cro

cro is a skill for Claude Code, Codex from alebgl77/claude-inc. It costs 99 tokens per session (1,022 once invoked), scanned A, original, MIT.

A conversion-rate optimisation reviewer for examining a page or funnel and finding what may stop visitors from completing its main action.

In plain words
What is it for?
Use it to review landing pages, pricing pages, trials, or sign-up flows, then plan A/B tests with success measures and sample-size guidance.
Why use it?
It replaces vague design opinions with a section-by-section record of clarity, risk, distraction, and motivation problems, plus prioritised experiments.

Skill for Claude CodeCodex

Part of the claude-inc plugin — 46 skills, 3 commands, 8 agents shipped together

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/alebgl77/claude-inc/cro
Any agent
npx skills add alebgl77/claude-inc --skill cro
Clone the repo
git clone --depth 1 https://github.com/alebgl77/claude-inc

Made for: Claude Code, Codex.

Or install claude-inc, the plugin that ships this one along with the rest of its 46 skills, 3 commands, 8 agents.

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.

agentmods badge for cro

README.md
[![agentmods](https://agentmods.dev/badge/skills/alebgl77/claude-inc/cro.svg)](https://agentmods.dev/skills/alebgl77/claude-inc/cro)
Your own site
<a href="https://agentmods.dev/skills/alebgl77/claude-inc/cro"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/cro.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,022 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.

ModelPer sessionOnce invoked
Fable 5 $0.00099 $0.01022
Opus 5 $0.00049 $0.00511
Sonnet 5 $0.00020 $0.00204
Haiku 4.5 $0.00010 $0.00102

Measured 4d ago against content hash 02bc12e4f3b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cro 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 4d 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/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRO — Conversion Lead

"Lift conversion rates"

When to use

  • A page or funnel underperforms — "the trial page converts at 1.8%, find out why"
  • Prioritizing experiments — "we can run 3 tests this quarter, which ones?"
  • Pre-launch conversion review — "sanity-check this pricing page before we ship"
  • Post-change regression — "signups dropped 20% after the redesign"
  • Not for writing the new copy itself — findings hand off to copywriting

Workflow

  1. Collect the funnel. Page URL/HTML/screenshots, current conversion rate, traffic sources, and the exact conversion event. No baseline number? Ask for the best estimate and mark the audit directional.
  2. Walk the friction log. Top to bottom, section by section, log every issue under four labels:
    • Clarity — can a first-time visitor say what this is and who it's for within 5 seconds?
    • Anxiety — unanswered risk: price surprises, data use, "what happens after I click?"
    • Distraction — competing links, carousels, anything pulling from the one intended action
    • Motivation — generic value prop, benefits stated as features, no reason to act now
  3. Run the heuristics.
    • Message match — does the headline repeat the promise of the ad or link that brought the click?
    • Above-the-fold value prop — headline + benefit + CTA visible without scrolling?
    • Form cost — field count × sensitivity; every field must earn its place
  4. Write the hypothesis backlog. One per finding: "Because we observed [evidence], changing [element] to [variant] will improve [metric]."
  5. Score ICE. Impact, Confidence, Ease — each 1-10 with a one-line justification. Rank by the product.
  6. Design the top 3 tests. Control vs variant spec, one primary metric, one guardrail metric, and a minimum-sample note: rough visitors per arm at the current baseline for a realistic lift. Flag tests that traffic volume would stretch past a month.
  7. Deliver the report in the format below and name the single first test to launch.

Read the full file on GitHub · 78 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.

  1. 4d ago First seen · 78 lines · 99 tokens per session scan A 02bc12e4f3b2

Subscribe to this mod's changes

cro is a skill published in the GitHub repository alebgl77/claude-inc (14 stars, last pushed yesterday), licensed MIT. It adds 99 tokens to every session and 1,022 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

mempalace-task

Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.

MemPalace/mempalace · 67 tokens

stale-sweep

Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…

googleapis/mcp-toolbox · 159 tokens

ceo-setup

One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 60 tokens

commitment-setup

One-time setup for the commitments tracking system. Creates workspace structure, schema docs, and installs triage and digest missions. Excluded from activation once projects/commitments/README.md exists in the workspace (the file this skill writes as its first step).

suyoumo/ClawProBench · 58 tokens

project-manager

Project management expert for Agile, estimation, risk management, and stakeholder communication.

RightNow-AI/openfang · 17 tokens

linear

Linear issue tracker API integration. Covers first-use identity bootstrap (viewer + teams cached), raw GraphQL for list/search/create/update, and the rules for handling "my issues" / "assigned to me" requests.

suyoumo/ClawProBench · 45 tokens