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#
npx skills add vercel-labs/agent-browserThis 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.
| Command | Description |
|---|---|
agent-browser skills | List all available skills (same as skills list) |
agent-browser skills list | List all available skills with names and descriptions |
agent-browser skills get <name> | Output a skill's full content |
agent-browser skills get <name> --full | Include references and templates alongside the skill |
agent-browser skills get --all | Output every skill |
agent-browser skills path [name] | Print the filesystem path to a skill directory |
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.