What it does
给你的本机 Agent(如 Claude Code、Grok Bot 等)装上完整联网能力的 Skill:三层通道调度 + 浏览器 CDP + 并行分治,自动积累站点经验,不断优化联网效率
- Connects Instruction files the AI reads; connects to nothing
- Account or key No key needed
- Category Coding
For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/eze-is-web-access)Use together with
MCP servers that connect the AI to services for the same work
Fallow
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
Desktop Commander
MCP server for terminal commands, file operations, and process management
Similar Skills
Same kind of work, ordered like the Skills list
| This one web-access | rea | graphify | archify | security-audit-skill | |
|---|---|---|---|---|---|
| Maker | eze-is | morluto | Graphify-Labs | tt-a1i | cloudflare |
| Skills | 1 | 1 | 1 | 1 | 1 |
| GitHub stars | 9,418 | 461,751 | 148,352 | 96,757 | 73,156 |
| Last code change | Oct 14, 2026 | Nov 16, 2026 | Nov 16, 2026 | Nov 15, 2026 | Sep 15, 2026 |
| License | – | MIT | Apache-2.0 | Apache-2.0 | MIT |
1 skills (instruction sets) by eze-is that an AI reads and follows · not an MCP server
How a Skill differs from MCP
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Works with
Claude CodeCodexCursorGemini CLI
From the maker’s README and the folders in the repo
Install
Is it safe?
- Who made it
GitHub account eze-is (person), 7 years old
- Use and upkeep
★ 9,418 stars · code last changed Oct 14, 2026
- Any scripts?
18 scripts that can run on a computer: scripts/cdp-proxy.mjs, scripts/browser-discovery.mjs, scripts/browser-discovery.test.mjs, scripts/browser-probe.mjs and 14 more
- Uses the internet?
Scripts that go online: scripts/proxy-maintenance.mjs, scripts/check-deps.mjs, scripts/check-deps.test.mjs, scripts/cdp-proxy.mjs
- Changes machine-wide settings?
No hooks or writes to machine settings found
Checked automatically from the repo files at commit d173a75 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
First: which AI do you use?
Pick your app and this page shows only how to install it there
Option 1Upload to claude.ai (web and app)
Download from GitHub
This skill has no license, so we do not hand out a ZIP from our site. Download it from GitHub and arrange the folder yourself, or use "Let the AI install it" above, which is easier
Download from GitHub (whole repo) ↗
Unzip it, then zip only the web-access folder again. The ZIP must have a web-access folder with SKILL.md at the top level, no loose files
Open Skills on claude.ai and upload
+Create skillUpload a skillpick web-access.zip
No Upload button? Turn on file creation first
SettingsCapabilitiesCode execution and file creation
Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free
Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)
Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)
Checked against official docs Nov 12, 2026 · Source: support.claude.com, support.claude.com, code.claude.com
Option 1Let Claude Code install it
Copy this sentence and paste it into a Claude Code chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Restart Claude Code, then type /web-access or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
The maker’s recommended way
Install Node.js (if you don’t have it)
Already installed? Check first · Open Terminal, type this command and press Enter
node -v- A version number such as v26.13.1 = installed, skip this step
- "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
How to open Terminal
Mac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed
Open the Node.js download page ↗
When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v
Install once; it works for everything that needs Node.js
Checking the commands · copy buttons appear once they pass
Copied from the maker’s README; it downloads and runs the maker’s code
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.claude/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Restart Claude Code, then type /web-access or ask for a matching task and Claude picks it up
ChatGPT desktop app
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Option 1Let ChatGPT install it
Open Codex in the ChatGPT desktop app and paste this sentence into the chat
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Option 2Put the folder there yourself
Put the web-access folder at ~/.agents/skills/web-access
~ is your home folder ($HOME)
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
After installing
- ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
- To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
- Codex picks up newly installed skills by itself; if one does not show up, restart Codex
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
ChatGPT on the web and mobile
Skills you install yourself do not work here; only skills that come with a plugin from the directory
To use this skill with ChatGPT, use the ChatGPT desktop app as above
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Option 1Let Codex install it
Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Restart Codex, then ask for a matching task; Codex lists the skill
Option 1Let Cursor install it
Copy this sentence and paste it into a Cursor chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
In Cursor’s Agent chat, type / and pick web-access
Checked against official docs Nov 12, 2026 · Source: cursor.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.cursor/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
In Cursor’s Agent chat, type / and pick web-access
Option 1Let the AI install it
For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
For Terminal users
Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.
Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026
View the original SKILL.md
The text below comes from the maker’s repo, not from PopNx MCP
Showing the first 8,000 characters · Open the full file on GitHub
---
name: web-access
license: MIT
description: >
所有联网操作必须通过此 skill 处理,包括:搜索、网页抓取、登录后操作、网络交互等。
触发场景:用户要求搜索信息、查看网页内容、访问需要登录的网站、操作网页界面、抓取社交媒体内容(小红书、微博、推特等)、读取动态渲染页面、以及任何需要真实浏览器环境的网络任务。
metadata:
author: 一泽Eze
version: "2.6.0"
github: https://github.com/eze-is/web-access
---
# web-access Skill
## 前置检查
在开始联网操作前,先检查 CDP 模式可用性;已有连接优先复用:
```bash
node "${CLAUDE_SKILL_DIR}/scripts/check-deps.mjs"
```
**Node.js 22+** 必需(使用原生 WebSocket)。
脚本先读取 `/health`:已有服务且 `connected === true` 时,校验浏览器偏好后直接使用,不重新探测浏览器、不启动第二个 Proxy;已有服务但连接断开时,由原服务重新连接。只有没有可用服务时,才发现浏览器并启动后台 Proxy。
按脚本输出处理:
- `exit 0` → 直接调用 Proxy API,不再手动启动或重启 Proxy
- `exit 2` → 尚未设置浏览器、也没有可复用的共享服务,进入首次配置(见下)
- `exit 1` → 按 stdout 错误信息处理。若提示包含「Agent 处理顺序」,按其步骤执行(如先用系统命令打开浏览器后重跑),自动可解则不打扰用户;仍失败再向用户求助。「配置错误」只需改正配置,不要为此停止或重启共享服务
**浏览器 = 它的用户数据目录。** `~/.web-access/config.env` 的 `WEB_ACCESS_BROWSER` 存数据目录路径,即含 `Local State` 的那一层(如 `~/Library/Application Support/Dia/User Data`),任何 Chromium 内核浏览器都可以;旧值 `chrome` / `chrome-canary` / `chromium` / `edge` 仍有效,按平台对应到标准目录。日常运行只读该目录里的 `DevToolsActivePort`,连不上就报错,不换浏览器、不猜端口。`--browser <数据目录路径>` 表达本次临时覆盖(不写 config.env)。
**首次配置**:按 `exit 2` 的输出逐步做,步骤以脚本输出为准。要点:脚本只列出应用数据根目录的最外层文件夹名;由你从名字认出浏览器,再用 `browser-probe.mjs` 探测(它只接受根目录下的相对路径);无论找到几个都要问用户,再把选定的数据目录写入配置。已有健康的共享服务时,前置检查优先复用它,不会进入首次配置。
若调试端口文件不可读,脚本会报告 `EPERM/EACCES`,不要当成浏览器未开启调试。可在 `config.env` 用 `WEB_ACCESS_CDP_PORT` 为日常浏览器显式指定已核对的端口;端口归属由配置提供,不自动猜测,另一浏览器的 `--browser` 不借用此端口。
用户数据(`config.env` 与站点经验)位于用户目录下的 `~/.web-access/`(Windows 为 `%USERPROFILE%\.web-access\`),不在 skill 目录内,升级 skill 不受影响。旧版本存放在 skill 目录内的数据,由前置检查首次运行时自动复制过来,并输出一行 `user-data:` 说明。
Proxy 是全体 Agent 共用的长驻服务。普通任务不因修改代码、连接等待或任务结束重启服务。维护和切换浏览器使用跨平台的 Node 命令(将路径替换为实际 skill 路径):
```bash
node "${CLAUDE_SKILL_DIR}/scripts/proxy-maintenance.mjs" status
node "${CLAUDE_SKILL_DIR}/scripts/proxy-maintenance.mjs" restart
```
维护命令按实例身份停止服务;有执行中的请求、未完成的 CDP 命令、Agent 标签页或连接正在建立时会拒绝停止,等任务清理完再运行。切换浏览器时先执行 `proxy-maintenance.mjs stop`,成功后再运行 `check-deps.mjs --browser <数据目录路径>`(或改写 config.env 后运行)。旧版本没有维护接口时,命令会提示一次性迁移,不自动强杀。退出码与状态字段见 [API 参考](references/cdp-api.md)。
检查通过后并必须在回复中向用户直接展示以下须知,再执行站点操作:
```
温馨提示:部分站点对浏览器自动化操作检测严格,存在账号封禁风险。已内置防护措施但无法完全避免,Agent 继续操作即视为接受。
```
## 浏览哲学与工作流
**像人一样思考,兼顾高效与适应性的完成任务。**
执行任务时不会过度依赖固有印象所规划的步骤,而是带着目标进入,边看边判断,遇到阻碍就解决,发现内容不够就深入——全程围绕「我要达成什么」做决策。这个 skill 的所有行为都应遵循这个逻辑。
**① 拿到请求** — 先明确用户要做什么,定义成功标准:什么算完成了?需要获取什么信息、执行什么操作、达到什么结果?这是后续所有判断的锚点。
**② 选择起点** — 根据任务性质、平台特征、达成条件,选一个最可能直达的方式作为第一步去验证。一次成功当然最好;不成功则在③中调整。比如,需要操作页面、需要登录态、已知静态方式不可达的平台(小红书、微信公众号等)→ 直接 CDP
**③ 过程校验** — 每一步的结果都是证据,不只是成功或失败的二元信号。用结果对照①的成功标准,更新你对目标的判断:路径在推进吗?结果的整体面貌(质量、相关度、量级)是否指向目标可达?发现方向错了立即调整,不在同一个方式上反复重试——搜索没命中不等于"还没找对方法",也可能是"目标不存在";API 报错、页面缺少预期元素、重试无改善,都是在告诉你该重新评估方向。遇到弹窗、登录墙等障碍,判断它是否真的挡住了目标:挡住了就处理,没挡住就绕过——内容可能已在页面 DOM 中,交互只是展示手段。
**④ 完成判断** — 对照定义的任务成功标准,确认任务完成后才停止,但也不要过度操作,不为了"完整"而浪费代价。
## 联网工具选择
- **确保信息的真实性,一手信息优于二手信息**:搜索引擎和聚合平台是信息发现入口。当多次搜索尝试后没有质的改进时,升级到更根本的获取方式:定位一手来源(官网、官方平台、原始页面)。
| 场景 | 工具 |
|------|------|
| 搜索摘要或关键词结果,发现信息来源 | **WebSearch** |
| URL 已知,需要从页面定向提取特定信息 | **WebFetch**(拉取网页内容,由小模型根据 prompt 提取,返回处理后结果) |
| URL 已知,需要原始 HTML 源码(meta、JSON-LD 等结构化字段) | **curl** |
| 非公开内容,或已知静态层无效的平台(小红书、微信公众号等公开内容也被反爬限制) | **浏览器 CDP**(直接,跳过静态层) |
| 需要登录态、交互操作,或需要像人一样在浏览器内自由导航探索 | **浏览器 CDP** |
浏览器 CDP 不要求 URL 已知——可从任意入口出发,通过页面内搜索、点击、跳转等方式找到目标内容。WebSearch、WebFetch、curl 均不处理登录态。
**Jina**(可选预处理层,可与 WebFetch/curl 组合使用,由于其特性可节省 tokens 消耗,请积极在任务合适时组合使用):第三方网络服务,可将网页转为 Markdown,大幅节省 token 但可能有信息损耗。调用方式为 `r.jina.ai/example.com`(URL 前加前缀,不保留原网址 http 前缀),限 20 RPM。适合文章、博客、文档、PDF 等以正文为核心的页面;对数据面板、商品页等非文章结构页面可能提取到错误区块。
进入浏览器层后,`/eval` 就是你的眼睛和手:
- **看**:用 `/eval` 查询 DOM,发现页面上的链接、按钮、表单、文本内容——相当于「看看这个页面有什么」
- **做**:用 `/click` 点击元素、`/scroll` 滚动加载、`/eval` 填表提交——像人一样在页面内自然导航
- **读**:用 `/eval` 提取文字内容,判断图片/视频是否承载核心信息——是则提取媒体 URL 定向读取或 `/screenshot` 视觉识别
浏览网页时,**先了解页面结构,再决定下一步动作**。不需要提前规划所有步骤。
### 页面就绪与完成判断
`/new` 或 `/navigate` 返回,只代表浏览器完成了当前文档的基础加载,不代表用户需要的内容已经出现。HTTP 200、`document.readyState === "complete"`、页面标题出现或导航调用成功,都不能单独作为任务完成标准。
导航后先用 `/eval` 检查目标内容。若目标内容尚未出现,而页面仍是空白、加载态、验证页、登录跳转或其它可能继续变化的中间状态,在默认 15 秒窗口内持续观察 URL、标题和 DOM;页面发生跳转或内容变化后重新判断。只有目标内容已经获取,或观察窗口结束后仍存在明确阻碍,才能继续提取或报告失败。
站点经验可以提供更精确的选择器、等待条件和已知中间状态,但只用于加速判断;即使没有站点经验,也必须遵循上述目标内容就绪规则。
### 补充:本地浏览器资源
用户指向**本人访问过的页面**("我之前看的那个讲 X 的文章"、"上次打开过的 XX 面板")或**组织内部系统**("我们的 XX 平台"、"公司那个 YY 系统"等公网搜不到的目标)时,检索本地浏览器(Chrome / Edge)书签/历史:
```bash
node "${CLAUDE_SKILL_DIR}/scripts/find-url.mjs" [关键词...] [--only bookmarks|history] [--browser chrome|edge] [--limit N] [--since 1d|7h|YYYY-MM-DD] [--sort recent|visits]
```
(此处 `--browser` 是浏览器名,只支持 Chrome / Edge,与 check-deps 的数据目录写法不同。)
关键词空格分词、多词 AND,匹配 title + url(可省略);默认遍历所有已安装的 Chromium 系浏览器(Chrome、Edge),`--browser` 限定单一来源;`--since` / `--sort` 仅作用于历史;默认按最近访问倒序,`--sort visits` 按访问次数排序(适合"高频访问的网站"这类场景)。
### 程序化操作与 GUI 交互
浏览器内操作页面有两种方式:
- **程序化方式**(构造 URL 直接导航、eval 操作 DOM):成功时速度快、精确,但对网站来说不是正常用户行为,可能触发反爬机制。
- **GUI 交互**(点击按钮、填写输入框、滚动浏览):GUI 是为人设计的,网站不会限制正常的 UI 操作,确定性最高,但步骤多、速度慢。
根据对目标平台的了解来灵活选择方式。GUI 交互也是程序化方式的有效探测——通过一次真实交互观察站点的实际行为(URL 模式、必需参数、页面跳转逻辑),为后续程序化操作提供依据;同时当程序化方式受阻时,GUI 交互是可靠的兜底。
**站点内交互产生的链接是可靠的**:通过用户视角中的可交互单元(卡片、条目、按钮)进行的站点内交互,自然到达的 URL 天然携带平台所需的完整上下文。而手动构造的 URL 可能缺失隐式必要参数,导致被拦截、返回错误页面、甚至触发反爬。
## 浏览器 CDP 模式
通过 CDP Proxy 直连用户日常浏览器(Chrome、Edge、Brave、Arc、Dia 等任意 Chromium 内核浏览器),天然携带登录态,无需启动独立浏览器。
若无用户明确要求,不主动操作用户已有 tab,所有操作都在自己创建的后台 tab 中进行,保持对用户环境的最小侵入。不关闭用户 tab 的前提下,完成任务后关闭自己创建的 tab,保持环境整洁。
### 启动
```bash
node "${CLAUDE_SKILL_DIR}/scripts/check-deps.mjs"
```
脚本检查 Node.js 后先复用已有 Proxy;没有可用服务时才检查浏览器调试端口、自动启动并等待连接。Proxy 以脱离当前命令会话的后台进程持续运行,没有运行时长或空闲退出计时器。前置检查的等待超时只结束本次检查,不停止 Proxy。
`/health` 的 `status: "ok"` 表示服务在运行,`connected: true` 表示浏览器连接仍有效。浏览器退出、重启或撤销远程调试权限后,服务可继续运行,但重新连接可能需要浏览器再次授权;不要把服务存活当成连接有效。
### Proxy API
所有操作通过 curl 调用 HTTP API:
```bash
# 列出用户已打开的 tab
curl -s http://localhost:3456/targets
# 创建新后台 tab(自动等待加载)— URL 走 POST body,避免目标 URL 含 query 时被切分
curl -s -X POST --data-raw 'https://example.com' http://localhost:3456/new
# 页面信息
curl -s "http://localhost:3456/info?target=ID"
# 执行任意 JS:可读写 DOM、提取数据、操控元素、触发状态变更、提交表单、调用内部方法
curl -s -X POST "http://localhost:3456/eval?target=ID" -d 'document.title'
# 捕获页面渲染状态(含视频当前帧)
curl -s "http://localhost:3456/screenshot?target=ID&file=/tmp/shot.png"
# 导航(URL 走 POST body,target 走 query)、后退
curl -s -X POST --data-raw 'https://example.com' "http://localhost:3456/navigate?target=ID"
curl -s "http://localhost:3456/back?target=ID"
# 点击(POST body 为 CSS 选择器)— JS el.click(),简单快速,覆盖大多数场景
curl -s -X POST "http://localhost:3456/click?target=ID" -d 'button.submit'
# 真实鼠标点击 — CDP Input.dispatchMouseEvent,算用户手势,能触发文件对话框
curl -s -X POST "http://localhost:3456/clickAt?target=ID" -d 'button.upload'
# 按视口坐标真实点击 — 可点中跨站 iframe 里的元素,不激活标签页
curl -s "http://localhost:3456/clickXY?target=ID&x=120&y=90"
# 页面里的 iframe — 列出 frameId(跨站 iframe 标 crossProcess),再在其中执行 JS
curl -s "http://localhost:3456/frames?target=ID"
curl -s -X POST "http://localhost:3456/eval?target=ID&frame=FRAME_ID" -d 'document.body.innerText'
# 文件上传 — 直接设置 file input 的本地文件路径,绕过文件对话框
curl -s -X POST "http://localhost:3456/setFiles?target=ID" -d '{"selector":"input[type=file]","files":["/path/to/file.png"]}'
# 滚动(触发懒加载)
curl -s "http://localhost:3456/scroll?target=ID&y=3000"
curl -s "http://localhost:3456/scroll?target=ID&direction=bottom"
# 关闭 tab
curl -s "http://localhost:3456/close?target=ID"
```
### 页面内导航
两种方式打开页面内的链接:
- **`/click`**:在当前 tab 内直接点击用户视角中的可交互单元,简单直接,串行处理。适合需要在同一页面内连续操作的场景,如点击展开、翻页、进入详情等。
- **`/new` + 完整 URL**:使用目标链接的完整地址(包含所有URL参数),在新 tab 中打开。适合需要同时访问多个页面的场景。
很多网站的链接包含会话相关的参数(如 token),这些参数是正常访问所必需的。提取 URL 时应保留完整地址,不要裁剪或省略参数。URL 通过 POST body 原样传入 `/new` 或 `/navigate`。
> **v2.5.3 迁移提示**:若引用的站点经验文件(`~/.web-access/site-patterns/*.md`)或其它脚本中仍含 `GET /new?url=...` 或 `/navigate?target=...&url=...` 的旧写法,调用会收到迁移指引。按 [`references/migration-2.5.3.md`](references/migration-2.5.3.md) 就地改写为 POST body 后再使用,并顺手把该站点经验文件更新掉。
### 媒体资源提取
判断内容在图片里时,用 `/eval` 从 DOM 直接拿图片 URL,再定向读取——比全页截图精准得多。
### 技术事实
- 页面中存在大量已加载但未展示的内容——轮播中非当前帧的图Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
From GitHub
- GitHub stars
- 9,418
- Maker
- eze-is
- License
- Not stated
- Last code change
- Oct 14, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 1