
from mini-browser30
A compact browser CLI for agents to navigate pages, take screenshots, scrape text, fill forms, click elements, and record screencasts via Chrome DevTools Protoc
Mini Browser (mb) provides a unix-style CLI for browser automation that connects to Chrome over the DevTools protocol. It exposes small commands (go, text, shot, snap, fill, click, record, audit, js) which let an agent observe pages, interact with elements by coordinates or selectors, run JS, and produce screenshots or recordings.
Use this skill when an agent needs to browse the web programmatically: automated testing, content scraping, visual audits, filling and submitting forms, capturing screenshots or screencasts, or running small JS snippets in page context. It's ideal for agents that prefer CLI-style primitives for navigation and interaction.
Best with code-capable agents that can call shell binaries and manage Chrome/CDP such as Copilot/Codex-style agents, Claude Code, or any agent with shell/CLI access and a headless/remote Chrome instance.
mini-browser (mb) is a CLI-based browser automation skill for agents using Chrome DevTools Protocol via puppeteer-core. No bundled scripts — the skill is purely a SKILL.md that documents the npm-installed `mb` CLI. Well-written documentation with clear command reference, usage patterns, and troubleshooting. No security concerns beyond the inherent risk of `mb js` allowing arbitrary JS execution, which is by design.
Clean skill with no scripts to audit. Pure documentation skill pointing to an external npm package. The skill would benefit from a references/ directory for extended examples and clearer output contracts beyond the --json flag mention.