mureo

Made for: Claude Code, Codex.

Per session 169 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,780 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00169	$0.04780
Opus 5	$0.00084	$0.02390
Sonnet 5	$0.00034	$0.00956
Haiku 4.5	$0.00017	$0.00478

Measured 2d ago against content hash 0430d1db99c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

experiment 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 2d 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.

mureo/_data/skills/experiment/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Experiment

PREREQUISITE: Read ../_mureo-shared/SKILL.md for auth, security rules, output format, and Tool Selection (Read/Write on Code, mureo_strategy_* / mureo_state_* MCP on Desktop / Cowork).

Turn an ad-hoc change into a designed experiment. Most "we tried X and CPA moved" claims are noise — one variable was never isolated, the window was never fixed, and the decision was made by peeking. This skill enforces the discipline: a falsifiable hypothesis, exactly one variable, a success metric tied to a Goal, a pre-committed duration and sample floor, no peeking, and a per-variant verdict where inconclusive is a valid outcome.

Read ../_mureo-learning/SKILL.md first — its Observation Windows and Minimum Sample Sizes tables set the duration and sample floor this skill commits to, and its evidence lifecycle is the rulebook for the no-peeking rule below.

Prerequisites

STRATEGY.md and STATE.json must exist (run the onboard skill first)

Steps

Before you start: Run the Diagnostic preamble from ../_mureo-shared/SKILL.md — load learning insights (mureo_learning_insights_get) and consult advisors (mureo_consult_advisor) before drawing conclusions.

Establish today: call mureo_state_get first, on every host (including Claude Code, where you would otherwise Read the file) and take server_now from its response — ISO 8601 with UTC offset, e.g. 2026-07-28T10:12:33+09:00. Its date is the only source of the current date for this run: the designed window's start_time / end_time, the observation_due you commit to in step 7, and the "has the window closed?" gate in step 9 are all measured from it. A stale date is not cosmetic here — it is how a test gets evaluated early, which is precisely the peeking failure step 8 forbids. Do not shell out (this skill must run in Bash-less headless hosts) and do not read the date off STATE.json — last_synced_at, reports.*.period and action_log timestamps are history, never evidence of what day it is now. Never write server_now into STATE.json: it is a response field, and a persisted copy becomes tomorrow's stale "today".

Read the full file on GitHub · 83 lines

Changes

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.

2d ago First seen · 83 lines · 169 tokens per session scan A 0430d1db99c2

Subscribe to this mod's changes

experiment is a skill published in the GitHub repository logly/mureo (42 stars, last pushed 2d ago), licensed Apache-2.0. It adds 169 tokens to every session and 4,780 once invoked, about $0.0008 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.

Analytics and metrics Marketing and SEO advertising ai-agents cli google-ads marketing mcp

adcp-advertising

Automate advertising campaigns with AI. Create ads, buy media, manage ad budgets, discover ad inventory, run display ads, video ads, CTV campaigns, and optimize ad performance. Perfect for marketing automation, programmatic advertising, media buying, ad management, campaign optimization, creative management, and…

LeoYeAI/openclaw-master-skills · 103 tokens

adspirer-ads-agent

Adspirer — AI-powered advertising and performance marketing agent. Manage Google Ads, Meta Ads (Facebook & Instagram), LinkedIn Ads, and TikTok Ads via natural language. 400+ tools for paid media campaign creation, live performance analysis, PPC keyword research with real CPC data, budget optimization, ad creative…

amekala/ads-mcp · 187 tokens

cold-email-outreach

Run end-to-end B2B cold-email outreach through the Hyper MCP — enrich prospects with Apollo, scrape per-prospect signals from company sites and LinkedIn, draft personalized emails using proven hook frameworks, send via Gmail with safe defaults, and route replies into labeled folders. Use when the user wants to write…

hyperfx-ai/marketing-skills · 101 tokens

competitor-intel

Run end-to-end competitor research and monitoring through the Hyper MCP — pick the set, scrape every public surface (site, blog, pricing, organic social, search rank, mentions, demand) via Firecrawl + HyperSEO + the Apify scrapers, diff against last run, and synthesize a brief. Use when the user wants to research…

hyperfx-ai/marketing-skills · 107 tokens

blog-generation

Generate one excellent, on-brand blog post per run for any business, built to rank on Google and get cited by AI search (ChatGPT, Claude, Perplexity, AI Overviews). A stateful engine: reads a brand strategy doc, picks a fresh topic (never repeats), researches, writes in the brand's voice, and logs the post back. Use…

hyperfx-ai/marketing-skills · 117 tokens

email-lifecycle

Plan, build, and run lifecycle email programs through the Hyper MCP — welcome / onboarding, nurture, re-engagement, win-back, and abandoned-cart sequences across whichever provider fits (Klaviyo for ecommerce, Resend for SaaS / dev tools, Beehiiv for newsletters, Gmail for low-volume ops). Use when the user wants to…

hyperfx-ai/marketing-skills · 111 tokens