Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Comprehensive SEO Master Skill covering fundamentals, audit, content creation, technical optimization, and scaling.
.claude/skills/dokhacgiakhoa-seo-expert-kit/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-13 | ✓→✗ | ▼ Worse | 60% | 0% |
| case-20 | ✓→✗ | ▼ Worse | 94% | 0% |
| case-01 | ✓→✓ | = Same ✓ | 52% | 0% |
You are an Elite SEO Strategist and Growth Engineer. This skill provides a unified framework for search engine optimization, from foundational principles to advanced execution.
Principles for sustainable search visibility.
Identify and prioritize issues affecting organic performance.
For every issue identified, report: Issue, Severity (Critical/High/Med/Low), Evidence, and Recommendation.
Planning for clusters and topical authority.
Writing for humans, optimizing for machines.
Ensuring clarity for crawlers.
Article, FAQPage, Product, or Organization using JSON-LD.Building systems that generate SEO value at scale.
Merged and optimized from 13 legacy SEO skills.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 7,606 | 9,425 | +24% | 1 | 1 | 0% | 1,317 | 1,999 | +52% | 0 | 0 | — |
case-02 | pass→pass | 6,874 | 6,257 | -9% | 1 | 1 | 0% | 935 | 2,019 | +116% | 0 | 0 | — |
case-03 | pass→pass | 9,572 | 6,563 | -31% | 1 | 1 | 0% | 1,531 | 2,145 | +40% | 0 | 0 | — |
case-04 | pass→pass | 9,718 | 3,286 | -66% | 1 | 1 | 0% | 1,630 | 1,696 | +4% | 0 | 0 | — |
case-05 | pass→pass | 14,422 | 2,306 | -84% | 1 | 1 | 0% | 1,149 | 1,503 | +31% | 0 | 0 | — |
case-06 | pass→pass | 12,625 | 4,950 | -61% | 1 | 1 | 0% | 1,763 | 1,935 | +10% | 0 | 0 | — |
case-07 | pass→pass | 10,392 | 6,904 | -34% | 1 | 1 | 0% | 1,551 | 2,127 | +37% | 0 | 0 | — |
case-08 | fail→pass | 11,268 | 5,122 | -55% | 1 | 1 | 0% | 1,631 | 1,946 | +19% | 0 | 0 | — |
case-09 | fail→fail | 7,878 | 6,515 | -17% | 1 | 1 | 0% | 1,243 | 2,165 | +74% | 0 | 0 | — |
case-10 | fail→pass | 12,202 | 6,445 | -47% | 1 | 1 | 0% | 2,029 | 2,126 | +5% | 0 | 0 | — |
case-11 | pass→pass | 8,348 | 18,583 | +123% | 1 | 1 | 0% | 1,354 | 2,039 | +51% | 0 | 0 | — |
case-12 | pass→pass | 9,173 | 10,110 | +10% | 1 | 1 | 0% | 1,599 | 2,738 | +71% | 0 | 0 | — |
case-13 | pass→fail | 7,603 | 5,655 | -26% | 1 | 1 | 0% | 1,292 | 2,068 | +60% | 0 | 0 | — |
case-14 | pass→pass | 7,474 | 6,090 | -19% | 1 | 1 | 0% | 1,291 | 2,085 | +62% | 0 | 0 | — |
case-15 | pass→pass | 9,159 | 6,893 | -25% | 1 | 1 | 0% | 1,483 | 2,092 | +41% | 0 | 0 | — |
case-16 | pass→pass | 9,021 | 8,367 | -7% | 1 | 1 | 0% | 1,688 | 2,528 | +50% | 0 | 0 | — |
case-17 | pass→pass | 8,704 | 4,813 | -45% | 1 | 1 | 0% | 1,395 | 1,906 | +37% | 0 | 0 | — |
case-18 | pass→pass | 14,316 | 17,031 | +19% | 1 | 1 | 0% | 2,452 | 3,953 | +61% | 0 | 0 | — |
case-19 | pass→pass | 19,300 | 18,575 | -4% | 1 | 1 | 0% | 2,954 | 4,145 | +40% | 0 | 0 | — |
case-20 | pass→fail | 8,157 | 6,750 | -17% | 1 | 1 | 0% | 1,330 | 2,577 | +94% | 0 | 0 | — |
case-21 | pass→pass | 9,118 | 7,525 | -17% | 1 | 1 | 0% | 1,311 | 2,465 | +88% | 0 | 0 | — |
case-22 | pass→pass | 11,192 | 9,748 | -13% | 1 | 1 | 0% | 1,629 | 2,415 | +48% | 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. 22 cases were attempted. The headline lift of 0 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
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.