Skip to content
cccskills
FreePublished on GitHub

opencli

Operate websites and Electron apps through CLI commands, reusing Chrome login sessions. Prefer over browser_task for supported sites (GitHub, Bilibili, Twitter/X, YouTube, etc.) — deterministic commands with structured JSON output.

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md2.3 KB
  • agents/openai.yaml298 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

OpenCLI - 网站 CLI 操作

通过 OpenCLI 将网站和 Electron 应用转化为 CLI 命令。 复用用户 Chrome 登录态,无需输入密码,返回结构化 JSON。

核心优势

  • 复用 Chrome 登录态 — 无需密码/token,直接用已登录的 Chrome
  • 确定性命令 — 比 browser_task 的 "让 LLM 猜" 可靠得多
  • 结构化 JSON 输出 — LLM 解析零歧义

何时使用 OpenCLI(优先于 browser_task)

场景推荐工具原因
操作有 adapter 的网站(GitHub、Bilibili 等)opencli_run确定性命令,JSON 输出
需要登录态的操作opencli_run复用 Chrome 登录
无 adapter 的网站browser_task / 手动 browser_*OpenCLI 不支持的站点
简单读取网页内容web_fetch无需浏览器

工具

opencli_list — 发现可用命令

opencli_list()

opencli_run — 执行命令

命令格式: <site> <subcommand>,直接传给 opencli。

opencli_run(command="zhihu hot list")
opencli_run(command="hackernews top")
opencli_run(command="bilibili video info", args=["BV1xx411c7XW"])

opencli_doctor — 诊断环境

opencli_doctor()

前置条件

  1. 安装 opencli: npm install -g @jackwener/opencli
  2. Chrome 浏览器正在运行并已登录目标网站
  3. Browser Bridge 扩展已安装(首次运行 opencli setup 配置)

决策路径

需要操作网站?
├─ 目标网站有 opencli adapter → opencli_run(首选)
├─ 需要登录但无 adapter → browser_task → 手动 browser_click/type 组合
├─ 只需读取内容 → web_fetch
└─ 只需搜索 → web_search

相关技能

  • browser_task — 无 adapter 时的降级方案
  • browser_navigate — 简单导航
  • web_fetch — 轻量 URL 内容获取
  • web_search — 搜索引擎查询

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Record important information to long-term memory for learning user preferences, successful patterns, and error lessons. When you need to remember user preferences, save successful patterns, or record lessons from errors.

The English summary is being prepared. Showing the original description.

openakita/openakita2KUpdated Sep 24, 2026

Click page elements by CSS selector or text content. When you need to click buttons, links, or select options. PREREQUISITE - must use browser_navigate to open target page first.

The English summary is being prepared. Showing the original description.

openakita/openakita2KUpdated Sep 24, 2026

Extract page content and element text from current webpage. When you need to read page information, get element values, scrape data, or verify page content.

The English summary is being prepared. Showing the original description.

openakita/openakita2KUpdated Sep 24, 2026

List all open browser tabs with their index, URL and title. When you need to check what pages are open, manage multiple tabs, or find a specific tab to switch to.

The English summary is being prepared. Showing the original description.

openakita/openakita2KUpdated Sep 24, 2026

Navigate browser to specified URL to open a webpage. When you need to open webpages or start web automation. PREREQUISITE - must call before browser_click/type operations. Auto-starts browser if not running.

The English summary is being prepared. Showing the original description.

openakita/openakita2KUpdated Sep 24, 2026

Open new browser tab and navigate to URL (keeps current page open). When you need to open additional page without closing current, or multi-task across pages. PREREQUISITE - must confirm browser is running first.

The English summary is being prepared. Showing the original description.

openakita/openakita2KUpdated Sep 24, 2026

See all skills by openakita

Report a problem with this skill