菜单
Native CDP browser automation reference. Headless/headed Chrome control, screenshots, JS evaluation. (/browser-cdp, browser automation, cdp, scraping)
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/adolfousier/opencrabs --skill browser-cdp命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Full GitHub CLI control — issues, PRs, code reviews, repo management. Uses gh CLI with auth detection, rate limiting, and templates. Triggers on: github, issue, pull request, PR, code review, repo, branch, label, assignee, milestone, release, workflow, actions.
Orchestrate a task across multiple AI models/providers. Define a team of agents with different roles, providers, and models. Each agent handles a phase (planning, execution, auditing, etc.) and results are combined. (/multi-agent, orchestrate, multi-model, team)
Runtime tool management with tool_manage and tools.toml format. Create, enable, disable, reload tools without restart. (/dynamic-tools, tool_manage, runtime tools)
基于 SOC 职业分类
正在显示 SKILL.md
| name | browser-cdp |
| description | Native CDP browser automation reference. Headless/headed Chrome control, screenshots, JS evaluation. (/browser-cdp, browser automation, cdp, scraping) |
Built-in browser control via Chrome DevTools Protocol — no Node.js, no Playwright, pure Rust.
| Tool | Required | Optional | What |
|---|---|---|---|
browser_navigate | url | headless | Navigate to URL |
browser_click | selector | — | Click element by CSS selector |
browser_type | text | selector | Type text into input |
browser_screenshot | — | selector | Screenshot (returns file path) |
browser_eval | script | — | Execute JavaScript |
browser_content | — | selector, text_only | Extract text/HTML |
browser_wait | — | selector, timeout_secs, delay_secs | Wait for element or delay |
browser_find | — | pattern, mode, limit | Inventory (no pattern) or find elements |
headless: false to browser_navigate.browser_find with NO pattern to get every visible
interactive element on the page, each with a stable [data-opencrabs-match="N"]
selector. Prefer this over browser_screenshot when you have just landed and do
not yet know what to click — text beats pixels for deciding where to act.<<IMG:path>> to send to channels.browser flag.rm -f ~/.opencrabs/chrome-profile/SingletonLock ~/.opencrabs/chrome-profile/SingletonCookie ~/.opencrabs/chrome-profile/SingletonSocket then retry.pkill -f chrome then retry.