Creates SEO-optimized competitor comparison and alternative pages (e.g., 'Product X vs Product Y', 'Product X Alternatives') to capture search traffic and assist buyer decision-making. Also audits existing competitor pages for accuracy and freshness.
Say it in your own words; the assistant finds this recipe by itself. Examples:
Use this skill when the user requests the creation of 'vs' pages, 'alternative' pages, or competitor comparison content for their website. It is also appropriate when the user asks to audit existing competitor pages for outdated claims or factual errors. This skill handles the four main formats: singular alternative, plural alternatives, you-vs-competitor, and competitor-vs-competitor.
You are an expert in creating competitor comparison and alternative pages. Your goal is to build pages that rank for competitive search terms, provide genuine value to evaluators, and position your product effectively.
Check for product marketing context first:
If .agents/product-marketing.md exists (or .claude/product-marketing.md, or the legacy product-marketing-context.md filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Never guess the competitor. If the request doesn't name one and the context file doesn't identify it, ask, and stop there. Don't draft a polished page around the most likely candidate.
Before creating competitor pages, understand:
Strengths and honest weaknesses
Competitive Landscape
Search volume for competitor terms
Goals
Comparison pages are public claims about another company. Every one should survive the competitor's own team reading it. - "Not observed" is not "doesn't have." A pricing page that doesn't list SSO is evidence about the page, not the product. Write "not listed on their pricing page (as of Mar 2026)" or drop the row. Use ✗ or "not available" only when their docs or a hands-on trial confirm the absence. - Date competitor facts. Pricing and features change. Put an "as of" date on pricing tables and in the competitor data file, and re-verify before republishing. - One look is a snapshot. A single visit can't support "they haven't changed pricing in years" or "no new features since 2024." That needs dated history (changelog, archived pages). - State what changed, not why. "They moved SSO to the Enterprise tier" is a fact. "Because they're squeezing upmarket" is a guess. Leave motive out unless they've said it publicly. - Separate fact from interpretation. Keep what their site says apart from what you think it means for the buyer, and keep both apart from what you recommend.
Search intent: User is actively looking to switch from a specific competitor
URL pattern: /alternatives/[competitor] or /[competitor]-alternative
Target keywords: "[Competitor] alternative", "alternative to [Competitor]", "switch from [Competitor]"
Page structure: 1. Why people look for alternatives (validate their pain) 2. Summary: You as the alternative (quick positioning) 3. Detailed comparison (features, service, pricing) 4. Who should switch (and who shouldn't) 5. Migration path 6. Social proof from switchers 7. CTA
Search intent: User is researching options, earlier in journey
URL pattern: /alternatives/[competitor]-alternatives
Target keywords: "[Competitor] alternatives", "best [Competitor] alternatives", "tools like [Competitor]"
Page structure: 1. Why people look for alternatives (common pain points) 2. What to look for in an alternative (criteria framework) 3. List of alternatives (you first, but include real options) 4. Comparison table (summary) 5. Detailed breakdown of each alternative 6. Recommendation by use case 7. CTA
Important: Include 4-7 real alternatives. Being genuinely helpful builds trust and ranks better.
AI-answer expectations by stage: these pages often earn citations in AI answers, but whether AI recommends your brand from them depends on offsite consensus (reviews, forums, analysts) — for emerging brands, a self-ranked list can surface the competitors in the AI answer while you get only the citation. Still publish for search intent and category framing, but set expectations accordingly — see ai-seo's citations-vs-recommendations reference for the data.
Search intent: User is directly comparing you to a specific competitor
URL pattern: /vs/[competitor] or /compare/[you]-vs-[competitor]
Target keywords: "[You] vs [Competitor]", "[Competitor] vs [You]"
Page structure: 1. TL;DR summary (key differences in 2-3 sentences) 2. At-a-glance comparison table 3. Detailed comparison by category (Features, Pricing, Support, Ease of use, Integrations) 4. Who [You] is best for 5. Who [Competitor] is best for (be honest) 6. What customers say (testimonials from switchers) 7. Migration support 8. CTA
Search intent: User comparing two competitors (not you directly)
URL pattern: /compare/[competitor-a]-vs-[competitor-b]
Page structure: 1. Overview of both products 2. Comparison by category 3. Who each is best for 4. The third option (introduce yourself) 5. Comparison table (all three) 6. CTA
Why this works: Captures search traffic for competitor terms, positions you as knowledgeable.
Start every page with a quick summary for scanners—key differences in 2-3 sentences.
Go beyond tables. For each dimension, write a paragraph explaining the differences and when each matters.
For each category: describe how each handles it, list strengths and limitations, give bottom line recommendation.
Include tier-by-tier comparison, what's included, hidden costs, and total cost calculation for sample team size.
Be explicit about ideal customer for each option. Honest recommendations build trust.
Cover what transfers, what needs reconfiguration, support offered, and quotes from customers who switched.
For detailed templates: See references/templates.md
Create a single source of truth for each competitor with: - Positioning and target audience - Pricing (all tiers) - Feature ratings - Strengths and weaknesses - Best for / not ideal for - Common complaints (from reviews) - Migration notes
For data structure and examples: See references/content-architecture.md
For each competitor, gather:
When asked to check existing competitive content for stale or risky claims, audit every asset that makes claims about competitors: vs and alternative pages, battle cards, talk tracks, objection docs, and comparison tables in decks.
Apply the Evidence Discipline rules above to every claim, including those in internal sales assets. Where several assets repeat one fact, fix it in the centralized competitor data so the fix carries through.
| Format | Primary Keywords |
|---|---|
| Alternative (singular) | [Competitor] alternative, alternative to [Competitor] |
| Alternatives (plural) | [Competitor] alternatives, best [Competitor] alternatives |
| You vs Competitor | [You] vs [Competitor], [Competitor] vs [You] |
| Competitor vs Competitor | [A] vs [B], [B] vs [A] |
Consider FAQ schema for common questions like "What is the best alternative to [Competitor]?"
Complete competitor profile in YAML format for use across all comparison pages.
For each page: URL, meta tags, full page copy organized by section, comparison tables, CTAs.
Recommended pages to create with priority order based on search volume.
Claims checked per asset, status counts (current / changed / unverifiable / overclaimed), and a prioritized fix list with replacement wording.
LICENSESKILL.mdevals/evals.jsonreferences/content-architecture.mdreferences/templates.mdVendored from coreyhaines31/marketingskills, commit e85f3cbc2e4a, path skills/competitors, licence MIT. The upstream licence file ships inside the skill.