Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to analyze competitors for SEO, content, backlinks, or positioning. Also use when the user mentions "competitor analysis," "competitor research," "competitor keywords," "competitor backlinks," "link gap," "content gap," "competitor content," "competitive analysis," or "competitor comparison." For content roadmap, use content-strategy.
.claude/skills/mkurman-competitor-research/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 42% | 0% |
|---------|--------| | Keyword/topic | Topics competitors rank for; gaps | Keyword opportunities; content ideas | | Content | Structure, length, gaps vs top rankers | Length target; H2 structure; content gaps | | Backlink | Link profile; sites linking to competitors | Link gap; outreach targets | | Pricing | Competitor pricing, positioning | Pricing context; differentiation | | SEO metrics | Organic traffic, rankings vs competitors | Benchmark; opportunity areas |
| Method | Practice | |--------|----------| | Reverse engineering | Analyze competitor titles, H1, URL; identify topics they rank for | | SERP overlap | Keywords with overlapping top-ranking pages → same cluster; #4–10 = opportunity | | site: operator | site:competitor.com to see indexed pages | | Tool | Ahrefs, Semrush—competitor keyword overlap, gap analysis |
Output: Keyword opportunities; topics competitors cover that you don't.
| Element | Check | |---------|-------| | Word count | Top 10 average; length target for your content | | H2 structure | Topics covered; structure to adopt | | Content gaps | What top rankers cover that you miss | | Keyword placement | Primary keyword in title, H1, first 100 words | | Format | Lists, tables, FAQ; match or improve |
Use when: Auditing or creating articles; see article-page-generator for Research Phase integration.
When analyzing or auditing a single article, use this lightweight workflow to obtain competitor articles:
"[target keyword]" to find top-ranking pagesOutput format: Competitor URLs; word count and H2 structure per URL; content gaps vs your article; recommended length target; keyword opportunities (terms top rankers use that your article misses).
| Action | Purpose | |--------|---------| | Compare profiles | Your backlinks vs competitors | | Link gap | Sites linking to competitors but not you | | Opportunity | Outreach to those sites; content they might link to |
Tools: Ahrefs, Semrush—Link Intersect, competitor backlink reports. See backlink-analysis.
| Use | Practice | |-----|----------| | Positioning | Where you sit vs competitors | | Differentiation | Value prop when price differs | | Alternatives pages | Who to include; how to position |
See pricing-strategy, alternatives-page-generator.
| Source | Use | |--------|-----| | SimilarWeb | Traffic, engagement, traffic sources by domain | | Ahrefs | Competitor domains, backlinks, DR | | SEMrush | Organic competitors, traffic share | | GA | Referral traffic, acquisition by source | | PostHog | Competitor feature usage (if tracked) |
project-context.md if present| Section | Content | |---------|---------| | Executive Summary | Key findings (top 3), top 3 recommendations | | Competitor Overview | Competitor, category, market position, key strength | | Product Comparison | Feature/capability vs Us vs Competitors | | SWOT Analysis | Our strengths/weaknesses/opportunities/threats; competitor deep dives | | Marketing & Messaging | Value prop, target audience, key channels | | Gaps & Opportunities | Gap, opportunity, priority | | Prioritized Recommendations | Recommendation, impact, effort, owner |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 23,272 | 23,059 | -1% | 1 | 1 | 0% | 3,610 | 4,660 | +29% | 0 | 0 | — |
case-18 | pass→pass | 10,847 | 5,145 | -53% | 1 | 1 | 0% | 1,724 | 1,987 | +15% | 0 | 0 | — |
case-02 | fail→pass | 16,629 | 13,631 | -18% | 1 | 1 | 0% | 2,550 | 3,267 | +28% | 0 | 0 | — |
case-03 | pass→pass | 19,945 | 14,179 | -29% | 1 | 1 | 0% | 3,112 | 3,336 | +7% | 0 | 0 | — |
case-04 | pass→pass | 18,655 | 18,930 | +1% | 1 | 1 | 0% | 2,906 | 4,036 | +39% | 0 | 0 | — |
case-05 | pass→pass | 14,769 | 22,087 | +50% | 1 | 1 | 0% | 2,129 | 3,116 | +46% | 0 | 0 | — |
case-06 | pass→pass | 15,441 | 13,305 | -14% | 1 | 1 | 0% | 2,418 | 3,268 | +35% | 0 | 0 | — |
case-07 | fail→pass | 16,476 | 12,801 | -22% | 1 | 1 | 0% | 2,330 | 3,296 | +41% | 0 | 0 | — |
case-08 | fail→pass | 7,649 | 2,638 | -66% | 1 | 1 | 0% | 1,119 | 1,595 | +43% | 0 | 0 | — |
case-09 | pass→pass | 4,525 | 2,693 | -40% | 1 | 1 | 0% | 758 | 1,620 | +114% | 0 | 0 | — |
case-10 | fail→fail | 9,384 | 2,353 | -75% | 1 | 1 | 0% | 1,308 | 1,553 | +19% | 0 | 0 | — |
case-11 | pass→pass | 5,890 | 3,075 | -48% | 1 | 1 | 0% | 853 | 1,667 | +95% | 0 | 0 | — |
case-12 | pass→pass | 18,377 | 17,688 | -4% | 1 | 1 | 0% | 2,842 | 4,027 | +42% | 0 | 0 | — |
case-13 | fail→fail | 22,092 | 15,123 | -32% | 1 | 1 | 0% | 1,950 | 2,416 | +24% | 0 | 0 | — |
case-14 | fail→pass | 12,962 | 10,368 | -20% | 1 | 1 | 0% | 1,916 | 2,726 | +42% | 0 | 0 | — |
case-15 | pass→pass | 6,565 | 1,978 | -70% | 1 | 1 | 0% | 1,014 | 1,469 | +45% | 0 | 0 | — |
case-16 | fail→pass | 6,430 | 2,027 | -68% | 1 | 1 | 0% | 971 | 1,439 | +48% | 0 | 0 | — |
case-17 | fail→pass | 11,913 | 10,719 | -10% | 1 | 1 | 0% | 1,865 | 2,787 | +49% | 0 | 0 | — |
case-19 | pass→pass | 6,651 | 5,303 | -20% | 1 | 1 | 0% | 966 | 1,949 | +102% | 0 | 0 | — |
case-20 | fail→pass | 10,633 | 4,287 | -60% | 1 | 1 | 0% | 1,723 | 1,809 | +5% | 0 | 0 | — |
case-21 | pass→pass | 40,107 | 10,464 | -74% | 1 | 1 | 0% | 2,392 | 2,833 | +18% | 0 | 0 | — |
case-22 | pass→pass | 18,181 | 19,346 | +6% | 1 | 1 | 0% | 2,543 | 3,932 | +55% | 0 | 0 | — |
case-23 | fail→pass | 10,412 | 2,608 | -75% | 1 | 1 | 0% | 1,538 | 1,646 | +7% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +39 percentage points is the difference between those two pass rates over the 23 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.