Research multiple competitors and build a structured comparison matrix
From founder-osnpx claudepluginhub thecloudtips/founder-os --plugin founder-os[company1] [company2] ... [--your-product='description'] [--output=PATH]compete//matrixPhase 3: Develop a comprehensive, annotated feature comparison matrix with [OSS]/[PAID] differentiation and cross-platform verification.
Research 2 or more competitors and build a structured comparison matrix across 7 key dimensions. Always executes fresh searches for each competitor — never uses cached data. Optionally adds a "You" column for self-positioning analysis.
Read the competitive-research skill at ${CLAUDE_PLUGIN_ROOT}/skills/compete/competitive-research/SKILL.md for surface scan strategy, query formulation, and data extraction rules.
Read the market-analysis skill at ${CLAUDE_PLUGIN_ROOT}/skills/compete/market-analysis/SKILL.md for matrix building conventions, dimension normalization, and self-comparison analysis.
Extract from $ARGUMENTS:
[company1] [company2] ... (required) — space-separated list of 2 or more company names or URLs. If fewer than 2 companies are provided, prompt: "Please provide at least 2 company names to build a comparison matrix. Example: /founder-os:compete:matrix Notion Linear Asana"--your-product="description" (optional) — description of your own product. When provided, adds a "You" column to the matrix.--output=PATH (optional) — output file path. Default: competitive-intel/matrix-[YYYY-MM-DD].md where [YYYY-MM-DD] is today's date.Check if context files exist at _infrastructure/context/active/. If the directory contains .md files, read business-info.md, strategy.md, and current-data.md. Use this context to personalize output (e.g., prioritize known clients, use correct terminology, align with current strategy). If files don't exist, skip silently.
Read the context-injection skill at _infrastructure/memory/context-injection/SKILL.md.
Query for memories relevant to the current input (company, contacts, topics detected in arguments).
If memories are returned, incorporate them into your working context for this execution.
For each company in the input list, apply the competitive-research skill independently:
Always execute fresh searches. Do not reuse any previously gathered data — each run of /founder-os:compete:matrix is a fresh research session.
Identify the company: Extract name and domain from each input (name or URL).
Formulate queries: Construct 4-6 targeted queries per company covering all 5 research dimensions (pricing, features, reviews, positioning, news).
Consult ${CLAUDE_PLUGIN_ROOT}/skills/compete/competitive-research/references/query-patterns.md for query templates. Use the Matrix Queries section for any cross-company comparison queries.
Execute searches: Run searches for each company. Apply data extraction and normalization rules from the competitive-research skill.
Extract matrix data points: For each company, extract the normalized values for all 7 matrix dimensions:
Sequencing: Research all companies before building the matrix. Complete all 5 research dimensions for one company before moving to the next to avoid data cross-contamination.
Apply the market-analysis skill's Matrix Building guidance:
Normalize all entries: Apply matrix normalization rules from ${CLAUDE_PLUGIN_ROOT}/skills/compete/market-analysis/references/analysis-frameworks.md to make all values comparable:
Build markdown table: Create a markdown comparison matrix with companies as columns and dimensions as rows.
Add 'You' column (only if --your-product was provided):
Add analysis summary: Below the matrix, include:
--your-product provided)Create output directory: Create competitive-intel/ directory at the working directory if it does not exist.
Write matrix file: Save to the output path. File should include: date, companies researched, the full comparison matrix, and analysis summary.
For each company researched:
Find the Research database: Search Notion for a database named "Founder OS HQ - Research". If not found, fall back to the legacy name "Competitive Intel Compiler - Research". If neither exists, skip Notion integration and warn the user once (do NOT create the database — it should be provisioned from the HQ template).
Resolve Company relation: For each researched company, search the "Founder OS HQ - Companies" database for a matching company name (case-insensitive). If found, use the existing page ID. If not found, create a new page in Companies with the company name as Title.
Save one record per company: Set Type="Competitive Analysis" and link the Company relation. Upsert by Company Name AND Type="Competitive Analysis" (update if exists, create if not).
If Notion MCP is unavailable:
${CLAUDE_PLUGIN_ROOT}/INSTALL.md."If a web search fails for one company:
Display in chat:
## Competitive Matrix — [Company A] vs [Company B] vs [Company C]
*Researched: [date]*
| Dimension | [Company A] | [Company B] | [Company C] | You |
|-----------|-------------|-------------|-------------|-----|
| Pricing | ... | ... | ... | ... |
| Target Market | ... | ... | ... | ... |
| Key Features | ... | ... | ... | ... |
| Positioning | ... | ... | ... | ... |
| Review Score | ... | ... | ... | ... |
| Strengths | ... | ... | ... | ... |
| Weaknesses | ... | ... | ... | ... |
| Positioning Opp. | — | — | — | 💡 [recommendation] |
*✅ = Your advantage | 💡 = Market whitespace*
---
### Market Overview
[1-2 sentences]
### Key Differentiators
- **[Company A]**: [what makes them distinct]
- **[Company B]**: [what makes them distinct]
### Whitespace Opportunities
[Underserved positions or unmet needs not covered by any competitor]
### Strategic Recommendations
1. **[Recommendation]**: [detail grounded in matrix data]
2. ...
End with:
**Matrix saved to**: [file path]
**Notion**: [Saved X company records to "Founder OS HQ - Research" (Type: Competitive Analysis) / Unavailable — not saved]
Read the pattern-detection skill at _infrastructure/memory/pattern-detection/SKILL.md.
Log this execution as an observation with: plugin name, primary action performed, key entities (companies, contacts), and output summary.
Check for emerging patterns per the detection rules. If a memory reaches the adaptation threshold, append the notification to the output.
/founder-os:compete:matrix Notion Linear
/founder-os:compete:matrix Asana ClickUp Monday Trello --your-product="Simple task manager for freelancers, $12/month"
/founder-os:compete:matrix Figma Sketch --output=reports/design-tools-matrix.md
/founder-os:compete:matrix "Notion" "Coda" "Obsidian" --your-product="Note-taking app with AI, free tier"