能力说明
这个 Skill 能做什么
基于 agent-browser CLI 的 AI 友好型网页自动化
安装方式
如何安装
人工安装
- 下载当前版本的
SKILL.md文件。 - 在目标运行时的 Skills 目录中创建名为
agent-browser-core的文件夹。 - 将文件放入该文件夹，随后按运行时自身的加载方式启用它。
mkdir -p skills/agent-browser-core
# 下载下方的 SKILL.md，并保存为：
# skills/agent-browser-core/SKILL.md清单路径：skills/agent-browser-core/SKILL.md。具体安装目录可能因运行时而异，请以目标运行时文档为准。
AI 安装将这段话发送给 AI，由它根据目标运行时完成安装并检查结果。
请帮我将「Agent Browser Core」安装到目标 AI 运行时中。
Skill 平台详情页：https://www.skillagenthub.com/skills/agent-browser-core
平台镜像下载地址：https://www.skillagenthub.com/api/skills/agent-browser-core/download
目标目录：skills/agent-browser-core/SKILL.md
请先确认当前运行时的 Skill 目录与安装规范；再下载或保存该版本的 SKILL.md 到正确位置。完成后请检查文件路径、版本和可加载性，并简要报告安装结果。不要执行 Skill 包内任何脚本。AI 使用提示
分两段提供给 AI
先提供 Skill 指令，再提供具体任务，让模型先了解能力边界，再执行实际工作。
第一段：Skill 指令先发送，用于建立能力、规则与限制。
---
name: agent-browser-core
display_name: "网页自动化"
description: OpenClaw skill for the agent-browser CLI (Rust-based with Node.js fallback) enabling AI-friendly web automation with snapshots, refs, and structured commands.
description_zh: "基于 agent-browser CLI 的 AI 友好型网页自动化"
description_en: "AI-friendly web automation via agent-browser CLI with snapshots & refs"
version: 1.0.1
allowed-tools: Bash
---
# Agent Browser Skill (Core)
## Purpose
Provide an advanced, production-ready playbook for using agent-browser to automate web tasks via CLI and structured commands.
## Best fit
- You need deterministic automation for AI agents.
- You want compact snapshots with refs and JSON output.
- You prefer a fast CLI with Node.js fallback.
## Not a fit
- You require a full SDK or custom JS integration.
- You must stream large uploads or complex media workflows.
## Quick orientation
- Read `references/agent-browser-overview.md` for install, architecture, and core concepts.
- Read `references/agent-browser-command-map.md` for command categories and flags.
- Read `references/agent-browser-safety.md` for high-risk controls and safe mode rules.
- Read `references/agent-browser-workflows.md` for recommended AI workflows.
- Read `references/agent-browser-troubleshooting.md` for common issues and fixes.
## Required inputs
- Installed agent-browser CLI and browser runtime.
- Target URLs and workflow steps.
- Session or profile strategy if authentication is required.
## Expected output
- A clear command sequence and operational guardrails for automation.
## Operational notes
- Snapshot early, act via refs, then snapshot again after DOM changes.
- Use `--json` for machine parsing and scripting.
- Use waits and load-state checks before actions.
- Close tabs or sessions when done to release resources.
## Safe mode defaults
- Do not use `eval`, `--allow-file-access`, custom `--executable-path`, or arbitrary `--args` without explicit approval.
- Avoid `network route`, `set credentials`, and cookie/storage mutations unless the task requires it.
- Allowlist domains and block localhost or private network targets.
## Security notes
- Treat tokens and credentials as secrets.
- Avoid `--allow-file-access` unless explicitly required.
第二段：任务请求在第一段之后发送，将方括号内容替换为你的目标。
请使用「Agent Browser Core」完成以下任务。
任务目标：
[描述你希望完成的结果]
输入资料：
[粘贴文本、链接、文件说明或数据]
输出要求：
[说明格式、语言、篇幅和验收标准]
请严格遵循上一段 Skill 指令中的边界、步骤和限制；缺少必要信息时先提出澄清问题。原始内容
SKILL.md
---
name: agent-browser-core
display_name: "网页自动化"
description: OpenClaw skill for the agent-browser CLI (Rust-based with Node.js fallback) enabling AI-friendly web automation with snapshots, refs, and structured commands.
description_zh: "基于 agent-browser CLI 的 AI 友好型网页自动化"
description_en: "AI-friendly web automation via agent-browser CLI with snapshots & refs"
version: 1.0.1
allowed-tools: Bash
---
# Agent Browser Skill (Core)
## Purpose
Provide an advanced, production-ready playbook for using agent-browser to automate web tasks via CLI and structured commands.
## Best fit
- You need deterministic automation for AI agents.
- You want compact snapshots with refs and JSON output.
- You prefer a fast CLI with Node.js fallback.
## Not a fit
- You require a full SDK or custom JS integration.
- You must stream large uploads or complex media workflows.
## Quick orientation
- Read `references/agent-browser-overview.md` for install, architecture, and core concepts.
- Read `references/agent-browser-command-map.md` for command categories and flags.
- Read `references/agent-browser-safety.md` for high-risk controls and safe mode rules.
- Read `references/agent-browser-workflows.md` for recommended AI workflows.
- Read `references/agent-browser-troubleshooting.md` for common issues and fixes.
## Required inputs
- Installed agent-browser CLI and browser runtime.
- Target URLs and workflow steps.
- Session or profile strategy if authentication is required.
## Expected output
- A clear command sequence and operational guardrails for automation.
## Operational notes
- Snapshot early, act via refs, then snapshot again after DOM changes.
- Use `--json` for machine parsing and scripting.
- Use waits and load-state checks before actions.
- Close tabs or sessions when done to release resources.
## Safe mode defaults
- Do not use `eval`, `--allow-file-access`, custom `--executable-path`, or arbitrary `--args` without explicit approval.
- Avoid `network route`, `set credentials`, and cookie/storage mutations unless the task requires it.
- Allowlist domains and block localhost or private network targets.
## Security notes
- Treat tokens and credentials as secrets.
- Avoid `--allow-file-access` unless explicitly required.