一键导入
browser-skill
Use a real browser to navigate the web, see pages visually, and interact with elements.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use a real browser to navigate the web, see pages visually, and interact with elements.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
Interact with companion devices (phones, laptops, headless servers) connected to Suzent.
Render rich interactive UI surfaces (tables, forms, cards, buttons) in the sidebar canvas or inline in chat using the render_ui tool.
Become a helpful co-worker in the workspace. Use it whenever you need to access, manage, or reference files.
Access and maintain the notebook knowledge base with Obsidian markdown conventions.
Create a new Suzent AgentSkill, or improve an existing one. Use when the user wants to author a skill from scratch, scaffold a SKILL.md with supporting scripts/references/assets, or refine a skill's description so it triggers reliably.
Install a Suzent AgentSkill from a Git repo, ZIP URL, or owner/repo GitHub shorthand. Use when the user wants to add a third-party or community skill to Suzent. Fetches and copies only; never executes fetched code at install time.
| name | browser-skill |
| description | Use a real browser to navigate the web, see pages visually, and interact with elements. |
The Browser Skill allows you to control a real, headless Chrome browser instance. This is useful for:
open <url> to navigate.snapshot -i to get a list of interactive elements with ID references (e.g., @e1).click @e1fill @e1 "search query"press @e1 Enter| Command | Arguments | Description |
|---|---|---|
open | <url> | Navigate to a URL. |
back | - | Go back in history. |
forward | - | Go forward in history. |
reload | - | Refresh the page. |
snapshot | ['-i'] | Get a semantic list of interactive elements (@e refs). |
click | <ref>|<selector> | Click an element (e.g., @e1). |
dblclick | <ref>|<selector> | Double-click an element. |
fill | <ref>|<selector> <text> | Clear and fill an input field. |
type | <ref>|<selector> <text> | Type text naturally (useful for auto-complete). |
press | <ref>|<selector> <key> | Press a specific key (e.g., Enter, ArrowDown). |
hover | <ref>|<selector> | Hover over an element. |
scroll | [dx, dy] | Scroll the viewport (default: down). |
click_coords | <x> <y> | Click at specific coordinates. |
snapshot -i before interacting to get fresh @e references.@e references are ephemeral and may change after navigation or dynamic updates.fill for standard forms, type for complex inputs reacting to keystrokes.