create-store-scraper

Generate grocery store flyer scraper skills and drift-detection files from browser reconnaissance.

1|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/Joresti/grocery-hack --skill create-store-scraper
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-store-scraper
Source: https://github.com/Joresti/grocery-hack/tree/main/.claude/skills/create-store-scraper
Command: npx skills add https://github.com/Joresti/grocery-hack --skill create-store-scraper

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It removes the guesswork and manual engineering required to add a new grocery store flyer source by generating a consistent scraper skill and drift-detection guardrails from browser reconnaissance.

Core Features & Use Cases

  • Scraper skill generation: Produces a full store flyer scraping workflow covering DOM-based extraction, Flipp API fetching, and Vision OCR for image-based flyers.
  • Strategy-specific drift detection: Outputs drift-detection metadata aligned to the detected scraping approach (selectors, pagination, page health checks, and image inventory signals).
  • Fit-for-purpose recon + testing: Detects blockers, view modes, pagination patterns, and product-card selectors, then structures the resulting implementation to match existing conventions across store skills.
  • Use Case: Add a store like Metro or RCSS to the weekly deal pipeline by running one command against the store’s flyer URL and receiving ready-to-use skill scaffolding.

Quick Start

Run this skill with the store name and flyer page URL, for example: "Create store scraper for Metro https://www.metro.ca/en/flyer".

Frequently Asked Questions about create-store-scraper

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate web scraping for grocery store flyers?

Automating web scraping for grocery store flyers is done by running this skill with a store name and flyer URL to generate a production-ready scraper. It performs interactive browser reconnaissance to select the best extraction strategy, covering DOM-based, Flipp API, and Vision OCR extraction.

When should I use Vision OCR instead of DOM selectors for web scraping?

Use Vision OCR for web scraping when flyer pages render products as images rather than accessible HTML. This skill automatically detects when DOM selectors fail or Flipp API fetching is unsupported, applying OCR to extract deal data from image-based grocery flyers.

What is drift detection in web scraping and how is it generated?

Drift detection in web scraping is a guardrail mechanism that monitors for structural changes like broken selectors or missing pagination. This skill generates strategy-specific drift-detection metadata alongside the scraper to validate page health and image inventory signals.

Does this flyer scraper generation require a headed Chrome browser with CDP debugging?

Yes, generating flyer scrapers requires a headed Chrome browser with CDP debugging enabled. The skill relies on interactive browser reconnaissance and a backend CDP helper script to analyze view modes, pagination patterns, and product-card selectors.

How do I add a new grocery store source to a weekly meal planning deal pipeline?

Add a new grocery store source to a weekly deal pipeline by executing one command with the store name and flyer page URL. The skill outputs convention-compliant scraper files and drift-detection scaffolding ready for immediate pipeline integration.

What are the limitations of using automated browser reconnaissance for scraper generation?

Limitations of automated browser reconnaissance for scraper generation include dependency on a headed Chrome environment and potential failure on highly obfuscated sites. The process requires a backend CDP helper script and may not bypass complex anti-bot view modes.