Slack

Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Sla...

概览

This Slack skill, hosted in the vercel-labs/agent-browser repository, enables AI agents such as Codex and Claude to interact with Slack workspaces through browser automation. Rather than relying solely on API-based interactions, the skill navigates the Slack web interface to perform tasks like checking for unread notifications, searching conversation histories, and sending messages. It allows agents to extract data and manage workspace navigation directly within a browser environment. As part of a popular open-source project with over 37,000 stars, this skill provides a framework for automating routine communication workflows. It interprets natural language triggers to execute UI-based commands, facilitating seamless information retrieval and workspace management for users seeking to integrate Slack into their automated agent workflows.

使用场景

Monitoring workspaces to identify and summarize unread messages across multiple channels.
Automating the delivery of messages or data extracts to specific team members via the browser.
Searching historical Slack conversations to retrieve specific information or archived data.

安装说明

# Review source first
open https://github.com/vercel-labs/agent-browser/blob/main/skill-data/slack/SKILL.md

Copy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.

安全提示

This skill operates via browser automation, meaning actions are performed within the context of an active Slack web session. Users must ensure the host browser environment is secure and that the agent's access aligns with workspace-specific permissions and data handling policies.

相关 Skills

Constant Time Testing

trailofbits/skills

前端设计

Constant-time testing 用于检测加密代码中的定时侧信道。在审计加密实现的定时漏洞时使用。

Claude CodeClaude
securitytesting
6,810 Stars已链接来源

Baoyu Design

JimLiu/baoyu-design

前端设计

创建精美的设计产出物作为自包含的 HTML:UI 模型、交互原型、线框图、落地页、仪表板、应用界面、移动应用、幻灯片(又名 PPT / PowerPoint 演示文稿)、文档和简历、动画、3D 对象、研究报告、HTML 电子邮件、图表、传单和视觉探索。每当用户要求为界面、产品屏幕、用户流程或内容布局进行设计、制作模型、原型设计、绘制线框图、可视化、探索或制作 PPT/幻灯片时使用。

CodexClaude Code
reviewdocuments
3,534 StarsMIT

Managed Deep Agents

langchain-ai/langchain-skills

前端设计

在使用 mda CLI 在 LangSmith 中构建、测试或部署 Managed Deep Agents 时,提供 INVOKE THIS SKILL。引导用户端到端地完成其第一个智能体——通过访谈了解其构建需求,将其映射到 MDA 的实际功能,然后进行脚手架搭建和部署。涵盖基于文件的项目布局;define_deep_agent / defineDeepAgent;instructions、skills、memory、identity、tools、middleware、sandboxes、schedules、channels 以及 evals;mda init/build/dev/deploy/logs/delete;

CodexClaude
typescriptpython
1,164 Stars已链接来源

GSAP Core

mxyhi/ok-skills

前端设计

核心 API 的官方 GSAP skill —— 包含 gsap.to()、from()、fromTo()、easing、duration、stagger、defaults、gsap.matchMedia()(响应式、prefers-reduced-motion)。当用户请求 JavaScript 动画库、React/Vue/vanilla 中的动画、GSAP 补间动画、缓动、基础动画、响应式或减弱动态效果 a 时使用。

CodexClaude Code
reactsecurity
423 StarsApache-2.0

花叔Design · Huashu-Design

mxyhi/ok-skills

前端设计

花叔Design——用HTML做高保真原型、交互Demo、幻灯片、动画、设计变体探索+设计方向顾问+专家评审。根据任务embody对应专家(UX/动画师/幻灯片设计师/原型师),避免web design tropes。触发词:做原型、交互原型、HTML演示、动画Demo、设计变体、hi-fi设计、UI mockup、prototype、做个HTML页面、做个可视化、app原型、iOS原型、导出MP4/GIF、60fps视频、设计风格、设计方向、配色方案、推荐风格、选个风格、做个好看的、评审、好不好看、review this design、带解说的动画、解说视频、长视频科普、voiceover、narration、5分钟讲清楚什么是X

CodexClaude Code
pythonreact
423 StarsApache-2.0

Design Build

tinh2/skills-hub-registry

前端设计

以 Ralph Wiggum 的速度构建独特的生产级界面。交付可运行的代码(Web 或移动端),包含现代 CSS、流体排版、有意义的动效,且无通用的 AI 审美。适用场景:'build UI'、'design this'、'create interface'、'make it look good'、'build screen'、'implement design'、'frontend build'、'design build'。

CodexClaude Code
reactdesign
14 Stars已链接来源