agent-browser SKILL.md skillA

agent-browser from seaworld008/commonly-used-high-value-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add seaworld008/commonly-used-high-value-skills/agent-browser@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
seaworld008/commonly-used-high-value-skills
Path
openclaw-skills/agent-browser/SKILL.md
Versions recorded
3
Latest version
v1.0.0, committed Jun 29, 2026
First version recorded
Mar 15, 2026
Size
7,017 bytes
Repository stars
73
License
MIT

Use when an agent needs real browser automation for semantic element targeting, form interaction, screenshots, recordings, script execution, session reuse, or end-to-end web workflow verification.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Agent Browser

当任务需要 **直接操作网页**(而不是只读 API 数据)时使用本技能。Agent Browser 基于标准的 CDP (Chrome DevTools Protocol) 协议,赋予 Agent 像人类一样浏览网页、填写表单、点击按钮以及处理复杂前端交互(如 React/Vue 渲染页面、弹窗、验证码预览)的能力。

## 安装

```bash
npx clawhub@latest install agent-browser
```

## 适用场景

- **打开网页并执行多步操作**:登录后台管理系统、在多个页签间比对数据、提交复杂的业务表单。
- **用自然语言定位元素**:无需编写复杂的 CSS Selector,直接通过“点击左上角的搜索框”或“找到包含‘加入购物车’字样的按钮”进行操作。
- **导出多媒体产出**:将当前页面保存为高清截图、滚动截长图、PDF 文档,甚至录制一段操作视频。
- **执行页面内 JavaScript**:直接在 Console 中注入自定义脚本,提取原本难以抓取的动态数据或模拟特定用户行为。
- **保存会话状态**:支持 Cookie、LocalStorage 的持久化(`retain` 机制),实现跨会话的免登录访问。

## 使用建议

1. **先说明目标页面与预期结果**:建立清晰的 `Success Criteria`。
2. **分阶段执行**:将复杂操作拆成可验证的原子步骤(导航 → 定位 → 操作 → 校验)。
3. **涉及账号安全**:优先使用隔离的浏览器 Profile,并开启最小权限模式。
4. **视觉优先**:在关键操作前后进行 `screenshot`,既是留存证据,也方便 Agent 自我纠错。

## 触发条件 / When to Use

- **API 缺失场景**:当目标网站不提供公开 API,只能通过网页前端交互获取数据时。
- **图形化报表抓取**:需要从复杂的仪表盘(Dashboard)中截取特定图表并分析。
- **自动化注册/登录流程**:需要模拟用户完成一系列实人认证或偏好设置步骤。
- **SEO 与前端性能测试**:通过 `console` 读取页面报错、性能指标(LCP, FID)并进行诊断。
- **动态内容实时监控**:如监控股市实时行情网页或秒杀活动的库存变动。

## 核心能力 / Core Capabilities

### 1. 语义化快照与定位 (Semantic Snapshot)
- **操作步骤**:
  1. 调用 `snapshot` 获取辅助功能树(Accessibility Tree)。
  2. 结合 `ax*`(可访问性引用)和 `n*`(DOM 引用)理解页面层级。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add seaworld008/commonly-used-high-value-skills/agent-browser@sha256:481d9840cd780b9b

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_g63wvdgzpsxdkqt4.svg)](https://markdownregistry.com/a/art_g63wvdgzpsxdkqt4)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Mar 15, 2026 and Jun 29, 2026, about one every 53 days.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-06-29 b4409df 7,017 BA view · diff
v1.0.02026-03-27 0b34652 6,823 BA view · diff
git:20260315.df072122026-03-15 df07212 815 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7017 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

seaworld008/commonly-used-high-value-skills · 73 stars · license MIT · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_g63wvdgzpsxdkqt4
GET https://markdownregistry.com/api/v1/resolve?ref=seaworld008/commonly-used-high-value-skills/agent-browser
GET https://markdownregistry.com/api/v1/blob/481d9840cd780b9bb966b58ca8b035b02eb9202029be07070a79a520ffd4ad81

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from seaworld008/commonly-used-high-value-skills

AGENTS.md AGENTS.md file
seaworld008/commonly-used-high-value-skills · AGENTS.md
git:20260907.7aad3b0 · audit A · 73 stars
CLAUDE.md CLAUDE.md file
seaworld008/commonly-used-high-value-skills · CLAUDE.md
git:20260907.7aad3b0 · audit A · 73 stars
agent-designer SKILL.md skill
seaworld008/commonly-used-high-value-skills · openclaw-skills/agent-designer/SKILL.md · Design AI agent responsibilities, tools, memory, orchestration, and evaluation when defining an agent architecture or…
v1.0.2 · audit A · 73 stars
CLAUDE.md@openclaw-skills/agent-hub CLAUDE.md file
seaworld008/commonly-used-high-value-skills · openclaw-skills/agent-hub/CLAUDE.md
git:20260424.86f3732 · audit A · 73 stars
agent-hub SKILL.md skill
seaworld008/commonly-used-high-value-skills · openclaw-skills/agent-hub/SKILL.md · Compare independent solutions with agent-hub when parallel competition is requested; isolate Git worktrees, evaluate…
v1.0.11 · audit A · 73 stars
agent-workflow-designer SKILL.md skill
seaworld008/commonly-used-high-value-skills · openclaw-skills/agent-workflow-designer/SKILL.md · Design agent orchestration, handoffs, state, recovery, and evaluation when a workflow needs multiple coordinated agents…
v1.1.1 · audit A · 73 stars
agile-product-owner SKILL.md skill
seaworld008/commonly-used-high-value-skills · openclaw-skills/agile-product-owner/SKILL.md · Manage product backlogs and sprints: user stories, acceptance criteria, epic breakdown, prioritization, estimates, and…
v1.0.1 · audit A · 73 stars
algorithmic-art SKILL.md skill
seaworld008/commonly-used-high-value-skills · openclaw-skills/algorithmic-art/SKILL.md · Create original generative art with p5.js, seeded randomness, flow fields, particles, and interactive parameters when…
v1.0.1 · audit B · 73 stars
andrej-karpathy-skills SKILL.md skill
seaworld008/commonly-used-high-value-skills · openclaw-skills/andrej-karpathy-skills/SKILL.md · Karpathy-inspired coding discipline for AI agents: think before coding, keep changes simple, edit surgically, and…
v1.0.0 · audit A · 73 stars
api-and-interface-design SKILL.md skill
seaworld008/commonly-used-high-value-skills · openclaw-skills/api-and-interface-design/SKILL.md · Design REST/GraphQL APIs, module interfaces, and type contracts when creating endpoints or changing public boundaries.
v1.0.4 · audit A · 73 stars
api-design-reviewer SKILL.md skill
seaworld008/commonly-used-high-value-skills · openclaw-skills/api-design-reviewer/SKILL.md · Use when reviewing API designs for consistency, usability, versioning, error semantics, security, backward…
v1.0.0 · audit A · 73 stars
api-test-suite-builder SKILL.md skill
seaworld008/commonly-used-high-value-skills · openclaw-skills/api-test-suite-builder/SKILL.md · Generate API tests from routes and contracts for authentication, validation, pagination, errors, uploads, and limits in…
v1.0.1 · audit A · 73 stars

Every file in seaworld008/commonly-used-high-value-skills

Other files named agent-browser

agent-browser SKILL.md skill
paperclipai/paperclip · packages/skills-catalog/catalog/optional/browser/agent-browser/SKILL.md · Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and…
git:20260528.9eac727 · audit A · 105,684 stars
agent-browser SKILL.md skill
shanraisshan/claude-code-best-practice · .claude/skills/agent-browser/SKILL.md · Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages…
git:20260210.a19f104 · audit A · 67,914 stars
agent-browser SKILL.md skill
vercel-labs/agent-browser · skills/agent-browser/SKILL.md · Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages…
git:20260824.021d925 · audit A · 44,324 stars
agent-browser SKILL.md skill
nanocoai/nanoclaw · container/skills/agent-browser/SKILL.md · Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots…
git:20260710.df4929d · audit A · 30,979 stars
agent-browser SKILL.md skill
mvschwarz/openrig · skills/_canonical/process/agent-browser/SKILL.md · Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages…
git:20260514.647864f · audit A · 7,989 stars
agent-browser SKILL.md skill
mvschwarz/openrig · packages/daemon/specs/agents/shared/skills/process/agent-browser/SKILL.md · Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages…
git:20260514.647864f · audit A · 7,989 stars
agent-browser SKILL.md skill
maxmiksa/auto-company · .claude/skills/agent-browser/SKILL.md · Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages…
git:20251121.df99134 · audit A · 3,150 stars
agent-browser SKILL.md skill
fcakyon/claude-codex-settings · plugins/agent-browser/skills/agent-browser/SKILL.md · Agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow…
git:20261014.032e03d · audit A · 1,181 stars

Browse by kind, by grade A, or by owner.