Browser Record
技能 已验证 活跃Open a named, traced browser session into an RVF cognitive container with a ruvector trajectory recording every action
To provide a robust and traceable mechanism for initiating and managing browser sessions, enabling detailed recording of user actions for replay, analysis, or debugging.
功能
- Opens named browser sessions
- Allocates RVF cognitive containers
- Records actions via ruvector trajectory
- Supports session replay and analysis
- Integrates with downstream browser skills
使用场景
- Starting any browser interaction that requires preserving the trace for later replay or analysis.
- Exploring a website interactively while ensuring all actions are recorded.
- Establishing a reusable session for subsequent browser-based tasks.
- Debugging complex user flows by reviewing recorded trajectories.
非目标
- Performing one-off, throwaway browser probes.
- Directly executing browser actions without session tracing.
- Redacting Personally Identifiable Information (PII) during navigation (handled by downstream skills).
工作流
- Allocate session ID and RVF container
- Begin trajectory recording
- Open browser via `browser_open`
- Snapshot initial state (accessibility, screenshot)
- Record trajectory step before and after each interaction
- End session cleanly with verdict
- Compact RVF file
- Index session in AgentDB
实践
- Browser Session Management
- Action Recording
- Trace Preservation
先决条件
- npx installed
- ruvector@0.2.25 or compatible
- @claude-flow/cli@latest or compatible
- MCP server with browser tools enabled
安装
请先添加 Marketplace
/plugin marketplace add ruvnet/ruflo/plugin install ruflo-browser@ruflo质量评分
已验证类似扩展
Playwright Recording
99使用 Playwright 将浏览器交互记录为视频。用于为 Remotion 视频捕获演示视频、应用程序演练和 UI 流程。触发器包括录制演示、捕获浏览器视频、录制网站屏幕或创建演练素材。
Browser Trace
99Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page summaries back into an agent loop so its next iteration learns from the last one.
Agent Browser
100AI 代理的浏览器自动化 CLI。当用户需要与网站交互时使用，包括浏览页面、填写表单、点击按钮、截屏、提取数据、测试 Web 应用或自动化任何浏览器任务。触发条件包括请求“打开网站”、“填表”、“点击按钮”、“截屏”、“抓取页面数据”、“测试此 Web 应用”、“登录网站”、“自动化浏览器操作”或任何需要以编程方式进行 Web 交互的任务。
Chatgpt Search
100Search ChatGPT and extract the full response + hydration JSON that powers the UI. Attaches to a running Chrome instance (port 9222 by default), opens ChatGPT, submits a query, waits for the streamed response, and returns structured data: messages, product cards, hydration JSON, and API calls. Use when asked to "search chatgpt", "ask chatgpt", "chatgpt search", "get chatgpt response", or "scrape chatgpt".
Cli Anything Safari
100Safari browser automation CLI on macOS via safari-mcp. Controls real Safari (native, keeps logins) by wrapping the safari-mcp MCP server. Every one of the 84 MCP tools is exposed 1:1 with schema-accurate arguments — guaranteed parity, no manual drift.
AutoBrowse
100Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser automation skills for specific website tasks.