skills/competitor-alternatives/SKILL.md
Use when creating competitor comparison pages, alternative-to landing pages, vs-competitor content, competitive battle cards, or win/loss analysis documentation. Use when a user says 'alternative page,' 'vs page,' 'comparison page,' 'battle card,' '[Product] vs [Product],' or 'competitor analysis content.' Do NOT use for general content marketing, SEO strategy unrelated to competitive pages, product roadmap decisions, or pricing strategy.
npx skillsauth add sharkitect-solutions/sharkitect-claude-toolkit competitor-alternativesInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
| File | Load When | Do NOT Load |
|------|-----------|-------------|
| references/competitive-intelligence-methods.md | Building battle cards, conducting win/loss analysis, setting up competitive monitoring, mining competitor reviews, designing CI workflows | Writing comparison page copy, CRO questions, legal compliance checks |
| references/conversion-optimization.md | Designing comparison page layouts, optimizing CTAs on competitive pages, A/B testing comparison formats, improving conversion rates on vs pages | CI methodology, legal compliance, battle card content strategy |
| references/legal-compliance.md | Making claims about competitors, using competitor trademarks or screenshots, publishing comparative advertising, responding to competitor legal objections | Page layout decisions, CI methodology, conversion optimization |
| Domain | This Skill Covers | Use Instead | |--------|-------------------|-------------| | General SEO content | Competitive keyword pages only | seo-audit, content-research-writer | | Pricing strategy | Competitive pricing presentation on pages only | smb-cfo | | Product roadmap | Feature gap documentation for pages only | Product management tooling | | Sales enablement (general) | Battle cards and competitive positioning only | sales-enablement | | Content marketing | Comparison/alternative content only | content-research-writer |
Four distinct formats exist. Each targets different search intent, converts at different rates, and requires different editorial approaches. Mismatching format to intent wastes ranking potential.
| Format | URL Pattern | Search Intent | Expected CVR | Editorial Stance |
|--------|-------------|---------------|-------------|------------------|
| Singular alternative | /alternative/[competitor] | Active switcher, frustrated with specific tool | 3-5% | Empathetic guide, validate their pain |
| Plural alternatives | /[competitor]-alternatives | Early researcher, exploring options | 2-3% | Objective curator, you are one of many |
| You-vs-them | /vs/[competitor] | Direct comparison shopper, shortlist of two | 4-7% | Confident but fair, acknowledge their strengths |
| Them-vs-them | /compare/[a]-vs-[b] | Evaluating competitors, unaware of you | 1-2% (but high brand discovery) | Neutral analyst, earn trust before introducing yourself |
The modifier attached to the competitor name reveals buyer stage and emotional state:
Structured win/loss interviews are the foundation of credible competitive content. Unstructured "why did you choose us" surveys produce self-serving data that readers detect immediately.
Minimum sample size: 20 interviews per competitor (10 wins, 10 losses). Below 20, patterns are anecdotal. Above 50, diminishing returns. Weight recent interviews (last 6 months) at 2x older ones.
Interview structure: (1) Open with their evaluation process -- who was involved, what triggered the search, what was the timeline. (2) Ask about decision criteria ranking before discussing specific vendors. (3) Walk through each vendor evaluated, strengths and weaknesses observed. (4) Close with the decisive factor -- the single thing that tipped the decision.
Never let sales teams conduct their own win/loss interviews. Confirmation bias contaminates results. Use a neutral party -- product marketing, an external firm, or a structured survey with forced-ranking questions.
Score features on a 1-5 scale weighted by buyer priority. Raw feature counts are meaningless -- a competitor with 200 features that neglects the 5 features your buyer cares about loses the comparison.
| Weight | Score Meaning | When to Assign | |--------|--------------|----------------| | 5 (critical) | Deal-breaker if missing | Buyer mentions unprompted in >60% of win/loss interviews | | 3 (important) | Influences decision | Buyer mentions in 30-60% of interviews | | 1 (nice-to-have) | Tiebreaker only | Buyer mentions in <30% of interviews |
Weighted score = Feature score (1-5) x Priority weight. Sum weighted scores per vendor. This produces defensible rankings that survive scrutiny because the weighting methodology is transparent and buyer-derived.
Three high-signal, low-noise sources for ongoing intelligence:
Eye-tracking research (Nielsen Norman Group, Baymard Institute) consistently shows comparison page visitors scan in an F-pattern, reading the first element thoroughly then skimming. Place the verdict above the fold, not the feature table.
Correct hierarchy: (1) Verdict sentence -- "Choose X if you need A; choose Y if you need B." (2) Summary comparison table -- 5-7 rows maximum. (3) Detailed comparison sections below.
Wrong hierarchy: Leading with a feature table. Users see a grid of checkmarks, conclude "they look the same," and bounce. Bounce rates on feature-first comparison pages run 15-25% higher than verdict-first pages (based on Hotjar/CrazyEgg heatmap studies across B2B SaaS sites).
Comparison pages are inherently suspect -- readers know the publisher has a bias. Trust engineering is the set of techniques that neutralize this suspicion:
Comparison pages convert 2-3x higher when the CTA follows a "you need X if..." section rather than appearing after a generic feature table. The psychological mechanism is self-selection: readers who have just confirmed they match the described profile experience commitment consistency -- they identified as the target audience and the CTA aligns with that self-identification.
High-converting placement: After "Who should choose [Your Product]" section. Low-converting placement: After a feature comparison table (reader is still evaluating, not decided). Avoid: Sticky CTAs that appear before the reader has consumed any comparison content. These convert at 0.3-0.5% on comparison pages vs 2-4% on product pages because comparison visitors are in evaluation mode, not purchase mode.
Feature tables with yes/no values are table stakes -- every competitor publishes them. Differentiation requires narrative comparison that addresses what feature tables cannot:
When a competitor genuinely outperforms you in a dimension, three approaches work:
Never ignore a dimension where you lose. Readers who have already used the competitor will immediately detect the omission, and your credibility collapses for every other claim on the page.
Present your pricing after the competitor's, not before. The competitor's price becomes the anchor. If they are more expensive, your price feels like a deal. If they are cheaper, present value metrics alongside price to shift the anchor from cost to value-per-dollar.
On plural alternatives pages (listing 5-7 alternatives), include at least one option that is clearly inferior on the dimensions your ideal buyer cares about. This "decoy" makes your product look stronger by contrast -- not through deception, but through legitimate comparison that highlights relative strengths. The decoy must be a real product, not a fabrication.
Max 5 alternatives per comparison page. Barry Schwartz's paradox of choice research shows that beyond 5-7 options, decision quality and decision satisfaction both decline. For plural alternatives pages, curate ruthlessly: include only alternatives that genuinely serve different segments. If two alternatives serve the same segment, keep the stronger one.
"What you lose by staying with X" is 2-2.5x more motivating than "what you gain by switching to Y" (Kahneman & Tversky, prospect theory). Structure at least one section around what the reader is missing or risking by not switching. Frame it as opportunity cost, not fear -- the goal is informed decision-making, not manipulation.
When targeting 20+ competitors, build template systems rather than writing each page from scratch:
Google's helpful content guidelines penalize stale comparison content. Build freshness into the system:
Only comparing against weak or unknown competitors while ignoring the dominant players readers are actually evaluating. Detect: Your top 3 competitors by market share are absent from your comparison pages. Traffic comes from long-tail terms, not head terms. Fix: Start with the hardest comparisons. If you cannot write an honest page against your strongest competitor, your positioning needs work before your content does.
Feature comparison tables using yes/no that hide implementation depth, quality differences, and practical limitations. A checkmark for "API access" could mean a full REST API or a read-only webhook. Detect: Every row in your comparison table is yes/no or checkmarks. Competitor columns have suspiciously many "no" entries. Fix: Replace checkmarks with descriptive text. "Full REST API with 99.9% uptime SLA" vs "Read-only API, rate-limited to 100 calls/day."
Publishing competitor pages that go stale within 3 months. Competitor pricing changes, features launch, products pivot -- and your page still shows last year's data. Detect: No "last verified" date on pages. Competitor pricing on your page differs from their current pricing page. Fix: Implement 90-day verification cycles. Assign ownership per competitor page. Automate pricing page monitoring.
Pretending objectivity while systematically sandbagging the competitor through selective emphasis, unfavorable screenshots, or comparison dimensions chosen specifically because you win them. Detect: Every comparison dimension favors you. Competitor strengths are mentioned in passing; your strengths get detailed paragraphs. Fix: Apply the trust engineering framework. Give at least one section where you explicitly recommend the competitor for a specific use case.
Comparing incomparable pricing structures -- your annual price against their monthly, your per-seat against their per-usage, your starter tier against their enterprise. Detect: Price comparison requires footnotes to be accurate. Readers in comments or reviews call out pricing inaccuracies. Fix: Normalize pricing to the same basis (monthly per-seat, or annual total for a defined team size). Show the math. Disclose billing model differences explicitly.
Making factual claims about competitors that cannot be substantiated, using competitor trademarks improperly, or publishing comparative advertising that violates jurisdiction-specific regulations. Detect: Claims include superlatives ("the only," "the best," "the fastest") without substantiation. Competitor logos are used without consideration of trademark law. No legal review of comparison page claims. Fix: See references/legal-compliance.md for jurisdiction-specific rules. Every factual claim about a competitor must be verifiable and sourced.
| Shortcut | Why It Seems OK | Why It Fails | Do This Instead | |----------|----------------|--------------|-----------------| | "We only need to compare against 2-3 competitors" | Covers the main threats | Readers searching for alternatives you did not cover find a competitor's page instead of yours. Every uncovered competitor is traffic you cede. | Map all competitors with >500 monthly search volume for "[competitor] alternative" keywords. Prioritize by volume, cover all above threshold. | | "Feature tables are enough for comparison pages" | Quick to produce, easy to scan | Checkbox tables commoditize the comparison. Readers cannot distinguish meaningful differences. Bounce rates exceed 65% on table-only pages. | Use tables as summary only. Follow each table with narrative comparison explaining what the differences mean in practice. | | "We can publish now and update later" | Speed to market matters for SEO | "Later" averages 14 months in practice. Stale pages with wrong pricing or missing features damage credibility permanently. Readers share the errors on social media. | Build verification into the publishing workflow. No page goes live without a "last verified" date and a 90-day review owner assigned. | | "Being objective means we should not recommend ourselves" | Appears unbiased | Readers came to your site. They expect your perspective. False neutrality reads as either lack of confidence or concealed manipulation. | Be transparent about your bias. State who you are, then provide genuine analysis. Recommend competitors for use cases where they genuinely fit better. | | "Competitor pages are just an SEO play" | Primary traffic source is organic search | Comparison pages serve sales enablement, customer success (competitive displacement), and brand positioning. Treating them as SEO-only produces thin content that ranks temporarily and converts poorly. | Design for the buyer, not the algorithm. Sales teams use these pages in deals. CSMs share them during competitive displacement. |
development
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ad copy,' 'ad creative,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' or 'audience targeting.' This skill covers campaign strategy, ad creation, audience targeting, and optimization.
testing
--- name: using-sharkitect-methodology description: Use when starting any conversation in a Sharkitect workspace OR before any task involving NEW pricing, positioning, proposal, strategy, plan-execution, or schema-design work — mandates invocation of Sharkitect-specific methodology skills (pricing-strategy, marketing-strategy-pmm, smb-cfo, hq-revenue-ops, executing-plans, brainstorming) under the same anti-rationalization discipline as using-superpowers. Documentation has failed 4 times across H
testing
Use when user says 'end session', 'wrap up', 'stop for the day', 'done for today', 'close out', 'save session', 'wrapping up', or invokes /end-session. Runs the full 9-step end-of-session protocol: resource audit, MEMORY.md update, lessons capture, plan status, pending items, workspace checklist, .tmp/ audit, git commit+push, Supabase brain sync, session brief, summary. Final step schedules a detached self-kill of the current session ONLY (3s delay) so the window closes cleanly. Other claude.exe processes (active workspaces) are NOT touched -- orphan cleanup is handled separately by Claude-Orphan-Cleanup-Hourly with proper age safeguards. Do NOT use for: mid-session quick saves (use session-checkpoint), skill syncing (use sync-skills.py), brain memory queries (use supabase-sync.py pull), document freshness reviews (use document-lifecycle), resource gap detection (use resource-auditor).
testing
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.