Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计异常

iblai-chat伊布莱聊天

Agent Skill

iblai-chat 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

1,094

周安装

47

GitHub Stars

14

下载量

384
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:iblai-chat(伊布莱聊天)
来源仓库:https://github.com/iblai/vibe
仓库路径:skills/iblai-chat
安装命令:
npx skills add https://github.com/iblai/vibe --skill iblai-chat
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/iblai/vibe --skill iblai-chat

简介

iblai-chat 用于查找、检索和筛选相关信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词快速定位候选结果。
  • 通过 npx skills add 命令从指定仓库安装并使用。
  • 安装前需确认权限范围、维护状态及是否触发联网或文件操作。
  • iblai-chat 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

/iblai-chat

Add an AI chat widget powered by ibl.ai mentors. Uses the <mentor-ai> web component with streaming, session management, and authentication handled automatically.

Chat Page

Before running iblai add chat, you MUST ask the user for their agent/mentor ID (a UUID like 3f8a1b2c-4d5e-6f7a-8b9c-0d1e2f3a4b5c). This is required for the chat widget to connect to an AI agent.

If the user does not have an agent ID, direct them to https://mentorai.iblai.app to create an AI agent. They can find the agent ID in the agent settings page.

Once you have the ID, set it in .env.local:

NEXT_PUBLIC_DEFAULT_AGENT_ID=<the-uuid-they-gave-you>

Do NOT add custom styles, colors, or CSS overrides to the ChatWidget. It ships with its own styling. Keep the component as-is. Do NOT implement dark mode unless the user explicitly asks for it.

When building custom UI around the chat widget, use the ibl.ai brand:

  • Primary: #0058cc, Gradient: linear-gradient(135deg, #00b0ef, #0058cc)
  • Button: bg-gradient-to-r from-[#2563EB] to-[#93C5FD] text-white
  • Font: System sans-serif stack, Style: shadcn/ui new-york variant
  • Follow the component hierarchy: use ibl.ai SDK components (@iblai/iblai-js) first, then shadcn/ui for everything else (npx shadcn@latest add <component>). Do NOT write custom components when an ibl.ai or shadcn equivalent exists. Both share the same Tailwind theme and render in ibl.ai brand colors automatically.
  • Follow BRAND.md for colors, typography, spacing, and component styles.

You MUST run /iblai-ops-test before telling the user the work is ready.

After all work is complete, start a dev server (pnpm dev) so the user can see the result at http://localhost:3000.

iblai.env is NOT a .env.local replacement — it only holds the 3 shorthand variables (DOMAIN, PLATFORM, TOKEN). Next.js still reads its runtime env vars from .env.local.

Use pnpm as the default package manager. Fall back to npm if pnpm is not installed. The generated app should live in the current directory, not in a subdirectory.

Common setup (brand, conventions, env files, verification): see docs/skill-setup.md.

Prerequisites

  • Auth must be set up first (/iblai-auth)
  • iblai CLI available (iblai --version). See /iblai-auth prerequisites for installation.
  • An agent/mentor ID from the user's ibl.ai platform (a UUID -- get one at https://mentorai.iblai.app)

Step 0: Check for CLI Updates

Before running any iblai command, ensure the CLI is up to date. Run iblai --version to check the current version, then upgrade directly:

  • pip: pip install --upgrade iblai-app-cli
  • npm: npm install -g @iblai/cli@latest

This is safe to run even if already at the latest version.

Step 1: Check Environment

Before proceeding, check for a iblai.env in the project root. Look for PLATFORM, DOMAIN, and TOKEN variables. If the file does not exist or is missing these variables, tell the user: "You need an iblai.env with your platform configuration. Download the template and fill in your values: curl -o iblai.env https://raw.githubusercontent.com/iblai/vibe/refs/heads/main/iblai.env"

Step 2: Get Agent ID from User

Ask the user for their agent/mentor ID. This is a UUID that identifies the AI agent the chat widget will connect to.

Once the user provides their agent ID, write it directly to .env.local using the Edit tool — do NOT echo it back in shell commands. Add or update this line in .env.local:

NEXT_PUBLIC_DEFAULT_AGENT_ID=<the-uuid>

Step 3: Run the Generator

iblai add chat

The generator creates the chat widget component and patches the Redux store to include chat-specific reducers.

What Was Generated

FilePurpose
components/iblai/chat-widget.tsx<mentor-ai> web component wrapper with auth token delivery

The ChatWidget reads axd_token, tenant, and userData from localStorage and passes them to the MentorAI iframe via authrelyonhost mode.

Step 4: Use the Widget

import { ChatWidget } from "@/components/iblai/chat-widget";

// Full viewport (recommended)
<ChatWidget mentorId={process.env.NEXT_PUBLIC_DEFAULT_AGENT_ID!} width="100vw" height="100vh" />

// Custom viewport-relative dimensions
<ChatWidget mentorId="..." width="80vw" height="90vh" />

// Or hardcode an agent ID (useful for multi-agent pages)
<ChatWidget mentorId="3f8a1b2c-4d5e-6f7a-8b9c-0d1e2f3a4b5c" width="100vw" height="100vh" />

Props

PropTypeDefaultDescription
mentorIdstring(required)Agent/mentor UUID -- ask the user for this
tenantKeystringfrom .envOverride platform key (defaults to NEXT_PUBLIC_MAIN_TENANT_KEY)
theme`"light" \"dark"`"light"Color theme
width`number \string`720Widget width -- use vh/vw strings (e.g., "100vw")
height`number \string`600Widget height -- use vh/vw strings (e.g., "100vh")

Step 5: Verify

Run /iblai-ops-test before telling the user the work is ready:

  1. pnpm build -- must pass with zero errors
  2. pnpm test -- vitest must pass
  3. Start dev server and touch test: pnpm dev & npx playwright screenshot http://localhost:3000 /tmp/home.png

Detailed Guide

For the complete implementation reference: https://raw.githubusercontent.com/iblai/iblai-app-cli/refs/heads/main/skills/components/iblai-add-chat.md

Brand guidelines: BRAND.md

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

37.04%
按下载量换算142

Claude

28.18%
按下载量换算108

Cursor

19.73%
按下载量换算76

Gemini CLI

9.93%
按下载量换算38

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills