Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.
.claude/skills/loulanyue-content-engine/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 94% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 62% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 99% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 90% | 0% |
| case-13 | ✓→✗ | ▼ Worse | 40% | 0% |
Turn one idea into strong, platform-native content instead of posting the same thing everywhere.
Clarify:
Default cascade:
When asked for a campaign, return:
Before delivering:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→fail | 15,579 | 16,441 | +6% | 1 | 1 | 0% | 2,319 | 3,383 | +46% | 0 | 0 | — |
case-01 | fail→fail | 11,357 | 12,520 | +10% | 1 | 1 | 0% | 1,779 | 2,519 | +42% | 0 | 0 | — |
case-02 | fail→fail | 9,013 | 10,649 | +18% | 1 | 1 | 0% | 1,456 | 2,226 | +53% | 0 | 0 | — |
case-04 | fail→pass | 8,716 | 12,788 | +47% | 1 | 1 | 0% | 1,290 | 2,505 | +94% | 0 | 0 | — |
case-05 | fail→fail | 15,255 | 14,109 | -8% | 1 | 1 | 0% | 2,478 | 2,784 | +12% | 0 | 0 | — |
case-06 | fail→fail | 13,815 | 13,871 | +0% | 1 | 1 | 0% | 1,874 | 2,518 | +34% | 0 | 0 | — |
case-07 | fail→pass | 7,140 | 8,764 | +23% | 1 | 1 | 0% | 1,162 | 1,882 | +62% | 0 | 0 | — |
case-08 | fail→pass | 10,128 | 17,037 | +68% | 1 | 1 | 0% | 1,531 | 3,051 | +99% | 0 | 0 | — |
case-09 | fail→fail | 6,768 | 10,441 | +54% | 1 | 1 | 0% | 1,021 | 2,069 | +103% | 0 | 0 | — |
case-10 | pass→pass | 18,932 | 16,494 | -13% | 1 | 1 | 0% | 2,755 | 2,940 | +7% | 0 | 0 | — |
case-11 | fail→pass | 5,709 | 7,221 | +26% | 1 | 1 | 0% | 914 | 1,736 | +90% | 0 | 0 | — |
case-12 | fail→fail | 11,927 | 11,488 | -4% | 1 | 1 | 0% | 2,140 | 2,443 | +14% | 0 | 0 | — |
case-13 | pass→fail | 6,827 | 6,185 | -9% | 1 | 1 | 0% | 1,006 | 1,412 | +40% | 0 | 0 | — |
case-14 | fail→fail | 5,835 | 8,187 | +40% | 1 | 1 | 0% | 856 | 1,688 | +97% | 0 | 0 | — |
case-15 | pass→pass | 17,895 | 15,181 | -15% | 1 | 1 | 0% | 2,830 | 2,987 | +6% | 0 | 0 | — |
case-16 | fail→fail | 8,418 | 11,050 | +31% | 1 | 1 | 0% | 1,303 | 2,263 | +74% | 0 | 0 | — |
case-17 | pass→pass | 7,205 | 5,758 | -20% | 1 | 1 | 0% | 1,019 | 1,362 | +34% | 0 | 0 | — |
case-18 | fail→fail | 4,236 | 6,639 | +57% | 1 | 1 | 0% | 723 | 1,673 | +131% | 0 | 0 | — |
case-19 | fail→fail | 7,489 | 9,293 | +24% | 1 | 1 | 0% | 1,119 | 1,923 | +72% | 0 | 0 | — |
case-20 | pass→pass | 13,566 | 13,089 | -4% | 1 | 1 | 0% | 2,044 | 2,598 | +27% | 0 | 0 | — |
case-21 | pass→pass | 8,828 | 6,744 | -24% | 1 | 1 | 0% | 1,672 | 1,776 | +6% | 0 | 0 | — |
case-22 | pass→pass | 14,657 | 11,189 | -24% | 1 | 1 | 0% | 2,223 | 2,204 | -1% | 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 +14 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.