competitor-matrix — Claude Code skill: competitor research
The competitor-matrix Claude Code skill researches competitors and builds a sourced comparison matrix. It runs when a founder asks who else is in their market or how to position a product against them.
MIT ★ 900 updated 2026-11-03
npx skills add emotixco/claude-skills-founder --skill competitor-matrix -a claude-codeWhat competitor-matrix does
The skill searches the web for 5 to 8 direct and indirect competitors, then compares their pricing, customer segments, and features. It links sources for each competitor and marks matrix entries Yes, No, Partial, or Unknown. It also ranks threats and identifies gaps in the market.
The output includes positioning advice and a feature to build first, saved to founder/competitor-matrix.md. Before researching, the skill reads founder/facts.md, founder/product-brief.md, and ${CLAUDE_PLUGIN_ROOT}/shared/conventions.md. The analysis needs a product or market and its target customer. Prices or funding details that cannot be found are marked “Not found”.
What it helps with
- compare features across direct and indirect competitors
- spot market gaps competitors have not filled
- rank the strongest competitors by threat
- choose a product niche and an initial feature
Example prompts for the agent
- Research competitors for our product and find a positioning niche. Our target customers are small teams.
- Analyze [market name], compare competitor pricing and features, and rank the threats. The target customer is [customer description].
How to install competitor-matrix
1Skills CLI (Vercel)
npx skills add emotixco/claude-skills-founder --skill competitor-matrix -a claude-code2Manually: put the files in place
~/.claude/skills/competitor-matrix/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/competitor-matrix/
1Skills CLI (Vercel)
npx skills add emotixco/claude-skills-founder --skill competitor-matrix -a codex2Manually: put the files in place
.agents/skills/competitor-matrix/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add emotixco/claude-skills-founder --skill competitor-matrix -a cursor2Manually: put the files in place
.cursor/skills/competitor-matrix/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install emotixco/claude-skills-founder skills/competitor-matrix2Manually: put the files in place
.github/skills/competitor-matrix/SKILL.md1Skills CLI (Vercel)
npx skills add emotixco/claude-skills-founder --skill competitor-matrix -a gemini-cli2Platform CLI
gemini skills install https://github.com/emotixco/claude-skills-founder --path skills/competitor-matrixManually: put the files in place
.devin/skills/competitor-matrix/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add emotixco/claude-skills-founder --skill competitor-matrix -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about competitor-matrix
How do I install competitor-matrix in Claude Code?
Run npx skills add emotixco/claude-skills-founder --skill competitor-matrix -a claude-code. The skill file is at ~/.claude/skills/competitor-matrix/SKILL.md.
What does competitor-matrix do?
It researches 5 to 8 competitors, creates a source-linked feature matrix, ranks threats, and suggests a positioning niche. The result is saved to founder/competitor-matrix.md.
What does competitor-matrix need to work?
Provide a product or market and its target customer. The skill reads founder/facts.md, founder/product-brief.md, and ${CLAUDE_PLUGIN_ROOT}/shared/conventions.md, then searches the web.
Source text
SKILL.md · MIT
---
name: competitor-matrix
description: Research 5-8 real competitors and build a sourced feature comparison matrix, positioning gaps, threat ranking, and a niche to own. Use when a founder asks who else is in their market or how to position against competitors.
argument-hint: "[your product or market to analyze]"
allowed-tools: Read Edit(founder/**) WebSearch WebFetch
---
You are a competitive intelligence analyst for early-stage startups. You work from sources, not memory.
Input: $ARGUMENTS
## Before you start
Read `${CLAUDE_PLUGIN_ROOT}/shared/conventions.md` and follow it.
- Reads: `founder/facts.md`, `founder/product-brief.md`
- Needs: the product or market, and the target customer
- Saves to: `founder/competitor-matrix.md`
## Instructions
Search the web before you write anything. Then build the matrix:
### 1. Market landscape
Identify 5-8 direct and indirect competitors. For each:
- **Name and URL**
- **Founded and funding stage** (bootstrapped, seed, Series A, and so on), with a source link
- **Pricing model** with actual prices from their pricing page, and the date you checked it
- **Target segment** (enterprise, SMB, prosumer, consumer)
- **Key differentiator** (one sentence: what they'd say on their homepage)
### 2. Feature comparison matrix
A markdown table comparing all competitors across 8-12 features that matter in this market.
- Use Yes / No / Partial / Unknown. "Unknown" is better than a guess.
- Add a column for the founder's product, marked "Planned" or "Building"
### 3. Positioning gaps
2-3 gaps no competitor fully covers. For each:
- What's missing
- Why it matters to users
- How hard it is to build (low, medium, high)
- How long a head start filling it first would give, as an estimate with reasoning
### 4. Threat assessment
Rank the top 3 competitors by threat level (high, medium, low) based on:
- Resource advantage (funding, team size)
- Feature overlap with the founder's product
- Speed of iteration (check their changelog or release history)
### 5. Strategic recommendations
- **Position to own:** one specific niche to win before expanding
- **Feature to ship first:** the single feature that creates the most differentiation
- **Competitor to watch:** who is most likely to enter this exact niche next
## Rules
- Be specific: "raised a $5M Series A in January 2025 (link)" beats "has funding".
- Every price and funding figure has a link. If you can't find it, write "Not found".
- Format the feature matrix as a proper markdown table.
- Keep total output under 2000 words.
© emotixco · MIT · emotixco/claude-skills-founder