技能说明

HITL Protocol — the open standard for human decisions in autonomous agent workflows. When a website or API needs human input, it returns HTTP 202 with a review URL. Autonomous agents like OpenClaw, Claude, Codex, or Goose forward the URL, poll for the structured result, and continue. Use this skill to make any website agent-ready, or to handle human-in-the-loop responses in your agent. Covers approval, selection, input forms, confirmation, and escalation review types. Supports polling, SSE, webhook transports, channel-native inline buttons (Telegram, Slack, Discord, WhatsApp, Teams), opaque token security, multi-step form wizards, and multi-round edit cycles.


中文介绍

HITL协议——用于自主代理工作流中人工决策的开放标准。当网站或API需要人工输入时,返回HTTP 202状态码及审核链接。诸如OpenClaw、Claude、Codex或Goose等自主代理会转发该链接,轮询结构化结果后继续执行。使用此功能可使任何网站具备代理兼容性,或在你的代理中处理人工介入响应。支持审批、选择、输入表单、确认和升级审核等各类人工干预类型。支持轮询、SSE、Webhook传输、平台原生内联按钮(Telegram、Slack、Discord、WhatsApp、Teams)、不透明令牌安全机制、多步骤表单向导以及多轮编辑循环。

直接复制以下提示词,发送给你的 AI 助手即可完成安装。

帮我下载并安装这个SKILL:https://skillhub.cstcloud.cn/download/hitl-protocol

点击右上角 下载SKILL 按钮

元信息

分类:Data AI
下载:3
浏览:3
标签:
HITL Protocol human-in-the-loop agent integration