automation-setup
Turn a user request into a scheduled automation by configuring cron jobs, including session-bound follow-ups and periodic checks.
Use Agent Browser for real browser navigation, dynamic pages, and web interaction; also use it as a distinct browser-based path when web_search is unavailable or fails.
$ npx -y skills add peiiii/nextclaw --skill agent-browser --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/agent-browserContext preview
The summary Claude sees to decide when to auto-load this skill.
Use Agent Browser for real browser navigation, dynamic pages, and web interaction; also use it as a distinct browser-based path when web_search is unavailable or fails.
name: agent-browser
description: Use Agent Browser for real browser navigation, dynamic pages, and web interaction; also use it as a distinct browser-based path when web_search is unavailable or fails.
description_zh: 使用 Agent Browser 完成真实浏览器导航、动态页面读取和网页交互;当 web_search 未配置或失败时,也可把它作为独立的浏览器路径评估使用。
metadata: {"nextclaw":{"emoji":"🌐"}}Agent Browser 是 NextClaw 调用的外部浏览器自动化 CLI。本 skill 只提供检查、安装引导、使用方式和安全边界,不包含 Agent Browser 的代码、npm 包或浏览器二进制。
先检查外部 CLI 是否存在:
command -v agent-browser agent-browser --version
如果 CLI 不存在:
1. 明确告诉用户这会安装第三方全局 npm 包并下载浏览器运行文件。 2. 用户当前请求若没有明确授权安装,先征得同意,不要静默安装。 3. 获得授权后执行:
npm install -g agent-browser agent-browser install
安装后或怀疑环境异常时先运行只读快速诊断:
agent-browser doctor --offline --quick
只有诊断表明需要修复且用户同意时,才运行可能重装浏览器或清理旧状态的 `agent-browser doctor --fix`。
本地模式不要求付费云浏览器,也不要求 Browserbase、Browser Use 等云 provider key。选择外部云 provider 时,才按对应服务的账户和计费规则处理。
Agent Browser 的命令会随版本演进。执行非简单任务前,先读取 CLI 自带且与当前版本匹配的核心指南:
agent-browser skills get core
只有需要完整参数或复杂工作流时再使用:
agent-browser skills get core --full
以这份版本匹配指南为准,不要只凭记忆猜测命令或复制过时示例。
为每个任务使用独立、简短、仅含小写字母、数字和连字符的 session 名称,例如 `nextclaw-research-1`。同一任务的所有浏览器命令都带同一个 `--session`:
agent-browser --session nextclaw-research-1 open https://example.com agent-browser --session nextclaw-research-1 snapshot -i -u agent-browser --session nextclaw-research-1 get title agent-browser --session nextclaw-research-1 get url
核心循环:
1. `open` 打开明确 URL。 2. `snapshot -i -u` 读取可交互元素和链接;只读正文时可使用完整 snapshot 或针对元素执行 `get text`。 3. 使用最新 snapshot 生成的 `@eN` ref 交互。 4. 页面导航、提交或动态重绘后先等待,再重新 snapshot;旧 ref 已失效。 5. 用页面标题、最终 URL、可见文本或预期状态验证结果。 6. 从实际打开和读取的页面记录来源 URL,不把搜索结果摘要当成已核验来源。
任务完成、失败或准备回复用户前,关闭本任务的 session:
agent-browser --session nextclaw-research-1 close
不要默认使用 `close --all`,它可能关闭其他并行任务的浏览器 session。
浏览器信息发现是受限制的替代路径,不等于搜索 API:
回复用户前确认:
Your long-term personal AI partner. NextClaw's mission is to be a good long-term partner to you. We are building toward a 1.0 that understands you, takes useful initiative, and continuously improves itself.
Turn a user request into a scheduled automation by configuring cron jobs, including session-bound follow-ups and periodic checks.
Use when the user asks to keep watching an external state, notify them when something changes or a condition is met, remember…
Use when deciding how to deliver an AI result: reply now, put durable news, reports, recommendations, or articles in the NextClaw…
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced…
Use when Hermes needs to become a formal NextClaw runtime entry, especially for setup, doctor, repair, readiness checks, and…