agentsclimarketplace

Find shopify store leads

Skill applora/agent-skills/skills/find-shopify-store-leads

Agent plugins/extensions for Shopify App Store intelligence.

Install
npx -y skills add applora/agent-skills --skill find-shopify-store-leads

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Finds and prioritizes relevant Shopify stores using public app-review relationships, competitor dissatisfaction, geography, and app-stack signals from Applora MCP. Use for account research, competitor-user discovery, integration prospecting, partner targeting, or preparing respectful personalized outreach.

SKILL.md

2.7 KB, as published. Nobody here has run it

Find Shopify Store Leads

Turn public Shopify App Store review signals into a small, relevant research list. This skill identifies evidence for targeting; it does not send messages.

Required connection

Use the Applora MCP server at https://applora.ai/mcp:

  • get_app_reviews({ handle, rating?, usageDuration?, hasContent?, cursor?, limit? })
  • search_stores({ search?, country?, cursor?, limit? })
  • get_store({ id, appHandle?, maxRating?, limit? })
  • search_apps({ query?, categoryHandles?, pricing?, builtForShopify?, minRating?, maxRating?, sort?, cursor?, limit? })
  • get_app({ handle, includeCategoryRanks?, limit? })

Store relationships come from public reviews. They indicate that a store reviewed an app at some point, not a confirmed current installation.

Workflow

  1. Define the ideal customer profile, geography, relevant competitor or complementary app, and the problem your offer solves.
  2. Resolve exact competitor handles.
  3. Pull recent reviews with merchant IDs:
    • 1–3 star for dissatisfaction-led targeting;
    • 4–5 star for complementary integration or partnership targeting.
  4. Fetch store profiles only for candidates matching the research thesis. Filter by app and maximum rating where useful.
  5. Look for:
    • an explicit complaint your product solves;
    • relevant app-stack or category signals;
    • geography fit;
    • review recency and specificity;
    • multiple signals rather than one vague review.
  6. Score fit, timing, evidence quality, and personalization potential.
  7. Produce a bounded shortlist with the public evidence and a respectful outreach angle.

Privacy and outreach guardrails

  • Do not expose or use email, phone, or address fields returned by any source.
  • Do not claim a current install, contract, budget, or buying intent.
  • Do not automate outreach, scraping, or enrichment without separate user authorization and applicable consent.
  • Avoid sensitive inference, spam tactics, and manipulative personalization.
  • Cite public review evidence accurately and avoid quoting personal details.

Output

Return:

  1. targeting thesis and filters;
  2. prioritized shortlist with store name, country, evidence, and confidence;
  3. why each store is relevant now;
  4. a one-sentence, non-creepy personalization angle;
  5. limitations and suggested manual verification.

Prefer 10 strong candidates over hundreds of weak leads.

Gives 0 of the 12 instructions most sales crm skills give

Counted across 361 of the 361 authors here whose files we hold, read 2026-08-06

  • Read product marketing context before writing if it existsin 22 of 361, across 14 files
  • keep the ask low-frictionin 16 of 361, across 7 files
  • Call RUBE_SEARCH_TOOLS firstin 15 of 361, across 5 files
  • personalize every outbound messagein 13 of 361, across 4 files
  • confirm connection status is activein 13 of 361, across 4 files
  • Keep forwardable blurbs under 100 wordsin 13 of 361, across 4 files
  • State if personalization context is missingin 13 of 361, across 4 files
  • Cut any sentence that does not drive a replyin 13 of 361, across 4 files
  • Use proof instead of adjectivesin 12 of 361, across 3 files
  • Use a single, low-friction call to actionin 12 of 361, across 4 files
  • Calibrate tone to the specific audiencein 12 of 361, across 3 files
  • Make each follow-up email add new valuein 12 of 361, across 6 files

Said here and by no other author read

  • use the Applora MCP server
  • define the ideal customer profile and research thesis
  • resolve exact competitor handles
  • pull recent reviews with merchant IDs
  • fetch store profiles for matching candidates
  • look for explicit complaints your product solves

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.