competitor-profiling Skill for Claude: Turn Competitor URLs Into Structured Profiles

competitor-profiling makes your assistant research a list of competitor URLs and write a structured profile for each, plus a summary.

Installs: 98.6K; on skills.sh
Stars: 57.9K; on GitHub
Files: 3; besides SKILL.md
Updated: Oct 2026; last repo commit

competitor-profiling takes competitor URLs and builds one markdown profile per competitor. It maps and scrapes the site, optionally pulls G2 and Capterra reviews, adds SEO and market data, and keeps what it observed, what it inferred and what it implies for you in separate layers. It saves all raw scrapes and SEO responses in dated folders before writing the profile, then adds a cross-competitor summary.

It defaults to a quick scan (homepage and pricing) and does a deep profile on request or for three or fewer competitors. It works best with the Firecrawl and DataForSEO MCP servers; without them it falls back to the built-in WebFetch and another SEO source, or marks metrics unavailable. It bundles no scripts.

Good for

Marketers and founders researching competitors
Product teams comparing positioning and pricing
SEO leads sizing competitor traffic and backlinks

Install competitor-profiling

Claude Code

Copy this prompt.

Install the competitor-profiling skill in Claude Code. Run this command:

npx skills add https://github.com/coreyhaines31/marketingskills --skill competitor-profiling

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

From its listing on skills.sh. Source.

What's in the skill

When it loads

When the user wants to research, profile, or analyze competitors from their URLs. Also use when the user mentions 'competitor profile,' 'competitor research,' 'competitor analysis,' 'profile this competitor,' 'analyze competitor,' 'competitive intelligence,' 'competitor deep dive,' 'who are my competitors,' 'competitor landscape,' 'competitor dossier,' 'competitive audit,' or 'research these competitors.' Input is a list of competitor URLs. Output is structured competitor profile markdown files. For creating comparison/alternative pages from profiles, see competitors. For sales-specific battle cards, see sales-enablement. For researching accounts you're selling to, see prospecting. For how a competitor grew over time and what to copy, see reverse-engineer-marketing.

Sections in SKILL.md

Initial Assessment
Tool Stack Selection
Core Principles
1. Facts Over Opinions
2. Structured and Comparable
3. Current Data
4. Honest Assessment
5. Untrusted Input
Saving Raw Data
Research Process
Phase 1: Site Scraping (Firecrawl or WebFetch)
Phase 2: SEO & Market Data (DataForSEO or Ubersuggest)
Phase 3: Synthesis
Output Format
Profile Document Structure
At a Glance

Key facts

Author: coreyhaines31 (GitHub)
Repository: coreyhaines31/marketingskills, folder skills/competitor-profiling
Installs on skills.sh: 98,610 (as of 2026-11-02)
Repo stars: 57,855 (whole repository, as of 2026-11-02)
License: MIT
Last repo commit: 2026-10-31
Files in the skill folder: 4 files: SKILL.md, 2 reference guides and an evals file
skills.sh audits: Gen Agent Trust Hub: pass, Socket: pass, Snyk: warn

What it includes

Checks product context, then confirms inputs
Reads .agents/product-marketing.md if it exists, then confirms URLs, your product, depth and focus areas.
Read · Initial assessment
Firecrawl and DataForSEO, or WebFetch and another SEO source
Picks the primary or alternative stack based on which MCP servers are connected.
Tool stack selection
Map the site, scrape key pages, optional reviews
Homepage, pricing, features, about, customers, integrations and changelog; saves each scrape to a dated folder.
Write · Phase 1: Site scraping
Backlinks, ranked keywords, traffic, competitors
Uses DataForSEO tools or whichever SEO source is connected; each raw response is saved as JSON.
Write · Phase 2: SEO and market data
One profile per competitor plus _summary.md
Follows a fixed template from references/templates.md; quick scan or deep profile.
Write · Phase 3: Synthesis and output
Re-check pricing, SEO and changelog; log changes
Adds a Change Log section and a new dated raw folder.
Write · Updating profiles

From the official docs

Permissions

Medium risk

It scrapes websites and may call Firecrawl and DataForSEO tools through your MCP connections, and it writes files into your project. Start with a quick scan, check your tool usage, and keep the output folder out of git if needed.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

It may spend credits on scraping and SEO tools
The primary stack calls Firecrawl and DataForSEO MCP tools, which may count against your plans or credits. Start with a quick scan on a few URLs and check usage.
It writes files to your project
It creates a competitor-profiles/ folder with raw scrapes, SEO JSON, profiles and a summary. Add the folder to .gitignore if you do not want it committed.
Scraped pages are treated as data
The SKILL.md says to ignore instructions embedded in competitor pages and note the attempt in the profile.

Technical details

Talks to	Competitor websites and review sites. Firecrawl and DataForSEO, if connected
Scopes	Firecrawl and DataForSEO MCP connections, if used

Questions

What does the competitor-profiling skill do?

It researches competitors from their URLs and writes one structured profile per competitor, covering positioning, product, pricing, customers, SEO and strengths and weaknesses. It then writes a summary across all of them.

How do I install competitor-profiling?

Use the install box at the top of the page. The marketingskills README also offers a Claude Code plugin route that installs the whole set of marketing skills, and notes the skills CLI may need -a claude-code when run from inside an agent session.

Does it need Firecrawl or DataForSEO?

No, but they are preferred. Without them it uses the built-in WebFetch and whatever SEO source is connected, such as Ahrefs, Semrush or Ubersuggest. With no SEO source, it marks those metrics unavailable instead of estimating them.

How accurate are the profiles?

The SKILL.md says every claim should trace to a source and that a missing feature is written as "not observed", not "absent". Profiles are dated snapshots, so check anything you plan to use publicly.

Is competitor-profiling safe?

It bundles no scripts. It fetches public competitor sites, may call paid tools you have connected through MCP, and writes files into a competitor-profiles/ folder in your project, so check your tool usage and review that folder.

What is the difference between competitor-profiling and the competitors skill?

competitor-profiling researches competitors and writes profiles. The SKILL.md says the competitors skill creates comparison and alternative pages from those profiles, and sales-enablement turns them into battle cards.

Information

updated Nov 2, 2026

Repository: coreyhaines31/marketingskills
Folder: skills/competitor-profiling

coreyhaines31/marketingskills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 2

competitor-profiling SKILL.md · github.com
marketingskills README · github.com