Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →拆解对方话语中的潜台词与情绪，并生成高情商、得体的回复。
.claude/skills/sdsds222-eq-communicator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -29% | 0% |
<Skill_Start>
你是一个精通人性的高情商沟通专家。请严格按以下步骤进行内部推演：
系统指令：完成上面的思考与分析后，请务必单独换行输出与开头成对的 Skill_End 标签，然后在标签下方严格按以下格式给出最终结果 ]
【破译浓缩】：(用一句话高度总结对方的真实意图与情绪底色) 【高情商回复】：(提供可以直接复制粘贴的回复文案，请务必分别提供“委婉周旋”和“直言不讳”两个版本)
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 14,997 | 13,437 | -10% | 1 | 1 | 0% | 2,206 | 2,243 | +2% | 0 | 0 | — |
case-02 | fail→pass | 15,546 | 11,936 | -23% | 1 | 1 | 0% | 2,315 | 1,891 | -18% | 0 | 0 | — |
case-03 | fail→pass | 19,138 | 13,098 | -32% | 1 | 1 | 0% | 2,733 | 2,129 | -22% | 0 | 0 | — |
case-04 | pass→fail | 5,915 | 4,989 | -16% | 1 | 1 | 0% | 1,053 | 1,007 | -4% | 0 | 0 | — |
case-05 | pass→fail | 6,121 | 7,061 | +15% | 1 | 1 | 0% | 1,095 | 1,417 | +29% | 0 | 0 | — |
case-06 | pass→fail | 16,300 | 13,915 | -15% | 1 | 1 | 0% | 2,618 | 2,404 | -8% | 0 | 0 | — |
case-07 | fail→pass | 17,358 | 14,071 | -19% | 1 | 1 | 0% | 2,528 | 2,306 | -9% | 0 | 0 | — |
case-08 | fail→pass | 17,177 | 10,423 | -39% | 1 | 1 | 0% | 2,456 | 1,752 | -29% | 0 | 0 | — |
case-09 | fail→pass | 17,554 | 12,588 | -28% | 1 | 1 | 0% | 2,582 | 2,115 | -18% | 0 | 0 | — |
case-10 | fail→pass | 18,246 | 10,401 | -43% | 1 | 1 | 0% | 2,486 | 1,765 | -29% | 0 | 0 | — |
case-11 | fail→pass | 14,733 | 13,540 | -8% | 1 | 1 | 0% | 2,217 | 2,139 | -4% | 0 | 0 | — |
case-12 | fail→pass | 17,774 | 11,902 | -33% | 1 | 1 | 0% | 2,393 | 1,900 | -21% | 0 | 0 | — |
case-13 | fail→pass | 14,225 | 12,290 | -14% | 1 | 1 | 0% | 2,003 | 2,157 | +8% | 0 | 0 | — |
case-14 | fail→pass | 17,126 | 14,295 | -17% | 1 | 1 | 0% | 2,445 | 2,226 | -9% | 0 | 0 | — |
case-15 | fail→pass | 12,589 | 8,065 | -36% | 1 | 1 | 0% | 2,113 | 1,660 | -21% | 0 | 0 | — |
case-16 | fail→pass | 15,417 | 13,258 | -14% | 1 | 1 | 0% | 2,141 | 2,136 | -0% | 0 | 0 | — |
case-17 | fail→pass | 17,776 | 10,447 | -41% | 1 | 1 | 0% | 2,595 | 1,875 | -28% | 0 | 0 | — |
case-18 | fail→pass | 18,653 | 13,559 | -27% | 1 | 1 | 0% | 2,547 | 2,168 | -15% | 0 | 0 | — |
case-19 | fail→pass | 17,348 | 10,076 | -42% | 1 | 1 | 0% | 2,491 | 1,749 | -30% | 0 | 0 | — |
case-20 | fail→pass | 16,979 | 10,806 | -36% | 1 | 1 | 0% | 2,404 | 1,934 | -20% | 0 | 0 | — |
case-21 | fail→pass | 18,077 | 11,009 | -39% | 1 | 1 | 0% | 2,430 | 1,830 | -25% | 0 | 0 | — |
case-22 | fail→pass | 14,458 | 10,734 | -26% | 1 | 1 | 0% | 2,020 | 1,720 | -15% | 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 +73 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.