More screenshots

    Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIGitHub CopilotGitHub CopilotGemini CLIGemini CLI+20 more

    🧪 Channel Experiment Postmortem

    1

    Audit one completed channel test against its predeclared qualified gate, attribution, owner exclusion, budgets, changed variables, and cooldown.

    $5

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    0 installsSecurity scanned
    🧪 Channel Experiment Postmortem

    🧪 Channel Experiment Postmortem

    Example session with this skill installed

    A 14-day directory experiment with a predeclared two-checkout-open gate, one changed artifact, two verified external events, zero cost, three effort hours, and a seven-day cooldown.

    • Read your context and instructions
    • Compiled the channel experiment postmortem

    REACHED with two eligible checkout openings, READY packet status, no budget overrun, one isolated changed variable, and a reminder that the result does not prove causality or repeatability.

    Connects securely to your tools. The creator never sees your data.

    What you get

    Close a marketplace or directory test against its predeclared qualified gateExclude impressions, owner activity, weak attribution, and out-of-window eventsRecord whether aggregate cost or effort exceeded its stop conditionDetermine when a bounded one-variable follow-up may begin after cooldown

    About this skill

    Channel Experiment Postmortem evaluates one owner-supplied completed distribution or marketing test against its predeclared objective, qualified outcome gate, measurement window, attribution, owner-activity exclusion, aggregate cost and effort limits, changed variables, and cooldown. The deterministic offline helper validates every event before filtering, rejects vanity gates, unknown event types, malformed actor or attribution fields, URL-shaped evidence references, and unsafe output paths. It returns REACHED, NOT_REACHED, or CANNOT_DETERMINE; eligible event counts; an explicit budget receipt; isolation and cooldown findings; and stable SHA-256 receipts. Reaching a gate does not prove causality or repeatability. The skill does not retrieve analytics, contact anyone, auto-follow up, publish, or impersonate the owner.

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 1 month ago

    • Passed all security checks, Safe to install

    Listed1 month ago

    Frequently Asked Questions