情绪检测技能。通过分析用户输入文本特征检测情绪状态。检测维度:词汇情绪词库、否定词与程度词处理、标点符号特征、长度与重复特征。返回emotion_state/confidence/intensity。
Scanned 9/3/2026
Install to Claude Code
npx -y skills add metago-ai/metagolifeform --skill metago-emotion --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Metago Emotion?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/metago-ai-metago-emotion-bc99290b)More formats (shields.io, HTML) on the badges page.
---
name: "metago-emotion"
description: "情绪检测技能。通过分析用户输入文本特征检测情绪状态。检测维度:词汇情绪词库、否定词与程度词处理、标点符号特征、长度与重复特征。返回emotion_state/confidence/intensity。"
version: "1.0.0"
author: "MetaGO"
category: "生活服务"
platforms: ["cursor","claude-code","codex","trae","codebuddy","qoder","zcode","workbuddy","qclaw","ima"]
trigger:
- "检测我的情绪"
- "分析文本情绪"
- "情绪状态评估"
- "识别用户感受"
- "看我现在什么心情"
---
# 情绪检测(metago-emotion)
## 描述
通过分析用户输入文本特征检测情绪状态。检测维度:词汇情绪词库、否定词与程度词处理、标点符号特征、长度与重复特征。返回emotion_state/confidence/intensity。
## 触发条件
用户请求情绪检测时自动激活。用户输入中包含明显情绪倾向时自动激活。
## 核心流程
1. 接收用户输入文本
2. 词汇情绪词库匹配
3. 否定词与程度词处理
4. 标点符号特征分析
5. 长度与重复特征分析
6. 输出情绪状态评估结果
## 输出格式
返回结构化JSON,包含:
```json
{
"emotion_state": "情绪状态",
"confidence": 0.0-1.0,
"intensity": "low|medium|high"
}
```
## 根源文档
`元构全息智能引擎.txt`(metago-emotion技能定义(223-227, 371-393))
> 注:完整蓝本未随公开仓库发布,以上为出处留存备查;本技能正文已自包含全部操作定义,运行时无需读取蓝本。
## 与其他技能的协同
- 与 `metago-scene-adapt` 协同:情绪状态影响场景适配
- 与 `metago-objectivity` 协同:情绪不影响客观性判定
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...