Skip to content
SkillModel-led3,871 tokens in use

competitor-profiling

Researches competitors into dated profiles of positioning, pricing, features, reviews and SEO, with observed facts kept apart from inference.

61,709 stars on the repository MIT Licensecoreyhaines31/marketingskills · skills/competitor-profiling
npx skills add coreyhaines31/marketingskills --skill competitor-profiling
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing competitor-profiling costs

94tokens idle
3,871tokens in use
8,118tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure25/25
  • Examples15/15
  • Output10/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community76
  • Maturity32
  • Momentum40

competitor-profiling turns competitor research into a repeatable, dated profile. It selects a data stack, saves raw scrapes, SEO data and reviews to disk, then writes a profile from a fixed template and a cross-competitor summary.

Every claim is tagged as observed, inferred or implication, and a feature not seen on the pages checked is written as not observed, never as absent.

What You Get

  • A dated profile per competitor from one template
  • Raw data saved by competitor and date: scrapes, SEO JSON and reviews
  • Sections on positioning, product, pricing, customers, SEO and strengths and weaknesses
  • Competitive implications written as questions or options
  • A cross-competitor summary file

Common Use Cases

  • Profiling three rivals before a pricing change
  • Checking what a competitor charges and claims today
  • Updating an old profile and noting what changed
  • Testing whether a conclusion about a rival is fair

What Makes It Unique

It separates observed, inferred and implied claims, forbids stating a rival’s motive, and treats fetched competitor pages as data to analyze, ignoring any instructions hidden in them. Metrics with no data source are marked unavailable.

Under The Hood

The SKILL.md and two references (a template file and a tool reference) are loaded as context. It tells the agent to scrape competitor pages with Firecrawl or WebFetch, pull SEO data through DataForSEO or another connected MCP, and write files under a competitor-profiles folder in your project. It ships no scripts; the tools need your own accounts.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers