Competitive Analyzer logo

Competitive Analyzer

Community
Mathews-Tom
competitive-analyzer

Competitive landscape analysis: Porter's Five Forces, competitor discovery, feature/pricing matrices, positioning maps, moat assessment via WebSearch. Triggers on: "competitive analysis", "competitor comparison", "competitive landscape", "Porter's Five Forces", "market positioning", "moat assessment", "defensibility analysis".

Overview

PublisherMathews-Tom
Repositoryarmory
Skill namecompetitive-analyzer
Stars
318
Forks
47
Bundled files
4
LicenseMIT
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.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Mathews-Tom on GitHub. Read the source before you install it.

Installation

Install the Competitive Analyzer 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.
  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/Mathews-Tom/armory.git /tmp/armory
mkdir -p .claude/skills
cp -r /tmp/armory/skills/competitive-analyzer .claude/skills/competitive-analyzer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Competitive Analyzer 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 Competitive Analyzer 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 Competitive Analyzer 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.

Competitive Analyzer

Systematic competitive landscape analysis: discovery, force analysis, feature comparison, pricing, positioning, and defensibility assessment.

When to use this skill vs. others

NeedSkill
Analyze competitors, compare features, assess moatscompetitive-analyzer (this skill)
Market sizing, TAM/SAM/SOM, demand signalsmarket-analyzer
General web research and data gatheringtavily / web-fetch

Workflow

Phase 1: Competitor Discovery

Identify competitors across three tiers using WebSearch.

Tier classification:

  • Direct competitors — Same solution to the same customer segment. Search: "[product category] alternatives", "[product] vs", "best [category] tools 2024"
  • Indirect competitors — Different solution to the same underlying problem. Search: "how to [solve problem] without [category]", adjacent category leaders
  • Potential competitors — Adjacent players with capability and incentive to enter. Search: recent funding rounds, platform expansion announcements, acqui-hires

Discovery sources:

  • Product Hunt: site:producthunt.com [category]
  • G2: site:g2.com [category] reviews
  • Capterra: site:capterra.com [category]
  • Crunchbase: site:crunchbase.com [category] funding
  • Industry reports and analyst coverage

Output: A competitor roster table:

CompetitorTierFoundedFundingHQEst. RevenueTarget Segment

Include 5-15 competitors. Fewer than 5 suggests the search was too narrow; more than 15 suggests the scope needs tightening.

Phase 2: Porter's Five Forces Assessment

Score each force 1-5 with supporting evidence. Reference references/porters-five-forces.md for scoring rubric and sub-criteria.

1. Threat of New Entrants (1-5)

  • Capital requirements and startup costs
  • Regulatory and compliance barriers
  • Technology and IP barriers
  • Brand loyalty and switching costs of incumbents
  • Access to distribution channels
  • Economies of scale advantages

2. Supplier Power (1-5)

  • Number of available suppliers
  • Uniqueness of supplier inputs
  • Switching costs between suppliers
  • Forward integration threat
  • Dependence on key vendors (cloud, APIs, data)

3. Buyer Power (1-5)

  • Buyer concentration relative to sellers
  • Price sensitivity and transparency
  • Switching costs for buyers
  • Backward integration threat
  • Availability of substitute information

4. Threat of Substitutes (1-5)

  • Availability of alternative solutions
  • Performance-to-price ratio of substitutes
  • Buyer propensity to switch
  • Switching costs to substitutes

5. Competitive Rivalry (1-5)

  • Number and size distribution of competitors
  • Industry growth rate
  • Product differentiation level
  • Exit barriers
  • Fixed cost structure and capacity

Synthesis: Calculate overall industry attractiveness (weighted average of forces). Higher scores mean more competitive pressure, lower attractiveness.

Phase 3: Feature & Pricing Matrix

Build a comprehensive comparison. Reference references/competitive-matrix.md for structuring methodology.

Feature comparison table:

Feature CategoryFeatureCompetitor ACompetitor BCompetitor COur Product
CoreFeature 1FullPartialNoneFull
IntegrationAPIRESTGraphQLNoneREST+GraphQL
SupportSLA99.9%99.5%None99.95%

Use: Full / Partial / None / Superior (exceeds category standard)

Feature analysis:

  • Table stakes — Features every competitor offers. Missing any = disqualifier.
  • Differentiators — Features only 1-2 competitors offer. Potential positioning angles.
  • Gaps — Features no competitor offers. Potential innovation opportunities.
  • Over-served — Features with extensive investment but low customer value signal.

Pricing comparison table:

CompetitorModelFree TierEntry PriceMid TierEnterpriseBilling
ASubscriptionYes$29/mo$99/moCustomMonthly/Annual
BUsage-basedTrial$0.01/unitVolume discountCustomMonthly

Pricing analysis:

  • Price-to-feature ratio positioning (value vs. premium)
  • Pricing model trends in the category
  • Customer segment alignment by price point

Phase 4: Positioning Map

Reference references/positioning-analysis.md for dimension selection and mapping methodology.

Step 1: Dimension selection Select the two dimensions most important to target customers. Common pairs:

  • Price vs. Feature richness
  • Ease of use vs. Power/flexibility
  • SMB-focused vs. Enterprise-focused
  • Vertical-specific vs. Horizontal/general

Validate dimension selection against customer research or publicly available review themes.

Step 2: Plot competitors Position each competitor on the 2D map using evidence from Phase 3.

High [Dimension Y]
    |
    |   [Comp A]        [Comp C]
    |
    |        [Comp B]
    |                    [Our Product]
    |
    |   [Comp D]
    |
Low  ────────────────────────────── High [Dimension X]

Step 3: White space identification

  • Quadrants with no or few competitors = potential positioning opportunities
  • Assess whether white space is genuinely underserved or intentionally avoided (no demand)
  • Evaluate feasibility of occupying the white space

Phase 5: Moat & Defensibility Assessment

Evaluate each moat type. Reference references/positioning-analysis.md for the moat taxonomy.

Moat TypePresent?StrengthEvidence
Network effectsYes/NoWeak/Moderate/StrongDescription
Switching costsYes/NoWeak/Moderate/StrongDescription
IP / TechnologyYes/NoWeak/Moderate/StrongDescription
BrandYes/NoWeak/Moderate/StrongDescription
Data advantageYes/NoWeak/Moderate/StrongDescription
Cost advantageYes/NoWeak/Moderate/StrongDescription
RegulatoryYes/NoWeak/Moderate/StrongDescription

Overall moat rating:

  • Weak — No meaningful barriers. Competitors can replicate within 6 months.
  • Moderate — 1-2 barriers provide temporary advantage. Replication takes 1-2 years.
  • Strong — Multiple reinforcing barriers. Replication takes 2-5 years.
  • Very Strong — Compounding barriers with flywheel effects. Extremely difficult to replicate.

Phase 6: Report Generation

Produce the final competitive analysis report with these sections:

  1. Executive Summary — Competitive landscape threat level (Low / Moderate / High / Critical), top 3 competitive risks, top 3 competitive advantages
  2. Competitor Roster — Discovery table from Phase 1
  3. Porter's Five Forces Scorecard — Force-by-force scoring with evidence from Phase 2
  4. Feature Comparison Matrix — Full feature table with gap analysis from Phase 3
  5. Pricing Analysis — Pricing table and positioning from Phase 3
  6. Positioning Map — 2D map with white space analysis from Phase 4
  7. Moat Assessment — Defensibility table and rating from Phase 5
  8. Strategic Recommendations
    • Immediate actions (0-3 months): address critical gaps or threats
    • Medium-term plays (3-12 months): build differentiators and strengthen moats
    • Long-term positioning (1-3 years): sustainable competitive advantage strategy
  9. Risks & Mitigation — Top competitive risks with specific mitigation strategies

Quality Checks

Before delivering the report, verify:

  • Competitor roster covers all three tiers (direct, indirect, potential)
  • Every Five Forces score has supporting evidence, not just a number
  • Feature matrix uses consistent scoring across competitors
  • Pricing data is sourced and dated (pricing changes frequently)
  • Positioning map dimensions are customer-relevant, not internal metrics
  • Moat assessment distinguishes between current moats and aspirational moats
  • Strategic recommendations are specific and actionable, not generic advice
  • All claims about competitors are sourced via WebSearch, not assumed

Edge Cases

SituationAdaptation
Pre-launch product with no direct competitorsFocus on indirect competitors and substitutes. Emphasize the "potential entrants" tier. The absence of direct competitors is itself a signal worth analyzing (nascent market vs. no market).
Highly fragmented market (50+ competitors)Segment competitors into strategic groups. Analyze 2-3 representative competitors per group rather than every player.
Monopoly or duopoly marketFive Forces analysis becomes more important. Focus on substitute threats and potential entrants. Analyze the dominant player's moats in detail.
B2B enterprise with opaque pricingNote pricing opacity as a finding. Use job postings, case studies, and review sites for indirect pricing signals.
User provides a competitor listSkip discovery in Phase 1. Validate the list for completeness (are there missing tiers?) and proceed to Phase 2.
Rapidly changing marketDate-stamp all findings. Flag data older than 6 months as potentially stale. Emphasize monitoring recommendations.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Competitive Analyzer AI skill do?

Competitive landscape analysis: Porter's Five Forces, competitor discovery, feature/pricing matrices, positioning maps, moat assessment via WebSearch. Triggers on: "competitive analysis", "competitor comparison", "competitive landscape", "Porter's Five Forces", "market positioning", "moat assessment", "defensibility analysis".

Why use Competitive Analyzer on TypingMind?

Because you install it once and use it with any model. Competitive Analyzer 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 Competitive Analyzer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Mathews-Tom/armory/tree/main/skills/competitive-analyzer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Competitive Analyzer?

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 Competitive Analyzer?

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

Is the Competitive Analyzer AI skill free?

Yes. It is published on GitHub by Mathews-Tom under the MIT license. 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 👇