lp-sourc-nbs-v1：猎聘 Agent 化寻源流水线 Skill
lp-sourc-nbs-v1 是 SkillHub 社区 Skill（@user_38ce330a/lp-sourc-nbs-v1，v1.0.0），面向猎聘雇主侧自动化寻源：通过 Playwright 与多进程 runtime（JD-Worker、Browser-Worker、Resume-Worker、Orchestrator）完成搜索、LLM 评估与「立即沟通」。文章说明安装命令、环境变量、criteria.json 字段及 jd_search_and_communicate.py 提交流程，并提示 requires_api_key、会话持久化与合规使用限制。
Read More咸鱼之王之沛神：闲鱼多店铺批量上货的 Agent Skill
咸鱼之王之沛神（@user_f847d9d9/xianyu-automation，v1.0.1）是 SkillHub 社区 business-ops 技能，面向闲鱼电商全自动上货。支持从总上货.txt 解析标题、文案、图片、价格与网盘链接，按当天日期筛选待上架商品并跳过已发布条目，以 Python 与 Playwright CDP 驱动浏览器发布，涵盖自动发货、售罄上架与 2 人小刀 0.88 等能力；双店铺模式支持省钱小喵咪、阿毛学弟，并可配置周一至六上午 10 点定时任务。标签 requires_api_key=false。可通过 skillhub install 安装到 Cursor 等 Agent 的 skills 目录，或按官方提示词让 AI 依据 skillhub.md 完成安装。
Read More浏览器自动化脚本生成器：用自然语言产出 Playwright 风格 Python 脚本
浏览器自动化脚本生成器（@user_f28fdad8/oc-browser-auto）是 SkillHub 社区 dev-programming 类 Skill，v1.0.0，无需 API Key。它根据登录、导航、表单、爬虫等场景的操作描述，引导 Agent 输出基于 Playwright 语法模板的 Python（.py）脚本。安装可参照 skillhub.cn/install/skillhub.md，用 skillhub install 并 --dir 指向 Cursor 等客户端的 skills 目录。适合需要快速搭脚本又愿在本地补全参数与合规评估的开发者。
Read More知乎抓取.skill：收藏夹到正文 Markdown 的 Agent 抓取流程
知乎抓取.skill（@user_9610c87f/zhihu-fetch-skill，v2.2.0）是 SkillHub 社区数据分析类 Skill，无需 API Key。它通过 python scripts/zhihu.py 统一处理收藏夹、专栏、个人页与问题页链接，API 与 Playwright 多级降级拉取 Markdown 正文与本地图片，Cookie 持久化保活，batch 断点续传，并可写入 Obsidian 的知乎收藏与知乎笔记目录。文章说明 SkillHub 安装命令、依赖准备及 route、collection、batch、obsidian 等典型流程与使用注意。
Read More抖音全类型自动发布：在 Agent 里打通文章、图文与视频发布
SkillHub 社区 Skill「抖音全类型自动发布」（@user_f4e1eca6/douyin-publish-article，v4.0.0）面向 creator.douyin.com，覆盖文章、图文、视频三类发布。文章经 douyin-publish.cjs 与 Playwright 一键走 8 步；图文、视频按 SKILL.md 分 10 步、8 步浏览器操作，支持话题、配乐（文章/图文）、自主声明与定时。依赖 OpenClaw CDP Chrome（127.0.0.1:18800）与创作者登录态，requires_api_key=false。安装见 skillhub.cn/install/skillhub.md，示例：skillhub install 并指定 Cursor/Claude 的 skills 目录。
Read More抖音视频提取文案：本地 Playwright + Whisper 把分享链接转成文字
介绍 SkillHub 社区 Skill「抖音视频提取文案」（@user_6a36b82b/douyin-transcribe-lz，v1.1.1）。当用户提供 v.douyin.com、douyin.com、iesdouyin.com 链接或整段分享口令，并提出提取文案、视频转文字、语音转录或「这个视频说了什么」等意图时，Agent 应启用该 Skill。底层用 Playwright 绕过登录墙捕获视频，Whisper medium 本地转录中文，无需云端 API，requires_api_key=false。文中说明 skillhub CLI 安装命令、各客户端 skills 目录及典型对话示例。
Read More浏览器自动化助手：把网页操作写成可执行的 Agent 指南
浏览器自动化助手（@user_c562f70c/browser-auto）是 SkillHub 社区 Skill，版本 1.0.0，面向 Agent 提供点击、表单、截图、多标签、登录、上传下载与数据抓取等流程指引，适用于 OpenClaw、Playwright、Selenium。文章说明其定位、能力与 SkillHub CLI 安装方式（含 Cursor、Claude Code 等 skills 目录），并给出安装后通过对话引用的典型起步步骤。无需 API Key。
Read More网页抓取与内容理解：多策略级联的网页采集与理解 Skill
SkillHub 社区 Skill「网页抓取与内容理解」（@user_f12a44b7/self-dev-web-scraper，v1.0.7）面向公开网页的正文与元数据采集。它从轻量 HTTP 起步，按需回退到 HTML 解析与 Playwright 渲染，并集成新闻检测、样板移除、结构化元数据提取与 LLM 实体识别。安装方式为按 skillhub.md 安装坐标包；通过「抓取网页」「批量爬取」等自然语言触发。不适用登录站（需自配 Cookie/Session）、API 文档站与大文件下载。
Read More基金实时估值抓取：用持仓加权推算盘中预计涨跌幅
基金实时估值抓取是 SkillHub 社区 data-analysis 类 Skill（v1.0.2，@user_516b4287/fund-realtime-scraper）。在用户需要查询基金实时估值或预计涨跌时使用 Playwright 访问同花顺爱基金 fund.10jqka.com.cn，抓取重仓持股实时数据并按持仓加权计算预计涨跌幅，支持单只与批量查询，无需 API Key。安装方式为按 skillhub.cn/install/skillhub.md 安装该坐标。适合对话中自然语言查估值，需注意结果为估算且依赖第三方页面。
Read More浏览器自动化工具箱：难抓站点的多方案降级 Skill
浏览器自动化工具箱（Browser Automation Toolbox）是 SkillHub 社区 Skill，坐标 @user_7495c5ed/browser-automation-toolbox，v2.0.11，分类 data-analysis。它提供 CloakBrowser、browser-act、Kimi WebBridge、Playwright 四套爬虫自动降级，以及 BrowserSkill 互补自动化，面向反爬难站、SPA 滚动、登录与验证码人工接管、AI 平台自动化等场景。安装需 SkillHub CLI，使用 skillhub install 并 --dir 指向 Agent 的 skills 目录（如 Cursor 的 ~/.cursor/skills/）。requires_api_key=false。
Read More企微文档读写全能小助手：用 MCP 读写 doc.weixin.qq.com
介绍 SkillHub 社区技能 @user_5f5835e5/wecom-doc-skill（v1.0.17）：内置企业微信文档 MCP 服务与 setup.sh，无需 git clone。说明 Node 18+、Playwright 扫码登录，以及 wecom_doc_fetch/write 等工具对 doc、sheet、smartsheet、slide、mindmap、flowchart 的读写能力；给出 skillhub install、~/wecom-doc-mcp 安装与 Cursor 等 MCP 配置路径及典型用法。
Read Moretest-framework-migration-skill: Migrating E2E Tests Across Selenium, Playwright, Puppeteer, and Cypress
test-framework-migration-skill is maintained by TestMu AI, is located in the LambdaTest/agent-skills repository, and is designed for AI assistants such as Cursor to migrate E2E tests across Selenium, Playwright, Puppeteer, and Cypress. The skill follows a five-step process to identify the source and target frameworks and languages, enforces reading reference mapping documents before rewriting locators, waits, assertions, and lifecycle, and includes Gotchas and a validation checklist. It supports 10 migration direction pairs and can be installed with npx agentskillsforall. MIT licensed, version 1.0.
Read Moreplaywright-skill: Generating Production-Ready Playwright E2E Tests
playwright-skill is an Agent Skill maintained by TestMu AI under the MIT license, designed to generate production-grade Playwright E2E and automation scripts in TypeScript, JavaScript, Python, Java, and C#. Before writing code, it distinguishes between local and TestMu AI cloud environments (3,000+ browser/OS combinations and real devices), defaults to TypeScript, and follows conventions for web-first assertions, selector priority, and the Page Object Model when there are more than three test cases. The documentation provides a local `playwright.config`, TestMu AI cloud `LT_USERNAME`/`LT_ACCESS_KEY` and CDP connection settings, a validation script `validate-config.py`, and the `npx playwright test` command for execution; HyperExecute and SmartUI should be delegated to other Skills.
Read Moredsh-browser-playwright-codex: Enabling AI to Operate in Real Browsers
`dsh-browser-playwright-codex` is a browser automation plugin for DeepSeek Harness (DSH) that uses Playwright to drive AI-based web operations in a visible browser window. Its core features include reusing logged-in accounts, preserving browser state, supporting multi-tab management and screenshots, and enabling stable operations through `ref` references. When it encounters CAPTCHAs or pop-up dialogs, the plugin automatically pauses and waits for human intervention, thereby addressing real-world login and interaction challenges. After installation, high-risk `evaluate` and `cdp` tools are disabled by default, and users must first obtain a Snapshot before performing subsequent actions. It is suitable for use cases such as list scraping, form filling, and order querying.
Read MoreIntroduction to the dsh-browsercontrol-mcp Plugin
The DeepSeek Harness plugin maintained by SciF-Lin converts the official Playwright MCP into a native tool, enabling agents to directly control real browsers. Core features include page navigation, interactions, screenshots, and JavaScript execution, supporting launch, CDP, and extension modes. Installation requires running a specific command and restarting the profile. Configuration includes parameters such as serverName, mode, and browser, with launch as the default mode. When using CDP or extension mode, be mindful of associated security risks and version compatibility.
Read MoreDeepSeek Harness Plugin: dsh-intranet-browser
`dsh-intranet-browser` is a plugin modified from `@yeesy369/dsh-browser-playwright`, designed to resolve the issue where DeepSeek Harness is restricted from accessing local and intranet addresses due to SSRF controls. It removes security restrictions, creates an isolated instance, and enables a user approval mechanism, allowing the AI to safely open, take screenshots of, and interact with web pages while debugging local services. This plugin is no longer maintained and has been merged into a unified plugin; when using it, you need to configure `evaluate: true` to enable specific features.
Read Moredsh-browser-use: DeepSeek Harness Browser Automation Plugin
`dsh-browser-use` is a browser automation plugin for DeepSeek Harness (DSH), maintained by `helloproblems`. It uses a three-layer architecture consisting of Hub, Backend, and Domain, supports Chrome and Edge backends, and provides an Agent isolation mechanism. The plugin achieves browser control through `chrome-devtools-mcp` and Playwright MCP, supports hot backend switching, and is suitable for web data scraping, automated testing, and interaction simulation. Installation requires Node.js ^22.19.0 or >=24.0.0 and a compatible DSH environment.
Read MoreDeepSeek Harness (DSH) Browser Automation Plugin: dsh-playwright
The `dsh-playwright` plugin for DeepSeek Harness (DSH) leverages Playwright to provide agents with a set of browser automation tools that are dynamically loaded at runtime. It supports both self-hosted and mounted modes, offering complete capabilities—from opening pages and click-based interactions to data scraping and capturing screenshots—and runs directly in the host process without requiring an external bridge service. Installation requires manually downloading Chromium, and it supports switching between Chinese and English as well as fast error propagation. It is currently compatible only with DSH 0.2.0-rc.2.
Read Moredsh-plugin-browser: DeepSeek Harness Built-in Browser Panel
`dsh-plugin-browser` is a browser plugin for the DeepSeek Harness (DSH) client, designed to simplify agent debugging of web interactions. Based on Playwright, it provides a real-time view, element selection, and model-callable tools (such as navigation, screenshots, clicks, and input) in the DSH right sidebar. Users can enable “Select Element” to insert element references as chips into the input box, enabling the model to locate elements precisely. Installation requires compatible versions of DSH and Node.js. It supports navigation, interaction, and code acceptance scenarios, but selectors only cover the main frame, and the screen stream is pushed only when the panel is visible.
Read MoreDeepSeek Harness Browser Use Plugin: Persistent Playwright Browser Tool and Interaction Panel
The DeepSeek Harness Browser Use plugin is built on Playwright to address challenges in browser operations for agent development. It provides persistent browser configuration, cross-tab login state sharing, a real-time visual interaction panel, and a suite of browser tools. Developers can monitor agent processes or manually take over control. The plugin supports configuration parameters such as headless mode and timeout, but note that snapshot references are single-use and no anti-crawling mechanism is provided.
Read Moredsh-webapp-testing: Web Application Testing and Playwright Workflows
`dsh-webapp-testing` is a user-maintained web application testing plugin for DeepSeek Harness (DSH). It is designed to provide web automation testing capabilities and Playwright workflow integration, with its design concept inspired by Anthropic skills. No official installation command is currently available; users need to obtain it from a community directory or GitHub repository. Because the licensing basis is only mentioned as inspiration rather than explicitly declared, users are advised to review the source code and licensing details before installation and confirm compliance before use.
Read Moredsh-web-fetch-playwright: Provides Real Browser Rendering Capabilities for DSH web_fetch
`dsh-web-fetch-playwright` is a DeepSeek Harness (DSH) plugin that uses Playwright to resolve missing-content issues when the native `web_fetch` tool fetches dynamic web pages. It supports both local and CDP backend modes, rendering SPA content in a real browser. The plugin provides content denoising (Readability, DOMPurify), Markdown conversion, resource limits, and Cloudflare challenge waiting, ensuring clean and configurable fetched content. To install it, restart `dsh web` and configure it in the settings panel.
Read Moredsh-plugin-browser: Playwright Browser Driver Plugin for DeepSeek Harness
`dsh-plugin-browser` is a DeepSeek Harness (DSH) community plugin that uses Playwright to drive a headless browser, enabling the model to render web pages, extract text, take screenshots, and perform automated interactions. It addresses the limitation of basic web tools that cannot execute JavaScript, supporting handling of SPA applications and dynamic data scraping. Installation requires running a command and relies on Playwright, while users can adjust parameters such as timeout, number of extracted characters, and browser path through a configuration file. The plugin isolates sessions per Agent, can simulate human browsing behavior, and is suitable for automated operation scenarios.
Read Moredsh-playwright-native: Registering local native Playwright CLI as a DeepSeek Harness pass-through tool
# Introduction Integrating Playwright with an Agent typically involves a semantic wrapper: splitting `test`, `install`, and `show-report` into multiple tools and designing a parameter schema for each subcommand. The problem with this path is that the Playwright CLI already possesses a complete feature set. No matter how comprehensive the mapping in the wrapper layer, options are inevitably missed, and the range of capabilities actually available to the Agent depends on the wrapper author. In DSH (DeepSeek Harness), "everything is a plugin"; all tools visible to the model originate from plugin registration. Thus, an alternative approach emerged: register a pass-through tool that passes the parameters provided by the Agent directly to the local CLI. `mitao-su/`
Read Moredsh-playwright: Share a browser page with the model in DeepSeek Harness
dsh-playwright is an MIT-licensed DSH plugin maintained by JeremyGuo, allowing users and the model to share the same Playwright browser page. The model navigates, clicks, inputs text, and performs keyboard operations via browser_* tools, while users can monitor the process in real-time on the Browser Use panel and take over control at any time. Navigation.
Read Moredsh-playwright-cli: Integrating Playwright CLI into DSH's Agent Loop
dsh-playwright-cli is a Host-only plugin for DSH agents designed to encapsulate common Playwright CLI operations as tools callable by the agent, thereby implementing automated testing workflows. The plugin provides four core functionalities: `playwright_version` probes the local CLI status; `playwright_install` automatically installs browsers and missing test dependencies; `playwright_test` runs test suites, supporting various parameter configurations; and `playwright_show_report` generates and returns the route or file path to the HTML report. The plugin runs based on DSH's shell executor, inheriting its sandbox strategy, timeout control, and environment variable configuration.
Read MoreDSH-BrowserUse: A browser-use Style Browser Automation Plugin for DeepSeek Harness
`dsh-browseruse` is a browser automation plugin for DeepSeek Harness (DSH), implemented purely in JavaScript with no build step required. It drives a standalone Google Chrome instance via `playwright-core`, enabling operations such as opening web pages, reading content, clicking, inputting text, scrolling, and switching between tabs, while supporting autonomous decision-making based on page state during multi-step tasks. Core features include: 11 fine-grained `browser_*` tools; `browser_task` for natural language autonomous tasks (default maximum of 30 steps); `browser_schedule` for scheduled tasks within the current session; a user confirmation mechanism before sensitive operations (e.g., payments, deletions); manual takeover during CAPTCHA detection; and an independent Pr
Read Moredsh-browser-playwright: A Playwright-Based Browser Plugin for DeepSeek Harness
dsh-browser-playwright is an MIT-licensed browser plugin designed for DeepSeek Harness, aimed at addressing issues such as CSS selector mismatches or oversized DOM contexts in traditional solutions. By leveraging Playwright to drive a real browser, the plugin utilizes accessibility snapshots and stable element references (ref) to constrain the model's interaction interface, avoiding direct selector guessing or outputting the complete DOM. Its core features include support for tab management, screenshots, structured extraction, and controlled JavaScript execution, along with 17 tool interfaces prefixed with `browser_`. The plugin can automatically detect browser channels such as Chromium and Chrome, and supports restricting navigation domains.
Read MoreDSH-Browser: A Playwright Browser Automation Plugin for DeepSeek Harness
dsh-browser is a Playwright-based browser automation plugin for DeepSeek Harness, designed to enable Agents to directly drive real web pages. It provides tools such as `browser_open`, `click`, `type`, `screenshot`, and `eval`, supporting page navigation, form interaction, JavaScript execution, content reading, and screenshot review. Browser state is maintained across tool calls, and it runs in headless mode by default. Installation requires `playwright-core` and a Chromium-based browser (it automatically attempts to use chromium/chrome/msedge; if missing, you can run `npx playwri
Read Moredsh-browser: A Self-Contained Browser Runtime for DSH
@anweat/dsh-browser is a networking tool plugin for DeepSeek Harness, which packages Playwright (Chromium) and OpenCLI as local dependencies for the plugin. It exposes browser services and up to 21 interactive browser tools externally. dsh-web-search-pro can inject this service through "inject," eliminating the reliance on a global CLI. The plugin supports page read/write, Recipe automation, limited crawling, OpenCLI platform adaptation, and experimental reusable assets. It also implements layered control for approval and resource throttling through automationMode and usagePolicy. This article introduces installation commands, typical usage, and applicable boundaries.
Read Moredsh-playwright-browser: Providing Playwright Multi-tab Browser Automation for DSH Agents
dsh-playwright-browser is a DSH networking tool plugin maintained by Clizo1209, based on Playwright, which registers ten browser_* tools for intelligent agents. It supports multi-tab, semantic positioning, bounded snapshots, and screenshots. The article covers installation commands, cordis.patch.yml configuration, typical invocation flow, and security considerations. The plugin runs with DSH process permissions; please verify the source code and MIT license before installation.
Read MoreConnect Playwright Browsers to DeepSeek Harness with dsh-playwright-browser
dsh-playwright-browser is a community plugin for DeepSeek Harness maintained by Clizo1209. It provides 10 browser_* tools, semantic positioning and multi-tab control for agents via Playwright. This article verifies the installation commands, configuration items and security boundaries against the directory page, GitHub README and npm version 0.1.3: no page eval is provided, and the plugin runs with the permissions of the current dsh process.
Read MoreUse recording-browser-flow-as-test: Walk through the process in the browser and automatically generate Playwright tests
# Introduction to `recording-browser-flow-as-test` in spencerpauly/awesome-cursor-skills: This tool allows users to walk through user workflows step-by-step using Cursor's built-in browser, record accessibility tree information via `browser_snapshot`, and then generate Playwright tests that use stable locators such as `getByRole` and `getByLabel`. This article verifies the installation commands, prerequisites, recording steps, assertion and hardening suggestions, as well as inapplicable scenarios such as 2FA and verification codes.
Read More`playwright-interactive: Using Persistent JS_REPL for UI Iteration and Debugging`
# Introduction to OpenAI's Featured Skill: playwright-interactive This skill enables persistent handling of Playwright/Electron via js_repl, allowing rapid iterative UI debugging on local web and Electron applications. It also supports completing QA checklists, functional validation, visual QA and viewport adaptation following official workflows. This article details the installation steps, pre-configuration requirements, typical code snippets, as well as notes such as the possible removal of js_repl in the current Codex, and makes a comparison with the CLI-oriented Playwright Skill.
Read MoreAdding E2E Tests: Building Playwright End-to-End Tests from Scratch with Agent Skill
### 正式翻译： # Adding E2E Tests from awesome-cursor-skills: Teach AI Agents to Build Playwright E2E Testing from Scratch This tutorial covers end-to-end setup with Playwright: installing dependencies, configuring `playwright.config.ts`, writing smoke tests and Page Objects, supplementing npm scripts and `.gitignore`, integrating GitHub Actions CI, and emphasizes best practices for `data-testid` and Playwright Codegen. It explains the positioning of this skill, its differences from webapp-testing, installation methods for Cursor/Claude Code, and a seven-step implementation workflow, making it suitable for frontend and full-stack projects that have not yet adopted E2E testing.
Read MoreDrive Real Browsers via Terminal: Getting Started with OpenAI's Official Playwright Skill
OpenAI's featured Skill "playwright" wraps the Playwright Agent CLI into a terminal browser automation workflow: opening pages, taking snapshots to obtain element references, filling forms and clicking, taking screenshots, and debugging with Trace. Verified based on the official SKILL.md, this article introduces the installation methods (Codex skill-installer, Cursor .cursor/skills), the usage of the wrapper script, typical command examples, as well as precautions such as re-snapshotting when refs fail and not writing @playwright/test by default. It is suitable for E2E exploratory automation and UI process troubleshooting scenarios.
Read More# webapp-testing: Let AI Agents Autonomously Validate Local Web Applications with Playwright
Anthropic's official webapp-testing Skill wraps Playwright browser automation into reusable, agent-friendly test workflows. It supports starting local dev servers, taking screenshots to inspect DOM, and capturing console logs, and validates dynamic single-page applications following a "inspect first, then operate" pattern. This article introduces its core capabilities, installation methods in Cursor and Claude Code, as well as the multi-server management with `with_server.py` and typical Playwright script examples, to help developers enable AI to independently run UI regression tests after modifying front-end code.
Read More