Competitor Analysis logo

Competitor Analysis

Organization
cognyai
competitor-analysis

Research competitor positioning, ads, pricing, and market gaps

Overview

Publishercognyai
Repositoryclaude-code-marketing-skills
Skill namecompetitor-analysis
Stars
111
Forks
15
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by cognyai on GitHub. Read the source before you install it.

Installation

Install the Competitor Analysis AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/cognyai/claude-code-marketing-skills/tree/main/skills/competitor-analysis
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/cognyai/claude-code-marketing-skills.git /tmp/claude-code-marketing-skills
mkdir -p .claude/skills
cp -r /tmp/claude-code-marketing-skills/skills/competitor-analysis .claude/skills/competitor-analysis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Competitor Analysis in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Competitor Analysis on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Competitor Analysis is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Competitor Analysis

Research a competitor or market to understand positioning, pricing, strengths, and gaps.

Usage

/competitor-analysis hubspot.com — analyze a specific competitor /competitor-analysis "marketing automation tools" — analyze a market category

Works with

Runs with zero accounts (WebSearch/WebFetch). Each connected provider replaces a guess with data.

JobPrimaryAlso answers itNo account
Who the real competitors areSemrush domain_organic_competitorsAhrefs organic_competitorsWebSearch "[company] competitors"
Organic footprint and top pagesSemrush domain_overview, domain_organic_keywordsAhrefs organic_keywords, top_pagesWebSearch
Paid search: are they bidding, on whatSemrush domain_paid_keywords—Google Ads Transparency Center (adstransparency.google.com), manual
AuthorityAhrefs batch_analysis (whole set in one call)cogny-ahrefs-lite tool_domain_rating—
Share of voice in AI answerscogny-ai-visibility tool_check_ai_visibility——
Recent launches, funding, pricing changescogny-brave-search tool_brave_newstool_brave_searchWebSearch "[competitor] news" / "announces"

Semrush and Ahrefs estimate traffic differently: pick one per table, or show both in separate columns. Write "Domain Rating by Ahrefs" next to every DR number.

Steps

1. Identify the competitive set

If given a company: WebSearch for "[company] competitors" and "[company] vs" If given a category: WebSearch for "best [category] [current year]" (take the year from today's date, never a hardcoded one) and "[category] comparison"

Build a list of 4-6 key competitors.

Enhanced when connected: If Cogny isn't connected, skip this and note what connecting adds (keyword-overlap competitors from Semrush/Ahrefs). Otherwise call mcp__cogny__list_integrations once: mcp__cogny__mcp__Semrush__domain_organic_competitors (domain, database = market country code) or mcp__cogny__mcp__Ahrefs__organic_competitors (target, country) returns the domains that actually compete for the same keywords. Merge with the WebSearch list and say which competitors only show up in one of them (search competitors you didn't know about are often the finding).

2. Analyze each competitor's positioning

For each competitor, WebFetch their homepage and key pages:

  • Tagline/headline: How do they position themselves?
  • Target audience: Who are they selling to?
  • Key features: What do they emphasize?
  • Pricing: What's the price point and model?
  • Social proof: Customer logos, testimonials, case studies
  • Recent moves: WebSearch "<competitor>" news, "<competitor>" announces, "<competitor>" funding OR launch OR pricing [current year], plus their own blog/changelog/press page via WebFetch. Keep only items with a date in the last ~3 months and cite the date.
    • Enhanced: if Cogny isn't connected, skip this and note what connecting adds. Otherwise mcp__cogny__mcp__cogny-brave-search__tool_brave_news (query: "<competitor>", freshness: "pm") gives dated launch, funding and pricing news from the last month

3. Analyze their search presence

WebSearch for key terms in the market:

  • Who ranks #1-3 for the main category keywords?
  • What content strategy are they using? (blog, comparison pages, tools)
  • Are they running Google Ads on brand/competitor terms? WebSearch can't see ads. Check the Google Ads Transparency Center (https://adstransparency.google.com, search the advertiser name) for whether they run ads and sample creatives; it doesn't show keywords, so brand-term bidding stays unverified unless the user runs the search themselves or Semrush is connected.

Enhanced when connected: If Cogny isn't connected, skip this and note what connecting adds (keyword/traffic estimates, paid keywords, Domain Rating, AI-answer share of voice).

  • Organic: mcp__cogny__mcp__Semrush__domain_overview per competitor (domain, database) for keywords and traffic; domain_organic_keywords (display_limit: 50) for what they rank on. Ahrefs: organic_keywords and top_pages (target, country) show which pages earn the traffic, which tells you their content strategy.
  • Paid: mcp__cogny__mcp__Semrush__domain_paid_keywords (domain, database). Flag competitors bidding on your brand and the terms everyone bids on.
  • Authority: mcp__cogny__mcp__Ahrefs__batch_analysis (targets: all competitor domains, country); without Ahrefs, mcp__cogny__mcp__cogny-ahrefs-lite__tool_domain_rating (target) per domain.
  • AI answers: mcp__cogny__mcp__cogny-ai-visibility__tool_check_ai_visibility for 2-3 category prompts a buyer would type ("best [category] for [segment]"), with brand, domain and competitors. Each check costs credits; set engines to limit it. If prompts were checked before, tool_get_ai_visibility_history (free) shows the trend.

4. Identify market gaps

Compare across all competitors:

  • What features does everyone offer vs. unique differentiators?
  • What pricing tier is underserved?
  • What audience segment is ignored?
  • What messaging angle is nobody using?

5. Report

Competitive Analysis: [Company/Market]

Competitive Landscape:
┌─────────────┬───────────────────┬──────────────┬───────────┐
│  Competitor  │    Positioning     │   Pricing    │ Strength  │
├─────────────┼───────────────────┼──────────────┼───────────┤
│ [Company 1] │ [tagline]         │ [price]      │ [key USP] │
│ [Company 2] │ [tagline]         │ [price]      │ [key USP] │
│ [Company 3] │ [tagline]         │ [price]      │ [key USP] │
└─────────────┴───────────────────┴──────────────┴───────────┘

Search Dominance:
- [keyword 1]: [who ranks #1]
- [keyword 2]: [who ranks #1]
- [keyword 3]: [who ranks #1]

Data (if connected; name the source on every number):
[If nothing is connected: "Data: not connected. Semrush/Ahrefs add traffic, paid-keyword and authority numbers; cogny-ai-visibility adds AI-answer share of voice." and omit the table.]
| Competitor | Organic keywords / traffic (Semrush or Ahrefs) | Paid keywords (Semrush) | DR (Domain Rating by Ahrefs) | AI mention rate (cogny-ai-visibility) |

Market Gaps:
1. [Gap description + opportunity]
2. [Gap description + opportunity]
3. [Gap description + opportunity]

Positioning Recommendation:
[Specific positioning advice based on gaps found]

Frequently asked questions

What does the Competitor Analysis AI skill do?

Research competitor positioning, ads, pricing, and market gaps

Why use Competitor Analysis on TypingMind?

Because you install it once and use it with any model. Competitor Analysis is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Competitor Analysis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cognyai/claude-code-marketing-skills/tree/main/skills/competitor-analysis. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Competitor Analysis?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Competitor Analysis?

As many as you like. As long as a model supports skills, you can use Competitor Analysis with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Competitor Analysis AI skill free?

It is published on GitHub by cognyai. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇