Hero
by
Homepage hero decisions for ecommerce teams: read what the current hero actually earns per visitor, then recommend the asset and copy to replace it with.
The homepage hero is the single most viewed piece of creative a store owns and usually the least measured. It gets changed on a seasonal schedule or when someone senior dislikes it, and the replacement is judged on how it looks rather than on what it earned. The reason is structural: the hero influences revenue through a chain of clicks and sessions that nobody attributes back to it, so there is no number to defend. This skill measures what the current hero earns per visitor, then recommends the asset and the copy to replace it with.
What It Does
- Measures revenue per homepage visitor attributable to the current hero.
- Separates hero performance from seasonal traffic changes underneath it.
- Reads which products the hero actually sends people to, and what they earn.
- Tests headline clarity against the category language your customers search.
- Checks that the promoted product has the stock to support the placement.
- Recommends the replacement asset and the copy, with what to keep.
Use Cases
- Replace a hero on evidence rather than on a seasonal calendar.
- Find out the current hero sends traffic to a product with two weeks of cover.
- Stop a redesign from removing the element doing the converting.
- Give a designer a brief with the headline and the product already decided.
Example Session
Is our homepage hero working, and what should replace it?
It converts fine and sends people to the wrong product.
- Metric | Current hero | Site average | Read
- Hero click rate | 31% | n/a | Healthy
- Revenue per homepage visitor | $1.84 | $2.41 | Below
- Destination product margin | 22% | 47% | Low
- Destination stock cover | 16 days | n/a | Thin
Nearly a third of homepage visitors click the hero, so the creative is doing its job. It points them at your thinnest margin product, which has sixteen days of cover, so every click sends attention somewhere it earns least and cannot be replaced. Keep the format and the photographic treatment, point it at the navy jacket, and lead with the category word customers actually search rather than the campaign name.
Why This Beats Prompting It Yourself
How The Hero Looks vs What It Earns Per Visitor: The Hidden Risk
A generic prompt evaluates a hero on composition, clarity and hierarchy, which is a real critique and not the one that decides revenue. A beautifully judged hero pointing at a 22% margin product with two weeks of cover is a design success and a commercial mistake, and nothing in the visual review will catch it.
When You Still Need To Keep What Is Working
Most hero replacements change everything at once, which throws away the 31% click rate along with the wrong destination. This skill separates the part that works from the part that does not and briefs a change to the destination and the headline only. Replacing a hero wholesale is how a site loses a converting element and never learns which one it was.
Known Limitations
Attributing revenue to a hero requires session-level path data, and where that is unavailable the skill reports click rate and destination economics without the revenue-per-visitor figure. Seasonal separation needs at least one comparable prior period. It recommends the asset direction and the copy, and does not produce imagery or publish anything to your storefront.
Install It
- Download the ZIP.
It is free and there is no account to create. - Unzip it into your agent's skills folder.
Claude Code reads ~/.claude/skills/, which is hidden by default: the command in the folder block opens it. Other agents scan their own directory, so drop the same folder there instead. - Ask your agent to use it.
Restart the agent if it was already running, then it picks the skill up with no config.
skills folder
Copy
~/.claude/skills/hero/
SKILL.md
references/hero-metrics.md
recommendations/
# one file per review, with the copy
# macOS: create the folder and open it in Finder
mkdir -p ~/.claude/skills && open ~/.claude/skills
# Windows: paste in the Explorer address bar
%USERPROFILE%\.claude\skills\Frequently asked questions
How is this different from asking for design feedback?
Design feedback judges the asset. This judges the placement: what it earns per homepage visitor, where it sends them, and whether that product can support the traffic. Those questions frequently have a worse answer than the design does.
Which agents does the skill run in?
Any agent that supports the open SKILL.md format: Claude Code, Cursor, Codex CLI, GitHub Copilot, Gemini CLI, Manus, Grok and others load it unmodified. The format is portable, the location is not. Each agent scans its own skills directory, so you drop the same folder into whichever one yours uses. There is no config file to edit and no API key to provision.
What does it need connected to work?
Homepage session data with click paths, order data, product margin, and stock on hand. Without path data it still reads destination economics and says the revenue-per-visitor figure is unavailable.
Why does it check stock on the destination product?
Because the homepage hero is the largest traffic source you control, and pointing it at a product with sixteen days of cover creates a stockout on your most visible item. The placement is only as good as the inventory behind it.
Does it write the headline?
It recommends the headline, tested against the category language your customers actually search rather than internal campaign naming. The wording is a starting point you should expect to edit, and the product and angle are the parts that matter.
What is included with the skill?
The skill itself, the hero metrics reference, the recommendation format, and the copy guidelines. It is free and security scanned. We re-publish the ZIP when the metrics change, so download it again if your readings start shifting.
The hero slot is the most expensive real estate you own.
Polar puts revenue per session and margin per collection on one definition, so the asset you promote is the one that pays for the placement.
<script type="application/ld+json">{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"How is this different from asking for design feedback?","acceptedAnswer":{"@type":"Answer","text":"Design feedback judges the asset. This judges the placement: what it earns per homepage visitor, where it sends them, and whether that product can support the traffic. Those questions frequently have a worse answer than the design does."}},{"@type":"Question","name":"Which agents does the skill run in?","acceptedAnswer":{"@type":"Answer","text":"Any agent that supports the open SKILL.md format: Claude Code, Cursor, Codex CLI, GitHub Copilot, Gemini CLI, Manus, Grok and others load it unmodified. The format is portable, the location is not. Each agent scans its own skills directory, so you drop the same folder into whichever one yours uses. There is no config file to edit and no API key to provision."}},{"@type":"Question","name":"What does it need connected to work?","acceptedAnswer":{"@type":"Answer","text":"Homepage session data with click paths, order data, product margin, and stock on hand. Without path data it still reads destination economics and says the revenue-per-visitor figure is unavailable."}},{"@type":"Question","name":"Why does it check stock on the destination product?","acceptedAnswer":{"@type":"Answer","text":"Because the homepage hero is the largest traffic source you control, and pointing it at a product with sixteen days of cover creates a stockout on your most visible item. The placement is only as good as the inventory behind it."}},{"@type":"Question","name":"Does it write the headline?","acceptedAnswer":{"@type":"Answer","text":"It recommends the headline, tested against the category language your customers actually search rather than internal campaign naming. The wording is a starting point you should expect to edit, and the product and angle are the parts that matter."}},{"@type":"Question","name":"What is included with the skill?","acceptedAnswer":{"@type":"Answer","text":"The skill itself, the hero metrics reference, the recommendation format, and the copy guidelines. It is free and security scanned. We re-publish the ZIP when the metrics change, so download it again if your readings start shifting."}}]}</script>