435 个 · 按相关度排序
Use browser-use to turn natural-language web tasks into repeatable browser automation backed by Playwright and agent loops. This skill helps an agent open sites, inspect page state, click, type, extract data, and recover from common UI changes with a real automation framework instead of brittle one-off scripts.
中文简介正在准备中。当前显示原文说明。
browser-use is an open-source Python framework for letting AI agents interact with websites through a real browser. It supports local execution, optional cloud browsers, custom tools, and a CLI for persistent browser sessions.
中文简介正在准备中。当前显示原文说明。
Browserable is an open-source, self-hostable browser automation library built for AI agents. This skill turns Browserable into a repeatable workflow for navigation, form filling, extraction, and browser-based task execution with local control instead of a hosted black box.
中文简介正在准备中。当前显示原文说明。
Browserbase MCP Server gives agents cloud browser control through Browserbase and Stagehand, with both hosted HTTP and self-hosted stdio options. It suits teams that want MCP-based browser automation but prefer Browserbase sessions and Stagehand’s action model instead of running Playwright locally.
中文简介正在准备中。当前显示原文说明。
Use Browserbase when an agent needs hosted browser sessions, remote automation, session recording, and scalable browser infrastructure without managing Chromium fleets directly. This skill packages the Browserbase API and SDK into a concrete workflow for running, monitoring, and extracting results from cloud browser sessions.
中文简介正在准备中。当前显示原文说明。
Records and replays browser sessions using rrweb recording library with DOM mutation serialization. Integrates with LogRocket API and FullStory Data Export API for session analytics.
中文简介正在准备中。当前显示原文说明。
Browserless turns Chrome, Firefox, and WebKit into a remote browser service you can self-host or consume as a managed platform. It gives automation stacks a stable WebSocket and REST surface for screenshots, PDFs, scraping, persistent sessions, and debugging without hand-managing browser fleets.
中文简介正在准备中。当前显示原文说明。
Drives headless Chrome via the Browserless.io API for scraping dynamic SPAs. Uses /content, /screenshot, and /pdf endpoints with stealth mode. Manages session tokens and concurrent connection limits.
中文简介正在准备中。当前显示原文说明。
Browsertrix Crawler is a browser-based crawling system from Webrecorder for high-fidelity site capture, QA replay analysis, and configurable crawl behavior. It runs complex crawls in a single Docker container and uses Puppeteer plus Chrome DevTools Protocol under the hood.
中文简介正在准备中。当前显示原文说明。
Bruno is an open-source, offline-first API client that stores collections as plain-text .bru files on your filesystem. It serves as a privacy-focused, git-friendly alternative to Postman and Insomnia with no cloud sync and no account required.
中文简介正在准备中。当前显示原文说明。
Uses Bubble's Plugin API and the Stripe.js SDK to embed a self-service subscription management portal inside a Bubble application. Configures Bubble's API Connector to call Stripe's Billing Portal Sessions endpoint and handles webhook events for real-time plan change updates.
中文简介正在准备中。当前显示原文说明。
Bubble Tea is a powerful Go framework for building terminal user interfaces based on The Elm Architecture. Developed by Charmbracelet, it supports inline, full-window, and mixed TUI applications with a high-performance cell-based renderer and declarative views.
中文简介正在准备中。当前显示原文说明。
Budibase is an open-source low-code platform for internal apps, forms, portals, and approvals. It gives agents a practical way to stand up operational tools on top of PostgreSQL, REST APIs, and other business data sources with self-hosted deployment options.
中文简介正在准备中。当前显示原文说明。
Let operators control local Claude Code, Codex, Cursor, Gemini CLI, and other coding agents from Slack, Discord, Telegram, Feishu/Lark, DingTalk, LINE, and WeChat Work.
中文简介正在准备中。当前显示原文说明。
Lints Protocol Buffer definitions using the Buf CLI ruleset and validates gRPC service contracts. Detects breaking changes between proto revisions using buf breaking with git integration.
中文简介正在准备中。当前显示原文说明。
Put an inline firewall and containment layer in front of agent network traffic, tool calls, and MCP traffic before you trust an agent with local secrets.
中文简介正在准备中。当前显示原文说明。
Run a repeatable evaluation suite for browser agents against static web task snapshots instead of judging them from demos or one-off tests.
中文简介正在准备中。当前显示原文说明。
Generates Blender Python (bpy) scripts that programmatically create Geometry Nodes modifier trees, using the node_groups API and GeometryNodeTree interface for parametric 3D asset generation.
中文简介正在准备中。当前显示原文说明。
Compare browser-agent reliability on a repeatable task and anti-bot suite before choosing a stack or claiming progress.
中文简介正在准备中。当前显示原文说明。
Score deep research agents on benchmark tasks using factual verification, report-quality scoring, and process evaluation before model or workflow changes ship.
中文简介正在准备中。当前显示原文说明。
Run Claude Code, Codex CLI, Gemini CLI, or OpenCode through bounded H100 post-training tasks and compare how well each agent improves a base LLM.
中文简介正在准备中。当前显示原文说明。
Automates migration from ESLint and Prettier to Biome (formerly Rome) by parsing .eslintrc and .prettierrc configs, mapping rules to biome.json equivalents, and running biome check --apply for bulk reformatting.
中文简介正在准备中。当前显示原文说明。
Use EnterpriseRAG-Bench to evaluate an enterprise RAG or knowledge-agent system against a realistic synthetic company corpus with answer, recall, and comparative scoring.
中文简介正在准备中。当前显示原文说明。
Convert a book or long document into a reusable AI mentor with source-grounded lessons, guided practice, citations, and persistent learning records.
中文简介正在准备中。当前显示原文说明。