Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to design, optimize, or audit a sidebar for blogs, docs, or content pages. Also use when the user mentions "sidebar," "blog sidebar," "content sidebar," "side panel," "sidebar navigation," "related content," "sidebar CTA," "doc sidebar," or "sidebar widgets." For blog layout, use blog-page-generator.
.claude/skills/kostja94-sidebar-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 55% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -15% | 0% |
Guides sidebar design for content sites (blogs, docs). ~80% of users focus on the left; sidebars influence flow but can hurt conversion if overused. Posts without sidebars show 3.1x higher conversion; bottom-right sticky CTAs outperform sidebars (5.62% vs 0.58% CTR).
When invoking: On first use, if helpful, open with 1-2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read it for content structure and conversion goals.
Identify:
| Approach | Typical result | |----------|----------------| | Sidebar CTA | <1% opt-in for blog sidebars | | In-content CTA | 3x+ higher conversion | | Bottom-right sticky | 5.62% CTR vs 0.58% sidebar | | No sidebar | 3.1x higher conversion vs with sidebar |
Recommendation: Prefer in-content CTAs or bottom-right sticky over sidebar CTAs. Use sidebar for nav and discovery, not primary conversion.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 17,344 | 9,645 | -44% | 1 | 1 | 0% | 2,905 | 2,146 | -26% | 0 | 0 | — |
case-02 | fail→pass | 23,023 | 11,345 | -51% | 1 | 1 | 0% | 3,864 | 2,416 | -37% | 0 | 0 | — |
case-03 | fail→fail | 19,449 | 9,289 | -52% | 1 | 1 | 0% | 3,054 | 2,104 | -31% | 0 | 0 | — |
case-04 | fail→pass | 13,531 | 9,910 | -27% | 1 | 1 | 0% | 2,182 | 2,104 | -4% | 0 | 0 | — |
case-05 | pass→pass | 18,190 | 13,934 | -23% | 1 | 1 | 0% | 3,384 | 2,896 | -14% | 0 | 0 | — |
case-06 | fail→fail | 14,686 | 10,430 | -29% | 1 | 1 | 0% | 2,658 | 2,448 | -8% | 0 | 0 | — |
case-07 | fail→pass | 5,954 | 7,231 | +21% | 1 | 1 | 0% | 1,180 | 1,827 | +55% | 0 | 0 | — |
case-08 | fail→pass | 16,478 | 8,639 | -48% | 1 | 1 | 0% | 2,453 | 2,081 | -15% | 0 | 0 | — |
case-09 | pass→pass | 14,946 | 9,444 | -37% | 1 | 1 | 0% | 2,807 | 2,224 | -21% | 0 | 0 | — |
case-10 | fail→pass | 13,562 | 9,729 | -28% | 1 | 1 | 0% | 2,220 | 2,092 | -6% | 0 | 0 | — |
case-11 | fail→pass | 17,250 | 8,153 | -53% | 1 | 1 | 0% | 3,026 | 1,944 | -36% | 0 | 0 | — |
case-12 | pass→pass | 13,729 | 9,084 | -34% | 1 | 1 | 0% | 2,444 | 2,048 | -16% | 0 | 0 | — |
case-13 | pass→pass | 15,804 | 7,866 | -50% | 1 | 1 | 0% | 2,436 | 1,888 | -22% | 0 | 0 | — |
case-14 | fail→pass | 20,190 | 9,731 | -52% | 1 | 1 | 0% | 3,353 | 2,217 | -34% | 0 | 0 | — |
case-15 | fail→pass | 11,367 | 7,707 | -32% | 1 | 1 | 0% | 2,094 | 1,725 | -18% | 0 | 0 | — |
case-16 | pass→pass | 10,094 | 5,401 | -46% | 1 | 1 | 0% | 1,820 | 1,511 | -17% | 0 | 0 | — |
case-17 | fail→pass | 12,548 | 8,135 | -35% | 1 | 1 | 0% | 2,320 | 1,947 | -16% | 0 | 0 | — |
case-18 | fail→fail | 12,333 | 7,573 | -39% | 1 | 1 | 0% | 2,255 | 1,881 | -17% | 0 | 0 | — |
case-19 | fail→fail | 11,583 | 7,483 | -35% | 1 | 1 | 0% | 2,226 | 1,819 | -18% | 0 | 0 | — |
case-20 | fail→pass | 17,794 | 12,265 | -31% | 1 | 1 | 0% | 4,055 | 3,585 | -12% | 0 | 0 | — |
case-21 | pass→pass | 9,028 | 6,431 | -29% | 1 | 1 | 0% | 1,679 | 1,641 | -2% | 0 | 0 | — |
case-22 | pass→pass | 15,042 | 9,709 | -35% | 1 | 1 | 0% | 2,838 | 2,429 | -14% | 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 +50 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.