浏览器自动化 SKILL.md skillA

浏览器自动化 from yuxinbeiyi/lianxin-ai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add yuxinbeiyi/lianxin-ai/浏览器自动化@v2

Pins v2 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: yuxinbeiyi/lianxin-ai
Path: skills/浏览器自动化/SKILL.md
Versions recorded: 2
Latest version: v2, committed Aug 4, 2026
First version recorded: Jun 6, 2026
Size: 3,342 bytes
Repository stars: 15
License: MIT

Playwright 驱动的浏览器控制（导航、点击、填表、按键、滚动、等待、标签页和截图）.

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

# 浏览器自动化

激活此技能后，你可以通过 Playwright 控制浏览器执行网页操作。

## 能力说明

- 打开网页（browser_navigate）
- 获取页面 ARIA 快照（browser_snapshot）
- 点击元素（browser_click，建议携带 snapshot_id）
- 填写表单（browser_fill，建议携带 snapshot_id）
- 发送受控按键（browser_press）
- 滚动页面（browser_scroll）
- 等待页面条件（browser_wait）
- 管理标签页（browser_tabs）
- 截取页面截图（browser_screenshot）
- 接管本机已启动浏览器（browser_connect，CDP，高风险需确认）
- 断开外部浏览器连接（browser_disconnect，不关闭外部浏览器）

## 使用流程

1. 用户说"打开某网页" → browser_navigate → 返回页面快照
2. 快照中标注 SNAPSHOT_ID 和可交互元素的 [ref=eX] 标记
3. 需要点击时 → browser_click(ref="e3", snapshot_id="snap_1")
4. 需要填表时 → browser_fill(ref="e2", text="内容", snapshot_id="snap_1")
5. 需要按 Enter/Tab 等键 → browser_press(key="Enter", ref="e2", snapshot_id="snap_1")
6. 页面内容在下方 → browser_scroll(amount=500, snapshot_id="snap_1")
7. 等待动态内容 → browser_wait(until="text", text="结果")
8. 如果返回 STALE_SNAPSHOT 或 STALE_REF → 重新调用 browser_snapshot，不要继续使用旧 ref
9. 需要查看页面变化 → browser_snapshot 刷新快照
10. 用户想看页面视觉效果 → browser_screenshot → describe_image

## 注意事项

- 浏览器默认可见模式（非 headless），会弹出窗口
- 需要等待页面加载时使用 browser_snapshot 检查状态
- 登录状态持久化到 `~/.lianxin/browser_profile/`
- 点击后建议调用 browser_snapshot 确认结果
- 每次页面变化后 ref 可能失效，必须使用最新快照中的 ref
- browser_wait 不接受任意 JavaScript 条件
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add yuxinbeiyi/lianxin-ai/浏览器自动化@sha256:f882bc8a42bcc067

The line at the top of this page pins the label v2, 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](https://markdownregistry.com/badge/art_t4giritzekpq2fg2.svg)](https://markdownregistry.com/a/art_t4giritzekpq2fg2)

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

Versions

The registry has recorded 2 versions of this file, between Jun 6, 2026 and Aug 4, 2026, about one every 58 days.

version	committed	commit	size	audit
v2 latest	2026-08-04	5f36185	3,342 B	A	view · diff
v2	2026-06-06	62e4be2	1,133 B	A	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 (3342 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

yuxinbeiyi/lianxin-ai · 15 stars · license MIT · pushed 2026-10-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_t4giritzekpq2fg2
GET https://markdownregistry.com/api/v1/resolve?ref=yuxinbeiyi/lianxin-ai/浏览器自动化
GET https://markdownregistry.com/api/v1/blob/f882bc8a42bcc067c87aadef6d3cfe2b2985ce11d71a9a265261c8f0b4016a76

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.