CRO auditor

Audit a funnel, page, or signup flow, pre-register the strongest CRO tests, and read measured results back into a human-approved pattern library.

Saves you ~4.6 h / week

Start with this playbook

How it works

Trigger: On the “Review due CRO experiments” schedule.
Job: Audit conversion data and build an evidence-ranked test backlog.
Outcome: An evidence-ranked conversion test backlog.

What it installs

Agents 2

CRO Analyst

Turns a page, funnel, or signup flow into an audit and ranked, testable hypotheses.
CRO auditor Quality Reviewer

Checks primary evidence, domain controls, deliverable completeness, and communication quality, stopping the run when the work is wrong, unsupported, incomplete, or uncertain.

Teams 1

CRO auditor quality team

The delivery agents produce the work while an independent quality reviewer checks each workflow handoff against explicit evidence, domain, and communication requirements before the run can continue.

Workflows 2

CRO audit

Frame and gather data, audit, build an ICE-ranked backlog, verify the top test's validity, then hand off for approval.
CRO experiment readback

Pull due experiment results, validate the comparison, obtain a human decision, and preserve the approved evidence and reusable pattern.

Documents 2

CRO experiment register

The pre-registered hypotheses, measurement plans, due readbacks, results, and human decisions for every CRO test.
Approved CRO patterns

The reusable conversion patterns a human approved after a completed, source-backed experiment readback.

Goals 1

Conversion up

Run a continuous experimentation program that lifts conversion by acting on the highest-ICE friction first. Success looks like: A standing backlog of 20+ ICE-scored A/B hypotheses, a pre-registered measurement plan and scheduled readback for every approved test, and a human-approved pattern library that preserves wins, losses, and unproven results with their source evidence.

Skills 4

cro

Audits marketing pages (homepage, landing, pricing, feature, lead-capture) for conversion across value-prop clarity, headline, CTA, hierarchy, trust, objections, and friction, then outputs quick wins, high-impact changes, and ranked test ideas. Adapted from coreyhaines31/marketingskills/cro.
signup-flow-cro

Optimizes signup, registration, and trial-activation flows by minimizing required fields, showing value before commitment, reducing perceived effort, and fixing field-level drop-off, with mobile and post-submit guidance. Adapted from coreyhaines31/marketingskills/signup.
ab-test-setup

Designs statistically valid, prioritized A/B tests: a falsifiable hypothesis, one variable, pre-committed sample size, primary/secondary/guardrail metrics, allocation, and rigorous result reading — plus running experimentation as an ongoing ICE-scored program. Adapted from coreyhaines31/marketingskills/ab-testing.
cro-analytics-readback

Compares a pre-registered CRO test with its baseline, checks measurement integrity and confounders, and prepares a human decision without automatically promoting a result.

Schedules 1

Review due CRO experiments

Runs the source-backed readback for due experiments without changing live pages or promoting winners automatically. ## Professional quality control Objective: complete the recurring CRO auditor operating cycle and deliver a review-ready, evidence-backed result rather than merely report that the schedule ran. Start by fixing the review period, reading the current source records and prior run, confirming required access, and listing missing or contradictory inputs. Execute the bundle's full authored method in order, retaining source, calculation, command, or before/after evidence for load-bearing findings. Separate facts from interpretation, apply supplied policy without inventing thresholds, and stop any branch that requires missing authority or an unconfirmed human rule. Produce the complete named deliverable plus an evidence record, assumptions, exceptions, unresolved questions, and concrete next actions with owners where the method calls for them. Run the workflow's independent verifier checks and fix failures before requesting approval. The task is done only when every requested section and quality criterion passes or a blocker is explicit; silence, inaccessible data, or polished prose is not proof of completion. Verify audience, offer, substantiation, platform limits, configuration, attribution readiness, and worst-case spend against the approved cap. Public copy must be specific and on-voice, with no generic AI phrasing, filler, hype, fake urgency, unsupported superlatives, repetitive cadence, or claims that exceed the evidence. The human retains authority over publication, sending, spend, signing, merging, deployment, and other consequential external actions.

Connectors optional

PostHog

Connects to PostHog so the CRO analyst can pull real funnel drop-off, event, and experiment data for the audit.
Open the PostHog connector
Mixpanel

Connects to Mixpanel so the CRO analyst can pull real funnel drop-off, event, and experiment data for the audit.
Open the Mixpanel connector

Folders 1

CRO experiments

Requirements

Browser access to your analytics or session-recording tool — The agent reviews funnel drop-off, heatmaps, session recordings, and experiment results through the tool's web interface in your browser. It pauses for approval before queuing any experiment or recording a result. Until you connect it, it works from attached exports, screenshots, and the page itself.

Setup guide

How to Automate CRO Audits

A practical guide to automating CRO audits with an agent: a seven-dimension audit, ICE-ranked test hypotheses, and approval before any experiment runs.

Read the setup guide

Don't see your workflow? Describe it.

A sentence or two about a recurring job is enough. We design the playbook that runs it and show you exactly what it saves.