AGENT SKILL

sero-browser

Use when a user asks to open, browse, capture, screenshot, or record a website/page; mentions browser tabs, visible Browser panel, screen recording, web navigation, website interaction, or browser automation; or when choosing between `sero browser`, `sero app record`, and `automation_browser`.

License 许可
Apache-2.0
所属仓库
sero-labs/sero
最近更新
2026-11-10
Stars
★ 28
Forks
4

01 前言 Front Matter

name
sero-browser
description
Use when a user asks to open, browse, capture, screenshot, or record a website/page; mentions browser tabs, visible Browser panel, screen recording, web navigation, website interaction, or browser automation; or when choosing between `sero browser`, `sero app record`, and `automation_browser`.

02 资源文件 1

03 SKILL.md 正文

Sero Browser

Use the visible Sero Browser panel for user-facing web browsing and recordings. Use hidden automation only when the user explicitly asks for headless/runtime browser automation or when testing a locally running app.

Visible browser workflow

  • Prefer sero-cli for visible browser tasks.
  • Start by showing the panel: sero browser show.
  • Navigate the current tab with sero browser goto <url>.
  • Use sero browser open <url> only when the user asks for a new tab/window or multiple pages side-by-side.
  • If unsure what tabs exist, run sero browser list before opening anything new.
  • For page text/content, prefer sero browser get-text over screenshots.
  • To move the visible page, use sero browser scroll --amount <px> or sero browser scroll --direction up --amount <px>; do not use sero app scroll for Browser pages.
  • Use sero browser screenshot only when visual evidence is needed.

Recording workflow

For prompts like “record the browser while opening a site”:

  1. sero browser show
  2. sero browser goto <initial-url>
  3. sero app record start
  4. Continue navigation with sero browser goto <next-url> or sero browser navigate <tab-id> <url>
  5. After the final navigation completes, wait 3–5 seconds for the page to render.
  6. Run sero app record stop as its own separate command.

You may batch browser show, initial navigation, app record start, and intermediate browser goto commands when that is convenient. Do not include app record stop in the same multi-command invocation as the final browser goto, because the recording can stop before the last page renders.

Do not use sero app screenshot --app web or open the web app for browser pages. The web app/plugin is separate from the Sero Browser panel.

Single-tab rule

  • Keep one browser tab for a single browsing task.
  • Do not repeatedly call sero browser open during one task.
  • After the first tab exists, use goto to reuse the active tab.
  • Use navigate <tab-id> <url> only when you intentionally selected a tab from sero browser list.

Hidden automation browser

automation_browser is hidden. It does not create visible tabs and is not captured by sero app record / sero app screenshot.

Use automation_browser for:

  • testing a locally running app,
  • taking hidden automation screenshots,
  • verifying DOM interactions when no visible recording is requested.

Do not use automation_browser for user-facing browsing or visible screen recordings.

Common routing examples

  • “Open BBC News, record the browser, go to Sport, then Football, then Premier League Table” → visible browser workflow; one tab; use goto for each navigation; wait 3–5 seconds after the table page loads, then stop app recording in a separate command.
  • “Take a screenshot of this website” → sero browser show, sero browser goto <url> if needed, then sero browser screenshot.
  • “Test my local web UI with clicks and assertions” → local dev server + automation_browser is acceptable unless the user asks for visible recording.

04 同仓库更多 Skills

sero-labs
sero-labs/sero

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

测试与质量Skill与智能体开发
★ 28
sero-labs
sero-labs/sero

skill-creator

Guide for writing and improving Sero skills. Use when the user wants to create a new skill, rewrite an existing one, or turn a repeated piece of work into reusable procedural knowledge for the agent.

内容创作者写作与文案Skill与智能体开发
★ 28
sero-labs
sero-labs/sero

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

设计师前端开发视觉设计
★ 28
sero-labs
sero-labs/sero

sero-humanize

Use to draft, edit, or audit Sero application content, including UI copy, documentation, README text, and release notes. Use unslop for regular chat and status reports instead. Not for code review or creative and promotional writing.

内容创作者代码审查
★ 28
sero-labs
sero-labs/sero

sero-plugin

Create Sero plugins — self-contained packages with a Pi extension (agent tools/commands), an optional React UI loaded via Module Federation, and an optional background runtime. Use when the user asks to create a Sero plugin/app/extension, add a sidebar panel, dashboard widget, or agent-integrated feature, or convert a Pi extension into a Sero plugin. Trigger on phrases like "create a plugin", "new Sero app", "add a tool with UI", "build an extension", "convert this Pi extension", or any request that touches `plugins/sero-*-plugin/`.

Skill与智能体开发
★ 28
sero-labs
sero-labs/sero

sero-dashboard-ui

Build, redesign or standardise Sero dashboard widgets and compact plugin views using the shared @sero-ai/ui dashboard components. Use when the user asks to create, restyle, clean up or make consistent a dashboard widget or a data-dense plugin view. Trigger on phrases like "dashboard widget", "widget for the dashboard", "restyle this widget", "make the widget consistent", "compact plugin view", or any work under a plugin's `ui/widgets/`.

设计师数据分析师分析与可视化
★ 28