Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Run a competitive SEO analysis comparing the user's site to chosen competitors across SERP overlap, content depth, backlink profiles, technical posture, and brand presence. Use this skill whenever the user wants to analyze competitors, find content gaps, identify backlink opportunities, understand why competitors outrank them, or benchmark against the rest of their category. Triggers on competitor analysis, competitive analysis, SERP analysis, content gap, backlink gap, why is X ranking, who is
.claude/skills/rampstackco-seo-competitor/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 53% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -15% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 49% | 0% |
Compare a site to its competitors and find the gaps worth closing. Stack-agnostic. Tool-friendly but tool-optional.
seo-onpage)seo-keyword first to find them)seo-content-audit)If competitors are unknown, start by listing the top 10 ranking domains for the user's top 10 priority keywords. Pick the 3 to 5 that appear most often.
Where competitor traffic estimation is the input you need (relative scale, channel mix, audience overlap), Similarweb MCP is the strongest source. Pair with Ahrefs (for backlink and keyword overlap) and Semrush (for SERP feature presence and SEO-PR overlap). Each platform gives a different cut of the same competitive landscape; using them together produces sharper signal than any one alone.
Competitor analysis covers five angles. Run all five for a full picture, or pick two or three for a focused investigation.
Where do you and the competitor compete head-to-head?
What does their winning content look like?
Where does their authority come from?
How clean is their technical foundation?
How well-known are they outside organic search?
references/competitive-audit-template.md.Default output is a markdown report at competitive-analysis.md plus accompanying spreadsheets for the keyword and backlink data.
Structure:
This skill's output depends on data, measurements, or tool results it cannot generate on its own. When a required input, tool, or data source is unavailable or unverifiable, the sanctioned output is the deliverable with the gap stated: what was needed, what was actually obtained or verified, and which parts of the output are affected. Fabricating, estimating, or interpolating a required number to complete the deliverable is never sanctioned. A stated gap is a complete answer.
references/competitive-audit-template.md - Fillable competitive audit template.references/content-gap-method.md - Detailed methodology for finding content gaps with example.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-07 | fail→pass | 13,229 | 10,934 | -17% | 1 | 1 | 0% | 2,098 | 3,209 | +53% | 0 | 0 | — |
case-01 | fail→pass | 25,764 | 23,602 | -8% | 1 | 1 | 0% | 4,407 | 5,699 | +29% | 0 | 0 | — |
case-02 | fail→pass | 31,446 | 37,528 | +19% | 1 | 1 | 0% | 5,174 | 7,672 | +48% | 0 | 0 | — |
case-03 | fail→fail | 19,618 | 22,374 | +14% | 1 | 1 | 0% | 3,435 | 5,441 | +58% | 0 | 0 | — |
case-04 | pass→pass | 8,244 | 9,643 | +17% | 1 | 1 | 0% | 1,419 | 3,000 | +111% | 0 | 0 | — |
case-05 | pass→pass | 18,164 | 11,592 | -36% | 1 | 1 | 0% | 2,853 | 3,468 | +22% | 0 | 0 | — |
case-06 | pass→pass | 15,489 | 10,699 | -31% | 1 | 1 | 0% | 2,499 | 3,332 | +33% | 0 | 0 | — |
case-08 | pass→pass | 12,904 | 10,490 | -19% | 1 | 1 | 0% | 2,144 | 3,222 | +50% | 0 | 0 | — |
case-09 | fail→pass | 15,396 | 3,489 | -77% | 1 | 1 | 0% | 2,360 | 2,016 | -15% | 0 | 0 | — |
case-10 | pass→pass | 14,267 | 7,449 | -48% | 1 | 1 | 0% | 2,377 | 2,655 | +12% | 0 | 0 | — |
case-11 | pass→pass | 13,155 | 11,125 | -15% | 1 | 1 | 0% | 2,184 | 3,232 | +48% | 0 | 0 | — |
case-12 | pass→pass | 12,621 | 10,268 | -19% | 1 | 1 | 0% | 1,982 | 2,924 | +48% | 0 | 0 | — |
case-13 | fail→pass | 15,599 | 14,163 | -9% | 1 | 1 | 0% | 2,526 | 3,773 | +49% | 0 | 0 | — |
case-14 | fail→pass | 22,765 | 2,651 | -88% | 1 | 1 | 0% | 1,036 | 1,973 | +90% | 0 | 0 | — |
case-15 | fail→pass | 14,894 | 6,668 | -55% | 1 | 1 | 0% | 2,565 | 2,697 | +5% | 0 | 0 | — |
case-16 | pass→pass | 14,225 | 13,401 | -6% | 1 | 1 | 0% | 2,309 | 3,465 | +50% | 0 | 0 | — |
case-17 | fail→fail | 19,364 | 14,669 | -24% | 1 | 1 | 0% | 3,168 | 3,815 | +20% | 0 | 0 | — |
case-18 | pass→pass | 16,473 | 9,229 | -44% | 1 | 1 | 0% | 2,721 | 2,807 | +3% | 0 | 0 | — |
case-19 | fail→fail | 15,880 | 13,703 | -14% | 1 | 1 | 0% | 2,539 | 3,519 | +39% | 0 | 0 | — |
case-20 | pass→pass | 14,722 | 15,429 | +5% | 1 | 1 | 0% | 2,196 | 3,767 | +72% | 0 | 0 | — |
case-21 | pass→pass | 15,423 | 10,692 | -31% | 1 | 1 | 0% | 2,405 | 3,091 | +29% | 0 | 0 | — |
case-22 | fail→fail | 13,651 | 10,371 | -24% | 1 | 1 | 0% | 1,900 | 2,889 | +52% | 0 | 0 | — |
case-23 | pass→pass | 10,598 | 8,136 | -23% | 1 | 1 | 0% | 1,567 | 2,550 | +63% | 0 | 0 | — |
case-24 | pass→pass | 12,603 | 3,086 | -76% | 1 | 1 | 0% | 2,001 | 1,896 | -5% | 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. 24 cases were attempted, and 23 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +29 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.