Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    marketing experiment results interpreter

    1

    Aggregate arm-level data only; respondent-level rows are refused.

    $1.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    About this skill

    Reads your finished campaign test and says what it proves: randomization audit, effect sizes with intervals and p-values, peeking and multiple-comparison flags, MDE, net value against incremental cost. Rollout and publishing stay human-approved drafts. Aggregate data only.

    What it does

    Interprets finished marketing campaign tests: randomization (SRM) audit, two-proportion and per-unit effect estimates with confidence intervals and p-values, Bonferroni and Benjamini-Hochberg multiplicity control, peeking and early-stopping flags, minimum detectable effect, practical and economic significance, and a rollout recommendation drafted for human approval. Aggregate arm-level data only; respondent-level rows are refused. Use when asked whether an A/B or campaign test result is statistically credible or just noise, whether a test was peeked at or over-tested, or what a proven effect costs versus earns before rollout.

    Use cases

    • Audit randomization and check whether a finished campaign test has enough signal to act on.
    • Report effect sizes with confidence intervals and multiple comparison control, flagging peeking or early stopping.
    • Weigh the measured effect against its incremental cost and draft a rollout recommendation for approval.

    What is included

    • SKILL.md: the workflow, trigger rules and output format.
    • references/: method notes and the markers used in outputs, loaded only when needed.
    • scripts/run.py: one self-contained Python script (standard library only) that does every calculation deterministically.
    • assets/: input and output schemas with a sample request and result.

    Limits

    Decision support only. Outputs label analytical estimates, information gaps and actions that need human approval. The skill does not send, publish, pay or change anything by itself, and it does not claim legal, regulatory or standards compliance.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 2 days ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listed2 days ago

    What's inside

    Frequently Asked Questions

    Reads your finished campaign test and says what it proves: randomization audit, effect sizes with intervals and p-values, peeking and multiple-comparison flags, MDE, net value against incremental cost. Rollout and publishing stay human-approved drafts. Aggregate data only.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use marketing experiment results interpreter on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.