skills.rest
TheGraphicKing
TheGraphicKingCOMMUNITY
Explore all skills by this author →
GitHub

competitor-scraper

Extract structured artifacts from competitor blogs, LinkedIn, pricing, careers, G2, and press pages.

Updated May 23, 2026
Search Tags:#competitive intelligence#web scraping#deduplication#competitor analysis#pricing monitoring#press monitoring#g2 reviews
One-click install
npx skills add https://github.com/TheGraphicKing/skott-canvas --skill competitor-scraper-thegraphicking
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: competitor-scraper
Source: https://github.com/TheGraphicKing/skott-canvas/tree/main/skills/competitor-scraper
Command: npx skills add https://github.com/TheGraphicKing/skott-canvas --skill competitor-scraper-thegraphicking

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually monitoring competitor activity across blogs, LinkedIn, pricing pages, careers listings, G2 reviews, and press coverage is slow and inconsistent. This Skill automates the collection of public competitor data and returns structured, deduplicated artifacts with full provenance metadata for downstream analysis. ## Core Features & Use Cases - Six Source-Type Extractors: Parses blog posts, LinkedIn posts, pricing pages, careers listings, G2 reviews, and press mentions with purpose-built field schemas for each source. - Fingerprint-Based Deduplication: Computes SHA-256 fingerprints per artifact and discards duplicates against the artifact store so only net-new signals are emitted. - Provenance Metadata: Every artifact carries competitor_id, run_id, fingerprint, and scraped_at timestamps so downstream classifiers and gap-analysis agents can trace each signal to its origin. - Use Case: A competitive intelligence scheduler dispatches a weekly scan job for a competitor; the Skill fetches all six sources, extracts structured fields, deduplicates against prior runs, and returns only new artifacts plus error reports for failed sources. ## Quick Start Run the competitor-scraper with a job payload containing the competitor ID, source URL list, run ID, and last-scan timestamp to collect fresh competitor artifacts.

Frequently Asked Questions about competitor-scraper

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

FAQPage Schema
How do I scrape competitor websites for competitive intelligence?▼

Provide a job payload with the competitor ID, source URL list, run ID, and last-scan timestamp. The Skill fetches blog, LinkedIn, pricing, careers, G2, and press sources, extracts structured fields per source type, and returns deduplicated artifacts.

What data can be extracted from competitor pricing pages?▼

Pricing page extraction captures the pricing model, tier names and descriptions, feature gates, deployment options, CTA language, minimum contract signals, and a diff flag indicating whether the page changed since the last scrape.

How does deduplication work when scraping competitor content?▼

Each artifact gets a SHA-256 fingerprint computed from source type, source URL, publication date, and title. The fingerprint is checked against the artifact store, and known duplicates are discarded and counted rather than emitted.

Can G2 review scraping extract reviewer names?▼

No, reviewer names are intentionally excluded. The Skill extracts star rating, review date, reviewer title, company size, pros and cons text, praised and criticized features, and a high-signal flag for enterprise-relevant mentions.

What happens when a competitor source URL returns an error?▼

Failed sources are reported in the source_errors array with their HTTP status codes. Distinct codes like 429 rate-limit and 404 not-found are preserved so the scheduler can apply the correct retry or escalation handling.

What are the limitations of automated competitor web scraping?▼

Extraction is limited to publicly visible content; fields that cannot be read directly from the page are returned as null rather than estimated. LinkedIn engagement signals are only captured when visible without authentication.

Related Skills

Explore More Marketing & Sales Skills→
theworkflowcotheworkflowco

research-competitive

Analyze competitors and market signals to produce competitive intelligence.

Official
Advanced
dexhunterdexhunter

agent-relay-digest

Generate curated digests from agent conversations with theme clustering and signal ranking.

Community
Advanced
yohayetsionyohayetsion
4

competitive-intelligence

Analyze competitive landscapes, competitor profiles, and win/loss reports.

Community
Advanced
tanaertanaer

web-scraper-pro-zhuyu28

Automate web scraping for JavaScript-rendered pages with anti-bot evasion.

Community
Advanced