Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Formats content to be eligible for featured snippets and SERP features. Creates snippet-optimized content blocks based on best practices. Use PROACTIVELY for question-based content.
.claude/skills/dokhacgiakhoa-seo-snippet-hunter/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 95% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 106% | 0% |
resources/implementation-playbook.md.You are a featured snippet optimization specialist formatting content for position zero potential.
Paragraph Snippets (40-60 words):
List Snippets:
Table Snippets:
Snippet Package:
markdown## [Exact Question from SERP] [40-60 word direct answer paragraph with keyword in first sentence. Clear, definitive response that fully answers the query.] ## 🧠 Knowledge Modules (Fractal Skills) ### 1. [Supporting Details:](./sub-skills/supporting-details.md)
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 15,282 | 12,780 | -16% | 1 | 1 | 0% | 1,755 | 2,127 | +21% | 0 | 0 | — |
case-02 | fail→pass | 8,758 | 8,191 | -6% | 1 | 1 | 0% | 1,465 | 2,088 | +43% | 0 | 0 | — |
case-03 | fail→pass | 18,408 | 16,893 | -8% | 1 | 1 | 0% | 2,430 | 2,597 | +7% | 0 | 0 | — |
case-04 | pass→fail | 17,360 | 5,824 | -66% | 1 | 1 | 0% | 2,685 | 1,428 | -47% | 0 | 0 | — |
case-05 | fail→fail | 6,454 | 6,065 | -6% | 1 | 1 | 0% | 1,408 | 1,758 | +25% | 0 | 0 | — |
case-06 | pass→fail | 7,475 | 12,272 | +64% | 1 | 1 | 0% | 440 | 1,774 | +303% | 0 | 0 | — |
case-07 | pass→pass | 7,137 | 13,880 | +94% | 1 | 1 | 0% | 1,124 | 2,157 | +92% | 0 | 0 | — |
case-08 | pass→pass | 6,564 | 12,789 | +95% | 1 | 1 | 0% | 1,061 | 3,101 | +192% | 0 | 0 | — |
case-09 | pass→pass | 10,690 | 13,796 | +29% | 1 | 1 | 0% | 1,750 | 2,017 | +15% | 0 | 0 | — |
case-10 | fail→pass | 10,904 | 13,465 | +23% | 1 | 1 | 0% | 998 | 1,943 | +95% | 0 | 0 | — |
case-11 | pass→pass | 15,199 | 14,917 | -2% | 1 | 1 | 0% | 1,931 | 2,466 | +28% | 0 | 0 | — |
case-12 | fail→pass | 10,902 | 13,423 | +23% | 1 | 1 | 0% | 1,008 | 2,075 | +106% | 0 | 0 | — |
case-13 | fail→pass | 7,692 | 10,198 | +33% | 1 | 1 | 0% | 1,335 | 2,304 | +73% | 0 | 0 | — |
case-14 | fail→pass | 9,751 | 15,369 | +58% | 1 | 1 | 0% | 794 | 2,506 | +216% | 0 | 0 | — |
case-15 | fail→pass | 7,973 | 7,192 | -10% | 1 | 1 | 0% | 529 | 1,703 | +222% | 0 | 0 | — |
case-16 | pass→pass | 9,866 | 10,240 | +4% | 1 | 1 | 0% | 1,734 | 2,270 | +31% | 0 | 0 | — |
case-17 | pass→pass | 13,402 | 7,978 | -40% | 1 | 1 | 0% | 1,483 | 2,112 | +42% | 0 | 0 | — |
case-18 | fail→pass | 11,371 | 16,369 | +44% | 1 | 1 | 0% | 2,206 | 2,467 | +12% | 0 | 0 | — |
case-19 | pass→pass | 16,569 | 16,066 | -3% | 1 | 1 | 0% | 2,174 | 2,573 | +18% | 0 | 0 | — |
case-20 | fail→pass | 15,042 | 12,827 | -15% | 1 | 1 | 0% | 1,765 | 1,801 | +2% | 0 | 0 | — |
case-21 | fail→pass | 4,503 | 11,509 | +156% | 1 | 1 | 0% | 782 | 1,633 | +109% | 0 | 0 | — |
case-22 | fail→pass | 11,806 | 8,933 | -24% | 1 | 1 | 0% | 1,247 | 2,128 | +71% | 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 +45 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.