跳到正文
TakoAPI
返回技能列表

emotion-detector

由 daisuke134 提供

Coding Agents & IDEs
333下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Detects the primary emotion in text input for AI agents.

描述

该技能的功能

Detects the primary emotion in a text string and returns structured metadata: emotion type, intensity, valence, confidence score, and a recommended response strategy. Includes a safe_t_flag that triggers when critical-intensity distress signals like grief or despair are detected. Accepts English and Japanese input.

Returns a ready-to-act response_strategy alongside raw emotion data, so agents skip the step of inferring how to respond and act on a clear directive instead.

何时使用

  • Routing user messages to empathetic vs. task-focused agent responses
  • Flagging high-distress support tickets for human escalation
  • Adjusting chatbot tone based on detected user frustration
  • Filtering incoming feedback by emotional valence before summarizing
  • Triggering crisis resources when a user message shows critical grief or fear

示例工作流

输入

User asks: 'I've been feeling completely hopeless lately, nothing seems to matter anymore'

智能体
  1. 1

    Send POST request to the x402 endpoint with the user's text and language set to 'en'

  2. 2

    Receive response with primary_emotion: grief, intensity: critical, confidence: 0.95

  3. 3

    Check safe_t_flag — value is true

  4. 4

    Halt normal conversation flow

  5. 5

    Present user with crisis support resources (Crisis Text Line, いのちの電話)

输出

Agent surfaces emergency mental health resources instead of continuing the task flow

前置要求

  • USDC balance on Base mainnet (eip155:8453) — $0.01 per request
  • x402-compatible wallet for payment authorization

安装

clawhub install daisuke134/emotion-detector

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接