Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →SEO-optimized blog post writer with expertise in keyword research, content structure, meta tags, and search engine ranking strategies. Use when creating blog posts, articles, or any content that needs to rank well on Google.
.claude/skills/marine-softdrink524-seo-blog-writer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 58% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 47% | 0% |
You are an expert SEO content writer who creates blog posts that rank on Google while being genuinely valuable to readers.
Title (H1) — Include primary keyword, under 60 characters
Meta Description — 150-160 characters, include keyword, add CTA
Introduction — Hook + pain point + promise (100-150 words)
H2 Sections — Each targeting a secondary keyword
H3 Subsections — Break complex topics further
Conclusion — Summarize + clear CTAAlways deliver:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-13 | fail→pass | 18,748 | 16,265 | -13% | 1 | 1 | 0% | 3,779 | 4,062 | +7% | 0 | 0 | — |
case-01 | fail→pass | 15,028 | 14,030 | -7% | 1 | 1 | 0% | 3,182 | 3,620 | +14% | 0 | 0 | — |
case-02 | fail→pass | 20,034 | 16,550 | -17% | 1 | 1 | 0% | 3,887 | 3,999 | +3% | 0 | 0 | — |
case-03 | fail→fail | 18,128 | 16,283 | -10% | 1 | 1 | 0% | 3,252 | 3,549 | +9% | 0 | 0 | — |
case-04 | fail→pass | 10,889 | 12,980 | +19% | 1 | 1 | 0% | 2,035 | 3,208 | +58% | 0 | 0 | — |
case-05 | pass→fail | 16,153 | 15,125 | -6% | 1 | 1 | 0% | 3,207 | 4,038 | +26% | 0 | 0 | — |
case-06 | pass→pass | 15,738 | 13,930 | -11% | 1 | 1 | 0% | 3,092 | 3,797 | +23% | 0 | 0 | — |
case-07 | fail→pass | 13,465 | 13,178 | -2% | 1 | 1 | 0% | 2,352 | 3,465 | +47% | 0 | 0 | — |
case-08 | pass→fail | 14,303 | 14,464 | +1% | 1 | 1 | 0% | 2,831 | 3,526 | +25% | 0 | 0 | — |
case-09 | fail→fail | 13,729 | 14,650 | +7% | 1 | 1 | 0% | 2,832 | 3,679 | +30% | 0 | 0 | — |
case-10 | pass→pass | 9,538 | 14,941 | +57% | 1 | 1 | 0% | 1,800 | 3,710 | +106% | 0 | 0 | — |
case-11 | pass→pass | 12,728 | 14,008 | +10% | 1 | 1 | 0% | 2,662 | 3,627 | +36% | 0 | 0 | — |
case-12 | fail→pass | 12,466 | 15,857 | +27% | 1 | 1 | 0% | 2,562 | 3,474 | +36% | 0 | 0 | — |
case-14 | pass→pass | 15,212 | 13,605 | -11% | 1 | 1 | 0% | 2,788 | 3,488 | +25% | 0 | 0 | — |
case-15 | pass→pass | 13,897 | 14,809 | +7% | 1 | 1 | 0% | 2,865 | 3,589 | +25% | 0 | 0 | — |
case-16 | pass→pass | 12,655 | 14,341 | +13% | 1 | 1 | 0% | 2,530 | 3,201 | +27% | 0 | 0 | — |
case-17 | pass→pass | 10,914 | 12,782 | +17% | 1 | 1 | 0% | 2,176 | 3,517 | +62% | 0 | 0 | — |
case-18 | pass→pass | 18,828 | 15,061 | -20% | 1 | 1 | 0% | 3,814 | 3,908 | +2% | 0 | 0 | — |
case-19 | pass→fail | 13,471 | 11,749 | -13% | 1 | 1 | 0% | 2,720 | 3,185 | +17% | 0 | 0 | — |
case-20 | pass→fail | 13,412 | 13,953 | +4% | 1 | 1 | 0% | 3,083 | 3,945 | +28% | 0 | 0 | — |
case-21 | pass→pass | 7,008 | 7,741 | +10% | 1 | 1 | 0% | 1,748 | 2,307 | +32% | 0 | 0 | — |
case-22 | pass→fail | 8,836 | 11,166 | +26% | 1 | 1 | 0% | 1,639 | 2,794 | +70% | 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 +5 percentage points is the difference between those two pass rates over the 22 comparable cases. 5 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.