competitor-profiling

Generates structured competitor profile markdown files from URLs using site scraping and SEO data.

Updated Aug 6, 2026
One-click install
npx skills add https://github.com/ferrarifankid04/ai-skills-public --skill competitor-profiling-ferrarifankid04
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: competitor-profiling
Source: https://github.com/ferrarifankid04/ai-skills-public/tree/main/claude-code/skills/competitor-profiling
Command: npx skills add https://github.com/ferrarifankid04/ai-skills-public --skill competitor-profiling-ferrarifankid04

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Researching competitors manually means visiting dozens of pages, pulling SEO metrics, and reading reviews, then assembling it all into a comparable format. This Skill automates that research pipeline, turning a list of competitor URLs into consistent, evidence-backed competitor profile documents. ## Core Features & Use Cases - Three-Phase Research Pipeline: Scrapes key competitor pages with Firecrawl (homepage, pricing, features, customers, integrations, changelog), pulls SEO and backlink intelligence via DataForSEO, then synthesizes everything into a standardized profile template. - Quick Scan vs. Deep Profile Modes: Defaults to a fast homepage-plus-pricing scan for large competitor lists, with a full deep-dive mode including review mining (G2, Capterra) and backlink analysis for three or fewer competitors. - Auditable Raw Data Storage: Saves every scrape, SEO response, and review source to dated folders under competitor-profiles/raw/ so snapshots can be diffed over time without re-running expensive API calls. - Use Case: A product marketer needs to prepare for a launch against five rivals. They provide the five URLs and receive five comparable profile files plus a _summary.md with a side-by-side comparison table, positioning map, and identified market gaps. ## Quick Start Profile these competitors and build a comparison summary: https://competitor-a.com, https://competitor-b.com, https://competitor-c.com.

Frequently Asked Questions about competitor-profiling

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

FAQPage Schema
How do I profile competitors from their website URLs?

Provide the list of competitor URLs and the skill maps each site with Firecrawl, scrapes key pages like homepage, pricing, and features, pulls SEO metrics from DataForSEO, and synthesizes one structured markdown profile per competitor plus a cross-competitor summary.

What pages should I scrape for competitor analysis?

Prioritize the homepage, pricing page, features pages, about page, customers or case studies page, integrations page, and changelog. Optionally scrape review sources like G2, Capterra, Product Hunt, and TrustRadius for sentiment and ratings.

What is the difference between quick scan and deep profile?

Quick scan covers only the homepage, pricing page, domain rank overview, and ranked keywords summary, producing an abbreviated profile. Deep profile adds all site pages, review mining, full backlink analysis, and technology stack detection. Quick scan is the default unless three or fewer competitors are requested.

Can I skip the SEO data collection in competitor profiling?

Yes, you can scope the research to exclude DataForSEO calls and only collect positioning, pricing, and customer data via scraping. The resulting profile flags the SEO section as not collected rather than leaving placeholders, and raw scrapes are still saved to disk.

How do I update an existing competitor profile?

Update rather than start fresh: re-scrape the pricing page first, re-pull SEO metrics, and scan the changelog for product changes. Save new raw data to a new date folder without overwriting prior snapshots, and append a Change Log section noting what changed.

What happens if DataForSEO returns no data for a competitor domain?

The domain may be too new or too small for SEO metrics. The profile notes insufficient data for those fields instead of failing, and the scraping-based sections like positioning, pricing, and features are still completed normally.