cowork-qa 浏览器会话
v0.1.1
io.github.inSideos-designs/cowork-qa
面向 LLM 的目标驱动 Playwright 浏览器会话,附完整操作轨迹与 aria 快照。
“playwright” 共 187 个结果
v0.1.1
io.github.inSideos-designs/cowork-qa
面向 LLM 的目标驱动 Playwright 浏览器会话,附完整操作轨迹与 aria 快照。
v1.9.1
io.github.noncelogic/mcp
面向 AI 智能体的托管 Playwright API,返回无障碍树而非截图。
v2.2.2
io.github.beycom/onetool-mcp
面向开发者的单个 MCP 全包:Brave、Google、Tavily、Context7、AWS、Excalidraw、数据库、GitHub、DevTools、Playwright。
v0.1.1
io.github.ArkNill/browsegrab
面向本地 LLM 的省 token 浏览器代理:Playwright + 无障碍树 + MarkGrab。
v0.7.3
io.github.Retio-ai/pagemap
面向 AI 智能体的结构化网页情报,比 Playwright/Firecrawl 少用 5 倍 token,准确率 84.7%。
v1.2.0
io.github.dpozimski/pdfspark-mcp
基于 Playwright 将 HTML 或 URL 转换为 PDF 文档
v1.0.3
io.github.aybelatchane/mcp-server-terminal
让 AI 智能体与终端应用交互的 MCP 服务器,可理解为终端版 Playwright。
v0.3.0
io.github.sunshad0w/html2md
将 HTML 转换为 Markdown,自动摘要并按章节抽取,支持 Playwright。
v1.1.1
io.github.JustasMonkev/mcp-accessibility-scanner
基于 Playwright 与 Axe-core 的自动化网页无障碍(Accessibility)扫描 MCP 服务器。
io.github.anthropics/skills/webapp-testing
使用 Playwright 与本地 Web 应用交互并测试的工具包。支持验证前端功能、调试 UI 行为、捕获浏览器截图和查看浏览器日志。
io.github.grafana/grafana/frontend-testing-strategy
按本仓库约定为 Grafana 前端代码(React/TypeScript,任意包或功能域)编写单元与 E2E 测试。新增、补齐或审查前端测试时使用;测试仅断言“渲染成功/已定义”、AI 生成测试质量存疑、或前端测试不稳定时同样适用。涉及可视化面板与 grafana-ui 可视化组件时,另需加载 panel-testing-strategy skill。
io.github.anomalyco/opencode/component-tests
Use when writing, changing, debugging, or reviewing the Playwright component tests that mount stories. That covers specs in packages/app/component-tests or packages/session-ui/component-tests, `*.fixture.tsx` files there or beside source (such as packages/gui-plugins/src/browser/panel.fixture.tsx), the stories they mount, and the shared harness in packages/stories (playwright/config.ts, playwright/story.ts, vite.config.ts, src/frame.tsx, src/index-plugin.ts, mocks). Also use when a component test is flaky, passed on retry, or fails with "Execution context was destroyed", "Failed to fetch dynamically imported module", or `#story-root` hidden. Covers mount args, source modules imported by URL, Vite dependency pre-bundling and reloads, a cold vs warm story server, mobile drawers, geometry, and checks before pushing.
io.github.browser-use/browser-use/browser-use
通过 CDP 直接控制浏览器完成 web 交互:自动化、抓取、测试、截图以及站点/应用操作。
io.github.browser-use/browser-use/cloud
Browser Use Cloud(托管版浏览器自动化 API)文档参考。凡涉及 Cloud REST API(v2、v3 或 v4)、browser-use-sdk(Python 或 TypeScript)、X-Browser-Use-API-Key 鉴权、cloud sessions、浏览器 profile、profile 同步、CDP WebSocket 连接、隐身浏览器、住宅代理、验证码处理、webhook、workspace、skill 市场、liveUrl 流、定价,以及集成模式(聊天界面、subagent、把浏览器工具接入已有 agent)时使用。n8n/Make/Zapier 集成、云上 Playwright/Puppeteer/Selenium、1Password 密钥库相关问题也适用。不适用于开源 Python 库(Agent、Browser、Tools 配置)——那些请用 open-source skill。
io.github.OpenHands/OpenHands/e2e-testing
This skill should be used when the user asks to "add an E2E test", "run live E2E", "run mock-LLM tests", "debug Playwright CI", "test the Docker image", or changes tests/e2e, Playwright configs, E2E workflows, artifacts, or test reporting.
io.github.deepseek-ai/deepseek-harness/record-browser-gif
使用可用的浏览器控制工作流,可选 Playwright Videos 提升采集帧率,并以确定性编码把浏览器或 Web UI 交互演示录制为优化后的 GIF,再用 gh --attach 将 GIF 附到 PR 上;无法附加时回退到专用 assets 分支。在被要求制作、录制或生成演示浏览器工作流的 GIF 时使用;凡改动面向产品用户的 GUI 行为的 PR,都必须附带从该 PR 真实服务端与模型流程录制的 GIF。
io.github.Stirling-Tools/Stirling-PDF/ui-walkthrough
对当前分支功能做完整的 UI 调查。枚举每个视图与状态(空态、有数据、加载、错误、每个对话框/菜单/面板、响应式断点、浅色+暗色+RTL),用内置 Playwright 工装捕获,汇总为带全局明暗切换滑杆的单图 HTML 走查,随后跑两轮审查:视觉/一致性(对齐、间距、专业感、明暗一致、对比度、截断)与 UX/易用性(流程、可发现性、可供性、空态/错误态、预期)。当被要求做 UI 走查、截图审查、设计或 QA 巡检、「找出可以更易用/更好的地方」或前端工作合并前使用。加 --fix 自动应用安全的前端修复并重新捕获;--theme 限定主题;--no-rtl 跳过 RTL。
io.github.outline/outline/verify-outline
Launch an isolated Outline instance (web UI + API, production build, own Postgres/Redis containers) from the current checkout and drive it in a headless browser to prove a user-facing change works, with screenshots, Playwright traces and database checks as evidence. Use when asked to verify, demo, reproduce or screenshot Outline behavior in the real app, rather than only in unit tests.
io.github.alirezarezvani/claude-skills/engineering-skills
工程团队技能包的索引,支持 Claude Code、Codex、Gemini CLI、Cursor、OpenClaw 及另外 6 种工具。涵盖架构、前端、后端、QA、DevOps、安全、AI/ML、数据工程、Playwright、Stripe、AWS、MS365(仅 stdlib Python 工具)。用于浏览或选择工程团队角色技能——只加载所需的单个专家 SKILL.md,切勿批量加载整个技能包。
io.github.anomalyco/opencode/app-e2e-tests
Use when writing, changing, reviewing, or debugging Playwright e2e tests in packages/app/e2e (regression keepers and user stories). Covers the mocked opencode server harness and the Bun static server, per-test isolation, page-load and route cost, the suite-wide service-worker block, races with first mount, hover, measurement, clock, dialogs and shortcuts, projects, shards and worker scheduling, rehearsing Windows timing locally, and diagnosing a CI flake from its artifacts. Not for Storybook component tests or e2e/performance benchmarks.
io.github.affaan-m/ECC/e2e-testing
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Use when writing Playwright tests, structuring page objects, or fixing flaky E2E runs in CI.
io.github.affaan-m/ECC/react-testing
React component testing with React Testing Library, Vitest/Jest, MSW for network mocking, accessibility assertions with axe, and the decision boundary between component tests and Playwright/Cypress end-to-end runs. Use when writing or fixing tests for React components, hooks, or pages.
io.github.affaan-m/ECC/browser-qa
在功能部署之后,通过浏览器自动化完成可视化测试与 UI 交互验证。
io.github.wekan/wekan/meteor-debugging
Use when diagnosing an unexplained failure in a Meteor 3 application before the failing layer or fix is known. Triggers on server crashes, client-only errors, stuck subscriptions, DDP or WebSocket disconnects, Minimongo/server data mismatches, hanging or flaky tests, slow builds, --inspect, console.log, .only, Playwright traces, Instrumentation lifecycle events, or requests to debug a Meteor app. Use this skill when evidence must distinguish Meteor tool, server, client, data, test, browser, mobile, or production boundaries. For test setup and authoring use meteor-testing; after confirming a domain cause, hand the repair to the owning skill.