Inputs
Provide these when prompted. The skill asks for anything missing before it runs.
Required
- Two or more company records
Optional
- Comparison dimensions you care about
- Your own product for white-space framing
Agent Skill
Competitor Research
Compare a group of companies by products, positioning, market focus, and differentiators.
Version 1.0 Updated June 2026 SKILL.md MIT 6 min read
Overview
What this skill does
Competitive comparisons assembled by hand tend to be uneven: one competitor gets three paragraphs, another a single line, and the axes of comparison shift between rows.
This skill compares every company on the same dimensions, builds a structured comparison table, summarizes positioning, and identifies overlaps and differentiation opportunities you can act on.
When to use it
Best used for
- Building a competitive landscape from a company set
- Comparing positioning across rivals
- Finding white space and differentiation angles
- Preparing competitive briefs
Know the limits
When not to use this skill
- You have only one company (use Company Research instead)
- The records lack product or positioning signal
- You need pricing data the records do not include
Outputs
A single comparison with a consistent, inspectable schema.
comparison_tableCompanies compared on shared dimensions.
positioning_summaryHow each company is positioned.
strengthsEvidenced strengths per company.
weaknessesApparent weaknesses or gaps.
overlapsWhere competitors converge.
differentiation_opportunitiesWhite space to exploit.
Example
Example
Two competitors compared briefly.
Input
Compare: Acme CRM (SMB, low price, simple) vs Northwind CRM (mid-market, integrations, higher price).Output
comparison_table: price (Acme low / Northwind high); segment (SMB / mid-market); integrations (few / many)
positioning_summary: Acme = simple+cheap; Northwind = integrated+upmarket
strengths: Acme onboarding; Northwind ecosystem
weaknesses: Acme limited integrations; Northwind complexity
overlaps: Both target sales teams
differentiation_opportunities: Mid-market simplicity with key integrationsThe table makes the trade-off explicit and surfaces a clear white space: integrated but simple for mid-market, between the two incumbents.
Setup
How to use the skill
General steps first, then notes for specific clients where verified.
- 1Download the file using the button below, or copy the Markdown.
- 2Place it in a directory named after the skill (e.g. skill-name/).
- 3Make sure the filename stays exactly SKILL.md.
- 4Add any references or assets included with the package.
- 5Load the skill into a compatible agent and provide the required inputs.
Claude Code
- 1Create a folder for the skill and save SKILL.md inside it.
- 2Place the folder where your project's skills are discovered.
- 3Reference the skill when you want it applied to your data.
Other compatible clients
- 1Confirm the client supports the open Agent Skills format.
- 2Load the SKILL.md file as instructed by that client.
- 3If skills are not auto-loaded, paste the Markdown as instructions.
Source
Full SKILL.md source
Read the rendered skill or copy the complete Markdown. The download is generated from this exact source.
Version 1.0 SKILL.md ~2 KB MIT
Competitor Research
Purpose
Compare a group of companies by products, positioning, market focus, and differentiators.
When to use this skill
- Building a competitive landscape from a company set
- Comparing positioning across rivals
- Finding white space and differentiation angles
- Preparing competitive briefs
When not to use this skill
- You have only one company (use Company Research instead)
- The records lack product or positioning signal
- You need pricing data the records do not include
Required inputs
- Two or more company records
Optional inputs
- Comparison dimensions you care about
- Your own product for white-space framing
Rules
- Compare every company on the same dimensions.
- Use supplied evidence; do not invent features or pricing.
- Separate facts from interpretation.
- Make overlaps and gaps explicit.
- Keep the table structure consistent.
Process
- Choose comparison dimensions (or use supplied ones).
- Extract each company against those dimensions.
- Build the comparison table.
- Summarize positioning, strengths, weaknesses.
- Identify overlaps and differentiation opportunities.
Output format
Return a single comparison with the following fields:
- comparison_table
- positioning_summary
- strengths
- weaknesses
- overlaps
- differentiation_opportunities
Validation
- Confirm all companies share the same dimensions.
- Confirm claims cite evidence.
- Confirm opportunities follow from the comparison.
Limitations
- Comparisons reflect supplied data, not full market knowledge.
- Positioning is interpretive and may need validation.
Before you rely on it
Safety and limitations
- Comparisons reflect supplied data, not full market knowledge.
- Positioning is interpretive and may need validation.
- Review the output before acting on it.
- Do not upload confidential datasets to an external model without authorization.
- Outputs depend on the model and the source data and are not guaranteed to be accurate.
History
Changelog
- v1.0June 2026
- Initial release.
Questions
Agent Skill FAQ
What does the comparison highlight?
Products, positioning, market focus, and differentiators side by side, plus the differentiation gaps — where a company is undifferentiated or where the market is unserved.
How many competitors can it compare?
It handles a small set well. For very large sets, use Market Research first to find segments, then compare within a segment.
Do I need ProfileSpider to use this skill?
No. The skill works on any compatible data. ProfileSpider is one convenient way to produce that structured input.
Does running this skill send data to ProfileSpider?
No. Downloading or copying the file does not send any data to ProfileSpider. What happens afterward depends on the AI service you load it into.
Are Agent Skills the same as prompts?
No. A skill is a structured, reusable package — task, inputs, rules, process, and output format — so the workflow runs consistently and can be shared, versioned, and edited.