competitor-profiling

Trigger phrases

Phrases that activate this skill when typed to Claude Code:

• competitor profile
• competitor research
• profile this competitor
• competitive intelligence
• competitor dossier

What it does

competitor-profiling is a Claude Code skill from Corey Haines’s marketing-skills repo. It turns Claude into a competitive-intelligence analyst who takes a list of competitor URLs and produces a structured dossier per competitor — positioning, ICP signals, pricing model, messaging frames, content posture, SEO authority, and gaps you can attack. The skill activates when you mention “competitor profile”, “competitive intelligence”, or “research these competitors”.

The output of a session is a per-competitor markdown profile: tagline and positioning, who they target (from copy and case studies), pricing structure, top-performing content, backlink and DR signals, messaging themes, and a “what they’re not doing” gaps section that feeds directly into your own positioning.

When to use it

Reach for it when:

• You can name your competitors but couldn’t write a one-page brief on any of them
• You’re rebuilding messaging and need to know what’s already taken
• You want a defensible competitive moat statement, not vibes

When not to reach for it:

• You don’t know who your competitors are — that’s a different exercise (customer research)
• You need real-time competitive monitoring; profiles are snapshots, not feeds

Install

The skill is distributed via Corey Haines’s marketing-skills repo. Install via the repo’s recommended path — copy the competitor-profiling SKILL.md into your project’s .claude/skills/competitor-profiling/ directory, or use the repo’s plugin install if you’ve set it up.

Once installed, the skill activates on the trigger phrases above. The first time it runs, it will check for .agents/product-marketing-context.md (or .claude/product-marketing-context.md) — populating that file with your product context first dramatically improves output quality across all of Haines’s marketing skills.

What a session looks like

A typical session has three phases:

1. Site scrape pass. WebFetch pulls homepage, pricing, customers, blog, key product pages. The skill extracts structured fields rather than scraping prose.
2. SEO + market layer. Backlink profile, top organic queries, DR, content cadence. Identifies which themes are competitive and which are uncontested.
3. Profile output. A standardized markdown profile per competitor with positioning, ICP, pricing, messaging, and a gaps section that becomes input for competitor-alternatives or your own messaging work.

The discipline that makes it work: structured fields, not paraphrase. A good profile is a database row you can compare across competitors, not a 3-page essay.

Receipts

Honest reporting on what competitor-profiling produces and where it has limits:

Where it works well:

• Profiles are scannable side-by-side because every competitor uses the same template
• The gaps section is where new positioning angles get discovered
• Catches positioning collisions before you launch a campaign on someone else’s frame

Where it backfires:

• Without paid SEO tools (Ahrefs, Semrush) the backlink/DR section relies on rough estimates
• If the competitor’s positioning is opaque or aspirational the profile inherits that opacity

Pattern that works: profile your top 3–5 competitors at once, not one at a time. The value is in the comparison — a single profile is half the picture.

Source and attribution

Originally written by Corey Haines. The canonical SKILL.md and any supporting files live in the competitor-profiling folder of his marketing-skills repository.

License: MIT. You can install, adapt, and redistribute the skill, with attribution preserved.

This page documents the skill from a practitioner’s perspective. For the formal spec and any updates, defer to the source repo.