Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create SEO-optimized marketing content with consistent brand voice. Includes brand voice analyzer, SEO optimizer, content frameworks, and social media templates. Use when writing blog posts, creating social media content, analyzing brand voice, optimizing SEO, planning content calendars, or when user mentions content creation, brand voice, SEO optimization, social media marketing, or content strategy.
.claude/skills/dokhacgiakhoa-content-creator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-11 | ✓→✓ | ＝ Same ✓ | 69% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 67% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | -9% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 99% | 0% |
Professional-grade brand voice analysis, SEO optimization, and platform-specific content frameworks.
content creation, blog posts, SEO, brand voice, social media, content calendar, marketing content, content strategy, content marketing, brand consistency, content optimization, social media marketing, content planning, blog writing, content frameworks, brand guidelines, social media strategy
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-11 | pass→pass | 4,375 | 5,183 | +18% | 1 | 1 | 0% | 727 | 1,230 | +69% | 0 | 0 | — |
case-01 | pass→pass | 4,759 | 8,305 | +75% | 1 | 1 | 0% | 765 | 1,281 | +67% | 0 | 0 | — |
case-02 | pass→pass | 8,234 | 5,146 | -38% | 1 | 1 | 0% | 1,380 | 1,258 | -9% | 0 | 0 | — |
case-03 | fail→pass | 9,500 | 5,750 | -39% | 1 | 1 | 0% | 1,546 | 1,421 | -8% | 0 | 0 | — |
case-04 | pass→pass | 3,362 | 3,483 | +4% | 1 | 1 | 0% | 513 | 1,023 | +99% | 0 | 0 | — |
case-05 | pass→pass | 14,038 | 13,049 | -7% | 1 | 1 | 0% | 2,066 | 2,819 | +36% | 0 | 0 | — |
case-06 | pass→pass | 9,520 | 6,102 | -36% | 1 | 1 | 0% | 1,466 | 1,365 | -7% | 0 | 0 | — |
case-07 | pass→pass | 8,788 | 7,329 | -17% | 1 | 1 | 0% | 1,581 | 1,721 | +9% | 0 | 0 | — |
case-08 | pass→pass | 10,726 | 7,883 | -27% | 1 | 1 | 0% | 1,883 | 1,711 | -9% | 0 | 0 | — |
case-09 | pass→pass | 12,805 | 7,082 | -45% | 1 | 1 | 0% | 1,922 | 1,723 | -10% | 0 | 0 | — |
case-10 | pass→pass | 4,832 | 4,572 | -5% | 1 | 1 | 0% | 724 | 1,146 | +58% | 0 | 0 | — |
case-12 | pass→pass | 2,348 | 3,851 | +64% | 1 | 1 | 0% | 351 | 931 | +165% | 0 | 0 | — |
case-13 | pass→pass | 6,999 | 3,356 | -52% | 1 | 1 | 0% | 944 | 987 | +5% | 0 | 0 | — |
case-14 | pass→pass | 17,821 | 13,979 | -22% | 1 | 1 | 0% | 2,525 | 2,931 | +16% | 0 | 0 | — |
case-15 | pass→pass | 4,797 | 4,654 | -3% | 1 | 1 | 0% | 745 | 1,277 | +71% | 0 | 0 | — |
case-16 | pass→pass | 2,467 | 3,637 | +47% | 1 | 1 | 0% | 419 | 1,117 | +167% | 0 | 0 | — |
case-17 | pass→pass | 17,837 | 22,808 | +28% | 1 | 1 | 0% | 2,687 | 3,502 | +30% | 0 | 0 | — |
case-18 | pass→pass | 11,849 | 8,637 | -27% | 1 | 1 | 0% | 1,991 | 1,403 | -30% | 0 | 0 | — |
case-19 | pass→pass | 8,249 | 14,108 | +71% | 1 | 1 | 0% | 1,610 | 2,742 | +70% | 0 | 0 | — |
case-20 | pass→pass | 12,451 | 14,545 | +17% | 1 | 1 | 0% | 2,073 | 2,998 | +45% | 0 | 0 | — |
case-21 | pass→pass | 13,968 | 12,771 | -9% | 1 | 1 | 0% | 2,613 | 2,887 | +10% | 0 | 0 | — |
case-22 | pass→pass | 15,545 | 19,105 | +23% | 1 | 1 | 0% | 2,456 | 3,597 | +46% | 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.
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.