agent

Neon Serverless Postgres 使用指南与最佳实践。涵盖入门、使用 Neon 进行本地开发、选择连接方式、Neon……

使用 Chrome DevTools MCP 进行专家级的浏览器自动化、调试与性能分析。用于与网页交互、截取屏幕截图、…

使用 Midscene 实现视觉驱动的桌面自动化。通过自然语言指令控制你的桌面。完全基于屏幕截图运行——无需 DOM 或无障碍标签。能够与屏幕上所有可见元素进行交互，不受技术栈限制。⚠️ 会接管用户真实的鼠标和键盘。对于 Web 应用，请优先选择“浏览器自动化”。仅适用于无法在浏览器中运行的桌面原生应用（Electron、Qt、macOS/Windows/Linux 原生应用）。触发词：打开应用、按下按键、desktop、computer、点击屏幕、输入文本、截取桌面、启动应用、切换窗口、桌面自动化、控制电脑、鼠标点击、键盘快捷键、屏幕截图、在屏幕上查找、读取屏幕、验证窗口、关闭应用、测试 Electron 应用。由 Midscene.js (https://midscenejs.com) 提供支持

将 GitHub、Linear、桌面提醒、Webhook 以及已连接的通讯平台上的通知，作为统一的 ECC 原生工作流进行操作。适用于真正的问题……

使用 Convex Agent 组件构建 AI 智能体，包括线程管理、工具集成、流式响应、RAG 模式和工作流编排

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web…

Vision-driven browser automation using Midscene Bridge mode. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visible elements on screen regardless of technology stack. Connects to the user's desktop Chrome browser via the Midscene Chrome Extension, preserving cookies, sessions, and login state. Does NOT take over the user's mouse or keyboard — operates through Chrome DevTools Protocol. Use this skill when the user wants to: - Browse, navigate, or open web pages in the user's own Chrome browser - Interact with pages that require login sessions, cookies, or existing browser state - Scrape, extract, or collect data from websites using the user's real browser - Fill out forms, click buttons, or interact with web elements - Verify, validate, test, or QA frontend UI behavior - Take screenshots of web pages - Automate multi-step web workflows - Test what was just built, validate the UI in real browser Powered by Midscene.js (https://midscenejs.com)

Reference skill for Zoom Virtual Agent. Use after routing to a virtual-agent workflow when implementing web embeds, Android or iOS wrapper integrations,…

Rslib best practices for config, CLI workflow, output, declaration files, dependency handling, build optimization and toolchain integration. Use when writing,…

Forge website capabilities into reusable Skills via browser automation. Three core uses: (1) CREATE Skills — when user says 'create/make/build/forge/generate a…

Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows

Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform

Execute sensitive browser actions (login, payments, form filling) outside the core agent loop using a dedicated CLI tool. Use when Claude needs to handle…

Checks async races, thread safety, TOCTOU, deadlocks, blocking I/O, resource contention. Use when auditing concurrency safety.

Checks blocking IO in async, unnecessary allocations, sync sleep, string concat in loops, redundant copies. Use when auditing runtime performance.

Databricks Lakebase Postgres: projects, scaling, connectivity, Lakebase synced tables, and Data API. Use when asked about Lakebase databases, OLTP storage, or…

Guides structured 4-stage experiment execution with attempt budgets and gate conditions: Stage 1 initial implementation (reproduce baseline), Stage 2…

Grafana Cloud AI and ML features — Grafana Assistant (natural language queries, dashboard generation, incident investigations), Dynamic Alerting (ML forecasting and outlier detection), Sift (automated root cause analysis with 8 analysis types), Knowledge Graph (entity discovery and RCA Workbench), and the LLM Plugin (OpenAI/Anthropic/Azure integration). Use when setting up AI-powered alerting, using natural language to query metrics/logs, automating incident investigation, or integrating LLMs with Grafana panels and workflows.

browser-scrape — an installable skill for AI agents, published by ruvnet/ruflo.

Use when installing or verifying this marketplace in Claude and Codex, aligning selected plugins, MCP settings, and Codex execution defaults.