dogfood
π―Skillfrom vercel-labs/agent-browser
Systematically explores and tests web applications to find bugs, UX issues, and other problems.
Overview
Dogfood is a skill from the Vercel Labs agent-browser project that systematically explores and tests web applications to find bugs, UX issues, and other problems. It produces a structured QA report with full reproduction evidence including step-by-step screenshots, repro videos, and detailed reproduction steps for every discovered issue.
Key Features
- Systematic Exploratory Testing - Methodically navigates web applications, visiting pages and testing features to discover issues
- Full Reproduction Evidence - Captures screenshots, records videos, and documents detailed reproduction steps for every finding
- Structured Report Generation - Produces organized QA reports using a template with summary counts, categorized issues, and reproduction details
- Authentication Support - Handles login flows including OTP/email codes, with saved session state for reuse
- Agent-Browser Powered - Uses the fast Rust-based agent-browser CLI with snapshot/act pattern for efficient browser automation
Who is this for?
This skill is for development teams who want automated QA and exploratory testing of their web applications. It is particularly useful for product teams that need thorough bug hunting with evidence-backed reports that can be handed directly to responsible teams, replacing or supplementing manual QA testing workflows.
Same repository
vercel-labs/agent-browser(9 items)
Installation
npx vibeindex add vercel-labs/agent-browser --skill dogfoodnpx skills add vercel-labs/agent-browser --skill dogfood~/.claude/skills/dogfood/SKILL.mdSKILL.md
More from this repository8
Automates web browsing tasks by navigating websites, extracting content, interacting with elements, and capturing screenshots programmatically
A browser automation CLI for AI agents by Vercel Labs, enabling website navigation, form filling, button clicking, screenshot capture, and data extraction through simple commands.
Headless browser automation for AI agents
A concise, practical guide for creating specialized skills that extend Claude's capabilities with domain-specific knowledge and workflows.
Skill for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Connects to running Electron apps and controls them programmatically.
Skill from agent-browser, a headless browser automation CLI for AI agents with a fast Rust binary and Node.js fallback for cross-platform support.
Skill
Skill