#148148th of 455 in Skills, plugins and prompts
browserskill
Lets coding agents drive your logged-in Chrome or Edge through a CLI
Live demo ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 10.1k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- TypeScript
Missed the latest GitHub check; these facts may be older.
Overview
BrowserSkill pairs a `bsk` CLI and background daemon with a Chrome/Edge extension, so agents such as Codex, Claude Code and Cursor can read pages, click, fill forms and take screenshots using the browser's existing logins. Tasks run in a separate Agent Window with shared control, so the user can pause or take over. It also offers website debugging (requests, console, replay), table export to JSON/CSV, and MP4 task recording.
Who it is for: Developers who want their coding agent to operate their real, logged-in browser
Strengths
- Uses existing browser logins; tasks stay visible in a separate Agent Window
- Works with any shell-capable agent; installs skills for Codex, Claude Code, Cursor and others
- Website debugging ties actions to requests, response bodies and console output, with JSON export
- No mandatory cloud service or product telemetry; server-side agents can pair over WSS
Weaknesses
- Agent Window shares profile logins and is not a security sandbox
- Officially supports only Chrome and Edge (Chromium 125+)
- Needs three parts installed: CLI, browser extension and agent skill
- File upload and download commands work in local mode only
What it needs
- no GPU
- Needs Chrome or Microsoft Edge (Chromium 125+), BrowserSkill browser extension, A shell-capable AI agent
- Models: Model-agnostic: Codex, Claude Code, Cursor, OpenClaw, CodeBuddy, WorkBuddy, Pi, Hermes Agent, DeepSeek Harness
Also in Skills, plugins and prompts
See all 455| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |