What is cro-optimizer?

A conversion-rate optimization skill that examines how people move through a website or product and where they stop. Conversion rate is the share of visitors who complete a target action, such as signing up.

Use it to inspect signup and other conversion funnels, compare results across user groups, and create a ranked list of A/B test ideas.

It turns analytics data into a clear view of where users drop out, so teams can focus testing on the biggest problems.

cro-optimizer — Skill for Claude Code and Codex by Humblytics

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.

Any agent

npx skills add Humblytics/humblytics-marketing-skills --skill cro-optimizer

Clone the repo

git clone --depth 1 https://github.com/Humblytics/humblytics-marketing-skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/humblytics/humblytics-marketing-skills/cro-optimizer/github.svg)](https://agentmods.dev/skills/humblytics/humblytics-marketing-skills/cro-optimizer)

Your own site

<a href="https://agentmods.dev/skills/humblytics/humblytics-marketing-skills/cro-optimizer"><img src="https://agentmods.dev/badge/skills/humblytics/humblytics-marketing-skills/cro-optimizer/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/humblytics/humblytics-marketing-skills/cro-optimizer"><img src="https://agentmods.dev/badge/skills/humblytics/humblytics-marketing-skills/cro-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,689 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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 5.1	$0.00076	$0.02689
Opus 5.5	$0.00030	$0.01076
Sonnet 5.5	$0.00015	$0.00538
Haiku 4.5	$0.00008	$0.00269

Measured 2mo ago against content hash 4e34de51e7ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cro-optimizer 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 2mo 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.

skills/cro-optimizer/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRO Optimizer

Purpose

Analyze conversion funnels using live Humblytics analytics (via the Humblytics MCP), identify the highest-impact drop-off points, and generate prioritized A/B test hypotheses with expected conversion-rate / volume impact. This skill turns raw analytics into a ranked optimization roadmap.

When to Use

Diagnosing why a funnel is underperforming
Identifying the biggest conversion bottleneck across a user journey
Generating a prioritized list of A/B test ideas
Preparing a CRO sprint plan or quarterly optimization roadmap
Analyzing page-level or step-level drop-off rates
Comparing conversion performance across segments (device, source, geography)

Credentials

Live data comes from the Humblytics MCP (server humblytics). Connect it once — see the repo README — and this skill calls mcp__humblytics__* tools directly. No API keys, base URLs, or .env plumbing live in the skill.

Never paste API keys into chat — they persist in transcripts and logs. Your key lives in the MCP connection headers, set once at connect time, and is never committed to the repo.
Property: the MCP auto-resolves your property for a single-property key (the common case). For a multi-property key, call list_properties and pass the propertyId you want to analyze.
Docs: https://docs.humblytics.com/api

Before You Start

Confirm the property — The MCP auto-resolves the property for a single-property key. If the key covers multiple properties, call list_properties and confirm which one to analyze.
Identify the funnel — Clarify which conversion flow to examine (e.g., homepage > pricing > signup > onboarding)
Check for context — Look for existing project docs, AGENTS.md, or product briefs that describe the business model, target audience, and current conversion goals
Establish the time range — Default to last 30 days; ask if the user wants a different window
Confirm MCP access — Verify the Humblytics MCP (server humblytics) is connected before pulling data

Read the full file on GitHub · 187 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.

2mo ago First seen · 187 lines · 76 tokens per session scan A 4e34de51e7ad

Subscribe to this mod's changes

cro-optimizer is a skill published in the GitHub repository Humblytics/humblytics-marketing-skills (85 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 2,689 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.

Analytics and metrics Claude Code Marketing and SEO ab-testing agent-skills attribution claude

cro-optimizer next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cro-optimizerHumblytics/humblytics-marketing-skills	Skill	85	1mo ago	MIT	A	76	Claude Code, Codex
authoring-ci-workflowsPostHog/posthog	Skill	41k	yesterday	none	A	200	Claude Code, Codex
isolating-product-facade-contractsPostHog/posthog	Skill	41k	yesterday	none	A	76	Claude Code, Codex
triaging-merge-queue-failuresPostHog/posthog	Skill	41k	yesterday	none	A	180	Claude Code, Codex
creating-online-evaluationsPostHog/posthog	Skill	41k	yesterday	none	A	203	Claude Code, Codex
debugging-mcp-analyticsPostHog/posthog	Skill	41k	yesterday	none	A	211	Claude Code, Codex
building-product-empty-statesPostHog/posthog	Skill	41k	yesterday	none	A	133	Claude Code, Codex