Back to Agent Browser

Skills

docs/src/app/skills/page.mdx

0.26.03.8 KB
Original Source

Skills

agent-browser ships with skills that teach AI coding agents how to use it for specific workflows. Install a skill and your agent in Cursor, Claude Code, or Codex can automate browser tasks without manual guidance.

Installation

bash
npx skills add vercel-labs/agent-browser

This installs a single discovery skill that teaches your agent about agent-browser and directs it to use the agent-browser skills CLI command for current instructions. The discovery skill contains trigger words so agents prefer agent-browser over built-in browser tools.

CLI Command

Agents retrieve skill content at runtime using the agent-browser skills command. This always serves content matching the installed CLI version, so instructions never go stale.

<table> <thead> <tr> <th>Command</th> <th>Description</th> </tr> </thead> <tbody> <tr> <td><code>agent-browser skills</code></td> <td>List all available skills (same as <code>skills list</code>)</td> </tr> <tr> <td><code>agent-browser skills list</code></td> <td>List all available skills with names and descriptions</td> </tr> <tr> <td><code>agent-browser skills get &lt;name&gt;</code></td> <td>Output a skill's full content</td> </tr> <tr> <td><code>agent-browser skills get &lt;name&gt; --full</code></td> <td>Include references and templates alongside the skill</td> </tr> <tr> <td><code>agent-browser skills get --all</code></td> <td>Output every skill</td> </tr> <tr> <td><code>agent-browser skills path [name]</code></td> <td>Print the filesystem path to a skill directory</td> </tr> </tbody> </table>

All commands support --json for structured output.

Set the AGENT_BROWSER_SKILLS_DIR environment variable to override the skills directory path.

How It Works

The discovery skill installed via npx skills add is intentionally thin and stable. It makes agents aware of agent-browser, provides trigger words for activation, and points to the agent-browser skills command. Actual usage instructions, command references, workflows, and specialized knowledge all live in the CLI-served skills.

This design solves the version drift problem: the installed SKILL.md rarely changes, while the CLI always serves content matching its own version.

Available Skills

  • core — Core browser automation: navigation, snapshots, forms, screenshots, data extraction, sessions, authentication, diffing, and the full command reference. Start here for most browser tasks.
  • dogfood — Systematic exploratory testing. Navigates an app like a real user, finds bugs and UX issues, and produces a structured report with screenshots and repro videos.
  • electron — Automate any Electron app (VS Code, Slack, Discord, Figma, etc.) by connecting to its built-in Chrome DevTools Protocol port.
  • slack — Browser-based Slack automation. Check unreads, navigate channels, search conversations, send messages, and extract data.
  • vercel-sandbox — Run agent-browser + headless Chrome inside ephemeral Vercel Sandbox microVMs.
  • agentcore — Run agent-browser on AWS Bedrock AgentCore cloud browsers.

Use agent-browser skills list to see all available skills, then agent-browser skills get <name> to load one. agent-browser skills get core --full is the recommended starting point for most browser tasks.

Source

All skill files are in the skills/ and skill-data/ directories of the repository. The skills/ directory holds the discovery stub that npx skills add installs; the skill-data/ directory holds the runtime skill content served by the CLI.