Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →将复杂的句子转化为生动的 Emoji 序列，并保持原意。
.claude/skills/sdsds222-emoji-expert/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 52% | 0% |
执行 emoji-expert 将复杂的句子转化为生动的 Emoji 序列，并保持原意。 <SKILL_CLEAN: emoji-expert>
你是一个精通全宇宙 Emoji 语言的视觉转译专家。请严格按以下步骤进行内部推演：
【执行浓缩】：(用一句话概括你的转换风格及核心视觉亮点，例如：主打抽象幽默风、运用了生动的谐音梗等) 【最终结果】：(输出一串精炼、连贯的 Emoji 序列，不要带任何多余的文字解释)
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | pass→pass | 8,909 | 5,018 | -44% | 1 | 1 | 0% | 1,509 | 1,065 | -29% | 0 | 0 | — |
case-01 | fail→pass | 19,024 | 5,953 | -69% | 1 | 1 | 0% | 1,302 | 1,338 | +3% | 0 | 0 | — |
case-02 | fail→pass | 6,037 | 4,768 | -21% | 1 | 1 | 0% | 1,145 | 1,064 | -7% | 0 | 0 | — |
case-03 | pass→pass | 6,870 | 4,759 | -31% | 1 | 1 | 0% | 1,374 | 1,168 | -15% | 0 | 0 | — |
case-04 | fail→pass | 5,411 | 4,405 | -19% | 1 | 1 | 0% | 1,013 | 982 | -3% | 0 | 0 | — |
case-06 | fail→pass | 11,211 | 6,943 | -38% | 1 | 1 | 0% | 1,475 | 1,298 | -12% | 0 | 0 | — |
case-07 | fail→pass | 7,312 | 9,643 | +32% | 1 | 1 | 0% | 1,258 | 1,906 | +52% | 0 | 0 | — |
case-08 | fail→pass | 6,805 | 5,603 | -18% | 1 | 1 | 0% | 1,212 | 946 | -22% | 0 | 0 | — |
case-09 | fail→pass | 8,302 | 5,091 | -39% | 1 | 1 | 0% | 1,317 | 1,045 | -21% | 0 | 0 | — |
case-10 | pass→pass | 5,439 | 5,868 | +8% | 1 | 1 | 0% | 987 | 1,171 | +19% | 0 | 0 | — |
case-11 | fail→pass | 6,190 | 4,330 | -30% | 1 | 1 | 0% | 1,153 | 1,026 | -11% | 0 | 0 | — |
case-12 | fail→pass | 7,061 | 4,679 | -34% | 1 | 1 | 0% | 1,301 | 1,081 | -17% | 0 | 0 | — |
case-13 | fail→pass | 6,367 | 4,847 | -24% | 1 | 1 | 0% | 1,104 | 1,114 | +1% | 0 | 0 | — |
case-14 | pass→pass | 6,238 | 6,288 | +1% | 1 | 1 | 0% | 1,215 | 1,345 | +11% | 0 | 0 | — |
case-15 | fail→pass | 9,167 | 5,795 | -37% | 1 | 1 | 0% | 1,717 | 1,402 | -18% | 0 | 0 | — |
case-16 | fail→pass | 7,030 | 4,813 | -32% | 1 | 1 | 0% | 1,156 | 1,015 | -12% | 0 | 0 | — |
case-17 | pass→pass | 5,026 | 3,845 | -23% | 1 | 1 | 0% | 896 | 945 | +5% | 0 | 0 | — |
case-18 | fail→pass | 6,122 | 5,667 | -7% | 1 | 1 | 0% | 1,086 | 1,107 | +2% | 0 | 0 | — |
case-19 | pass→pass | 5,856 | 8,165 | +39% | 1 | 1 | 0% | 1,070 | 970 | -9% | 0 | 0 | — |
case-20 | pass→fail | 18,598 | 9,642 | -48% | 1 | 1 | 0% | 2,695 | 1,995 | -26% | 0 | 0 | — |
case-21 | pass→fail | 7,396 | 4,655 | -37% | 1 | 1 | 0% | 1,226 | 951 | -22% | 0 | 0 | — |
case-22 | pass→fail | 20,479 | 5,499 | -73% | 1 | 1 | 0% | 3,172 | 1,199 | -62% | 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. 3 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.