agentleFS
Infinite-Labs-AIInfinite-Labs-AI/infinite-skills/skills/ecommerce-app-cro/SKILL.md

ecommerce-app-cro

Skill43 starsChanged 4 months agoMITView on GitHub

Use when improving ecommerce product pages, collection pages, carts, checkout, subscriptions, app store listings, screenshots, reviews, or mobile conversion surfaces.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Look for gaps in proof, comparison, sizing, benefit clarity, social proof, risk reversal, visual explanation, shipping or billing …

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ecommerce and App CRO

Improve product pages, carts, app listings, screenshots, paywalls, and checkout surfaces where users are close to buying or installing.

Identify The Surface

Classify the request:

  • Ecommerce product page.
  • Collection or category page.
  • Cart or checkout.
  • Subscription landing page.
  • App store or Play listing.
  • In-app paywall.
  • Mobile onboarding purchase moment.

Gather the URL, screenshots, product details, traffic source, current conversion rate if known, price, reviews, and return or cancellation concerns.

Diagnose The Buying Question

Each surface must answer a different question:

  • Product page: is this right for me?
  • Collection page: which option should I choose?
  • Cart: should I finish now?
  • Checkout: can I trust this transaction?
  • App listing: is this worth installing?
  • Paywall: is the paid version worth it now?

Classify the blocker:

  • Fit: is this right for me?
  • Trust: can I believe this?
  • Risk: what happens if I choose wrong?
  • Value: is it worth the price, time, or install?
  • Urgency: why act now instead of later?
  • Completion effort: what makes finishing feel hard?

Look for gaps in proof, comparison, sizing, benefit clarity, social proof, risk reversal, visual explanation, shipping or billing transparency, and mobile usability.

Recommend Surface Changes

Use channel-native fixes:

  • Product images that show scale, use, outcome, and details.
  • Review snippets tied to objections.
  • Variant or plan comparison.
  • Clear shipping, returns, billing, and renewal terms.
  • Screenshot order that tells the app’s value story.
  • Paywall copy tied to the activation moment.
  • Checkout reassurance without clutter.

Output

Conversion surface:
[surface and goal]

Buyer question:
[what must be answered]

Friction points:
| Blocker | Problem | Evidence | Fix |

Asset changes:
- Image/screenshot:
- Copy:
- Proof:
- Offer:
- UX:

Priority fixes:
1. [fix]
2. [fix]
3. [fix]

Test idea:
[what to test and how to judge it]

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.