agentleFS
manypicommanypicom/sales-skills/skills/ecommerce-store-prospecting/SKILL.md

ecommerce-store-prospecting

Skill1 starsChanged 2 months agoMITView on GitHub

Find and qualify online stores as prospects, using platform footprints, app stacks, catalogue size and traffic signals. Use whenever the user mentions ecommerce leads, Shopify stores, WooCommerce sites, online store prospecting, DTC brands, merchants as prospects, marketplace sellers, or wants to sell to online retailers. Also use when building a list for an agency, app or service that sells to store owners.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Paid app count is the strongest single qualifier: if you sell an app or a service.

    line 54
  2. Distinctive:

    Don't offer a free audit as the hook: Every agency does, and merchants have learned it's a sales call.

    line 111

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 Store Prospecting

Selling to online stores has an advantage most segments don't: nearly everything you need to qualify a merchant is publicly visible on their own website. The platform, the apps, the catalogue size, the shipping regions, the payment methods and the review volume are all readable without a database.

The difficulty is the opposite of most B2B: there are hundreds of thousands of stores, most are too small to buy anything, and the owner's email is rarely published.

Detecting the platform

Each platform leaves a signature in the page.

# Shopify
curl -s https://store.com | grep -ioE 'cdn\.shopify\.com|Shopify\.theme|shopify-features'

# WooCommerce
curl -s https://store.com | grep -ioE 'woocommerce|wp-content/plugins/woocommerce'

# BigCommerce, Magento, Squarespace, Wix, Webflow, Ecwid
curl -s https://store.com | grep -ioE 'bigcommerce|Magento|static1\.squarespace|wix\.com|webflow|ecwid'

# Headless or custom builds show none of these — check for a commerce API instead
curl -sI https://store.com | grep -iE '^(x-shopify|server|x-powered-by)'

Platform matters because it defines the integration surface, the buying behaviour and often the budget. Shopify merchants buy apps readily and at low friction. Custom-build merchants have engineers and different problems entirely.

Qualifying by size

Most stores can't afford a B2B contract. Size filtering is the difference between a workable list and a very large useless one, and none of the usual firmographics are available.

Proxies that work, in rough order of reliability:

SignalHow to read it
Product review volumeThe best proxy for order volume available publicly
Number of paid apps installedA store paying for 15 apps has revenue and a budget
Catalogue sizeProducts in the sitemap. Very small or enormous both mean something
Team or careers pageAny employees at all separates hobby from business
Custom theme vs defaultInvestment in the storefront
Multi-currency or multi-regionOperational maturity
Wholesale or B2B sectionRevenue diversity
Traffic estimatesDirectional only. Third-party estimates are wide
# Catalogue size on a Shopify store, from the sitemap
curl -s https://store.com/sitemap_products_1.xml | grep -c '<loc>'

Paid app count is the strongest single qualifier if you sell an app or a service. A merchant already paying for a dozen apps has demonstrated willingness to spend on tooling. One running the default theme with no apps generally hasn't.

The app stack as a signal

Installed apps are detectable from the page source and tell you more than the platform does.

  • Complementary apps installed → they invest in this area and you fit alongside
  • A competitor's app installed → displacement play, and you know exactly what they're paying for
  • An obvious gap → they run paid traffic with no analytics, or 500 products with no reviews widget
  • Recently removed something → churn from a competitor, if you can detect the leftover markup

The gap play is the strongest for cold email because the pitch is concrete and observable. See technographic-signals for the accuracy discipline — detect for segmentation, cite only what you can source.

Other sources of qualified stores

Marketplaces and app directories. A platform's own app store shows which merchants use which tools, and its partner directory lists agencies serving them.

Crowdfunding graduates. Successfully funded hardware and consumer campaigns become DTC brands with a product, a customer base and no operational infrastructure. Timing is everything — reach them as fulfilment starts.

Marketplace sellers. Sellers on the large marketplaces who also run their own store, or who don't yet and should.

Ad libraries. Public ad transparency libraries show which brands are actively spending on paid social. Active ad spend is a strong budget signal and a strong intent signal for anything conversion-related.

Review platforms and awards. Retail awards, "best of" merchant lists, platform case studies.

Trade shows and wholesale marketplaces, for brands selling both DTC and wholesale.

Finding the contact

The hard part. Store sites are built for consumers, not for B2B contact.

  1. The about or our-story page. DTC brands love a founder story, and it usually names them.
  2. Press or wholesale pages. Often carry a real business address rather than support@.
  3. The domain registration on smaller independent stores.
  4. Social profiles, where founders are frequently public and reachable.
  5. Company registry data for the trading entity.
  6. support@ or hello@ as a last resort — heavily filtered, read by a support agent, and rarely reaching the owner. Separate campaign if used at all. See email-verification.

For small DTC brands the founder is the buyer, which makes the founder story page the single most productive source.

Writing to merchants

Merchants are inundated by agencies and app vendors. The email has to demonstrate you looked at their store specifically.

Your product pages load the review widget after the main content, so on mobile the star rating pops in about a second late — it's the kind of thing that costs a few percent of add-to-cart without showing up anywhere obvious.

That's specific, observable, useful whether or not they reply, and it proves you opened the site. Compare with "I noticed you're using Shopify and thought I'd reach out", which is true of two million stores.

Two things that work particularly well in this segment: a concrete observation about their store, and a number attached to a result for a comparable brand. Two things that don't: generic audits offered as a hook, and anything that opens by criticising their site.

Peak-season timing matters more here than elsewhere. Emailing a merchant in the last weeks before the holiday peak gets ignored, however good the email. January and mid-year are when merchants evaluate.

Don't do these

  • Don't email every store on a platform. Size-filter first or the list is worthless.
  • Don't cite an app detection you haven't verified. Detection has real error rates.
  • Don't send to support@ and expect the owner.
  • Don't offer a free audit as the hook. Every agency does, and merchants have learned it's a sales call.
  • Don't outreach during peak season.
  • Don't scrape checkout or account-gated pages.
  • Don't lead by criticising their store. Observation, not verdict.

Building the list

Everything above is visible per store and invisible in aggregate, which means this is a research problem rather than a database query. That's why most ecommerce lists are just "all Shopify stores in a country" and perform accordingly.

ManyPI fits because the qualification criteria go into the brief rather than into a post-processing step: keywords for the platform and app footprint, exclusions for the segments you don't want, and extra_columns to research the review volume, app count, catalogue size and founder name per store, each with a source URL. required_fields: ["email"] means stores where no contact could be found aren't saved or billed. Over MCP:

claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user

Related skills

lead-sourcing, technographic-signals, lead-enrichment, personalization-at-scale, web-scraping-lead-data, lead-scoring-qualification

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.