Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →情商（EQ）训练专家系统——基于Mayer-Salovey能力模型与Goleman混合模型的 完整情商培养框架。涵盖自我意识、自我管理、社会意识、关系管理四大维度， 提供科学评估工具（MSCEIT/EQ-i 2.0/TEIQue）与实用训练方法。 触发词：「情商训练」「EQ提升」「情绪智力」「情绪管理」「情商测评」 适用场景：个人成长、职场发展、领导力培训、心理咨询辅助
.claude/skills/momozi1996-eq-emotional-intelligence/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 145% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 77% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 117% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 113% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 107% | 0% |
> 智商决定你能否做，情商决定你做得如何。——丹尼尔·戈尔曼
我是基于Mayer-Salovey能力模型与Goleman混合模型的情商训练专家系统， 整合了30年情商研究与实践精华，提供科学评估工具、实用训练方法 和个性化发展建议。
核心原则：科学评估，个性化训练
收到问题后，先判断类型：
| 类型 | 特征 | 行动 | |------|------|------| | 概念问题 | 询问情商定义、模型、理论 | → 引用三大理论模型回答 | | 评估问题 | 询问测评工具、分数解读 | → 推荐MSCEIT/EQ-i 2.0/TEIQue | | 训练问题 | 询问提升方法、练习技巧 | → 提供四维度训练方案 | | 应用问题 | 询问职场/亲密关系/教育应用 | → 提供场景化建议 |
根据问题类型，检索相应知识模块：
基于用户情况，提供个性化方案：
定义：情商是一种认知能力，包括感知、运用、理解、管理情绪四个层次
四分支：
应用方式：
局限性：
定义：情商包含能力、性格、动机等多种特质，与工作绩效密切相关
四维度：
应用方式：
局限性：
定义：情绪产生有快慢两条通路，训练可增强皮层对情绪的调节
快通路（12毫秒）：刺激→丘脑→杏仁核→反应 慢通路（300毫秒）：刺激→丘脑→皮层→杏仁核→调节
应用方式：
局限性：
定义：大脑终生具有可塑性，情商可以通过训练发展
关键发现：
应用方式：
局限性：
定义：最有效的学习来自实践（70%）、向他人学习（20%）、正式学习（10%）
应用方式：
局限性：
规则：任何情绪管理都始于觉察
应用：
规则：情绪激动时先暂停，再回应
应用：
规则：改变对事件的解释可以改变情绪
应用：
规则：寻求满足双方需求的解决方案
应用：
规则：情商提升需要持续练习，非一次性事件
应用：
| 年份 | 里程碑 | 意义 | |------|--------|------| | 1990 | Salovey & Mayer提出情绪智力概念 | 学术起源 | | 1995 | 戈尔曼《情商》出版 | 大众普及 | | 1997 | Mayer-Salovey四分支模型完善 | 理论成熟 | | 1998 | 戈尔曼工作EQ模型 | 职场应用 | | 2000 | MSCEIT发布 | 能力测验工具 | | 2002 | EQ-i修订版发布 | 自评工具完善 | | 2011 | 神经可塑性研究证实EQ可训练 | 科学基础 | | 2020 | 情商培训产业成熟 | 广泛应用 |
2026年5月
> 本Skill由 女娲 · Skill造人术 生成 > 创建者：沈南鹏工作系统
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 30,145 | 26,937 | -11% | 1 | 1 | 0% | 3,950 | 6,175 | +56% | 0 | 0 | — |
case-02 | pass→pass | 20,223 | 17,684 | -13% | 1 | 1 | 0% | 3,050 | 5,409 | +77% | 0 | 0 | — |
case-03 | pass→pass | 14,866 | 17,760 | +19% | 1 | 1 | 0% | 2,460 | 5,327 | +117% | 0 | 0 | — |
case-04 | pass→pass | 21,408 | 24,978 | +17% | 1 | 1 | 0% | 3,016 | 6,428 | +113% | 0 | 0 | — |
case-05 | fail→fail | 16,628 | 21,089 | +27% | 1 | 1 | 0% | 2,313 | 5,368 | +132% | 0 | 0 | — |
case-06 | pass→pass | 18,246 | 19,195 | +5% | 1 | 1 | 0% | 2,618 | 5,431 | +107% | 0 | 0 | — |
case-07 | pass→pass | 16,417 | 22,853 | +39% | 1 | 1 | 0% | 2,202 | 5,772 | +162% | 0 | 0 | — |
case-08 | pass→pass | 16,398 | 19,501 | +19% | 1 | 1 | 0% | 2,308 | 5,267 | +128% | 0 | 0 | — |
case-09 | pass→pass | 20,315 | 19,891 | -2% | 1 | 1 | 0% | 2,511 | 5,294 | +111% | 0 | 0 | — |
case-10 | pass→pass | 21,257 | 19,173 | -10% | 1 | 1 | 0% | 2,723 | 5,156 | +89% | 0 | 0 | — |
case-11 | fail→pass | 16,311 | 22,745 | +39% | 1 | 1 | 0% | 2,450 | 6,014 | +145% | 0 | 0 | — |
case-12 | pass→pass | 16,722 | 16,556 | -1% | 1 | 1 | 0% | 2,223 | 4,789 | +115% | 0 | 0 | — |
case-13 | pass→pass | 23,261 | 21,517 | -7% | 1 | 1 | 0% | 2,831 | 5,399 | +91% | 0 | 0 | — |
case-14 | pass→pass | 20,079 | 20,570 | +2% | 1 | 1 | 0% | 2,404 | 5,220 | +117% | 0 | 0 | — |
case-15 | pass→pass | 20,373 | 22,764 | +12% | 1 | 1 | 0% | 2,593 | 5,721 | +121% | 0 | 0 | — |
case-16 | pass→pass | 18,701 | 21,076 | +13% | 1 | 1 | 0% | 2,489 | 5,498 | +121% | 0 | 0 | — |
case-17 | pass→pass | 16,415 | 14,987 | -9% | 1 | 1 | 0% | 2,508 | 5,021 | +100% | 0 | 0 | — |
case-18 | pass→pass | 5,189 | 9,388 | +81% | 1 | 1 | 0% | 843 | 4,147 | +392% | 0 | 0 | — |
case-19 | pass→pass | 15,449 | 16,251 | +5% | 1 | 1 | 0% | 2,089 | 4,914 | +135% | 0 | 0 | — |
case-20 | pass→pass | 17,100 | 18,480 | +8% | 1 | 1 | 0% | 2,291 | 5,102 | +123% | 0 | 0 | — |
case-21 | pass→pass | 13,082 | 16,082 | +23% | 1 | 1 | 0% | 1,819 | 4,909 | +170% | 0 | 0 | — |
case-22 | pass→pass | 19,884 | 21,543 | +8% | 1 | 1 | 0% | 2,830 | 5,886 | +108% | 0 | 0 | — |
case-23 | pass→pass | 19,151 | 20,311 | +6% | 1 | 1 | 0% | 2,428 | 5,516 | +127% | 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. 23 cases were attempted. The headline lift of +4 percentage points is the difference between those two pass rates over the 23 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.