agent-browser
Use the agent-browser CLI to exercise web interfaces, inspect rendered accessibility state, verify interactions, and capture screenshots. Use for browser-based UI testing and evidence collection. Do not use as a substitute for deterministic Playwright coverage when an automated regression test is the requested deliverable.
- Installs
- 65
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/emdash-cms/emdash --skill agent-browser- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads agent-browser automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Test interfaces with agent-browser
Use the installed agent-browser CLI for rendered, user-facing verification. Load its version-matched instructions before relying on command syntax:
agent-browser skills get core --full
Use a specialized bundled guide when the target requires one. agent-browser skills list shows the available guides.
Verification loop
- Start or identify the target application and record the exact URL and viewport.
- Open the page in a named session.
- Take an accessibility snapshot and identify controls by role, label, or snapshot reference.
- Perform the user action.
- Wait for the resulting state, then take a fresh snapshot. References can become stale after navigation or a substantial DOM update.
- Verify the observable result, console errors, and relevant network behavior.
- Capture screenshots when visual evidence helps establish the result.
For EmDash admin testing, authenticate through the development bypass rather than attempting to automate passkeys:
agent-browser open 'http://localhost:4321/_emdash/api/setup/dev-bypass?redirect=/_emdash/admin'
Use auth/dev-bypass instead when setup is already complete.
Interaction guidance
- Prefer role and label locators when they express the user-facing control clearly. Use snapshot references for efficient exploration.
- Re-snapshot after a dialog opens, a route changes, or content is replaced.
- Wait for a selector or visible state instead of adding a fixed delay unless timing itself is under test.
- Use a named session for flows that depend on cookies or storage. Close sessions that are no longer needed.
- Check
agent-browser consoleandagent-browser errorswhen the UI behaves unexpectedly. - Use
agent-browser network requestswhen the result depends on a request or response boundary.
Evidence
Record the path tested, inputs, viewport, expected result, actual result, and any console or request failures. For UI changes, capture before-and-after screenshots of every affected screen.
Save screenshots inside the task workspace with descriptive filenames. Inspect the saved image before reporting success; a completed screenshot command does not prove that the intended state was visible.
Browser exploration does not replace a regression test when stable automated coverage can protect the behavior. Convert a confirmed defect into the narrowest meaningful automated test when the task includes implementation.
FAQ
What does the agent-browser skill do?
Use the agent-browser CLI to exercise web interfaces, inspect rendered accessibility state, verify interactions, and capture screenshots. Use for browser-based UI testing and evidence collection. Do not use as a substitute for deterministic Playwright coverage when an automated regression test is the requested deliverable.
How do I install agent-browser?
Run npx skills add https://github.com/emdash-cms/emdash --skill agent-browser in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/agent-browser/ (personal) or .claude/skills/agent-browser/ (project).
Which AI agents can use agent-browser?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is agent-browser safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains agent-browser?
It is published by emdash-cms in emdash-cms/emdash. It has 65 recorded installs.
More from emdash-cms/emdash
emdash-cli
emdash-cms/emdash
Use the EmDash CLI to inspect and manage an EmDash instance from the command line, including content, schema, media, taxonomies, menus, search, authentication, seeds, migrations, generated types, and whole-site export and import.
creating-plugins
emdash-cms/emdash
Create EmDash CMS plugins with sandboxed hooks, routes, storage, content and media APIs, MCP tools, and declarative admin UI, or native React and Astro extensions. Use when scaffolding or implementing an EmDash plugin.
wordpress-plugin-to-emdash
emdash-cms/emdash
Open the skill to read its SKILL.md instructions.
wordpress-theme-to-emdash
emdash-cms/emdash
Open the skill to read its SKILL.md instructions.
Popular productivity & automation skills
agent-browser
vercel-labs/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.
lark-doc
open.feishu.cn
飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；/page/ 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。