# browser-act/skills

Browser automation CLI built for AI agents. Break through anti-bot walls, hand off to humans across platforms when stuck. Parallel multi-task execution, independent multi-session operation, isolated multi-account browsing.

Repository: https://github.com/browser-act/skills
Canonical: https://ross.abutalabs.com/products/browser-act-skills
Homepage: https://www.browseract.com/?co-from=github
Language: Python
License: MIT
License Family: permissive
Topics: ai-agents, automation, claude-code, claude-code-skills, cursor, no-code, openclaw, openclaw-skills, web-scraping, web-scraping-api, data-extraction, web-data-extraction, claude-cli, claude-skills, codex, codex-cli, codex-skill, openclaw-cli, openclaw-skill, agent-infrastructure
Last push: 2026-08-24T14:56:52+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 14
- inputs: {"age_days": 208, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5446, forks 267 (observed 2026-08-28T04:09:18.129406+00:00)

## What it is
BrowserAct Skills is a Python-based browser automation CLI designed for AI agents, providing real-browser control with anti-bot evasion (stealth fingerprints, TLS rotation, residential proxies, CAPTCHA solving), human handoff, and isolated multi-account/multi-session browsing. It complements the BrowserAct Cloud platform, which builds reusable no-code scraping bots from natural-language prompts.

## Use cases
- scrape product listings and prices from e-commerce sites with an AI agent
- bypass anti-bot walls and CAPTCHAs when collecting web data
- run parallel browser automation tasks with isolated accounts
- hand off a stuck browser task to a human operator
- reuse local Chrome login state for authenticated scraping sessions
- build a reusable web scraper from a natural-language prompt without code
- extract structured data from JavaScript-rendered pages into CSV or JSON

## When to choose
- you need AI agents to drive a real browser with anti-bot evasion and session isolation
- you want no-code, reusable scraping bots managed in the cloud
- you need multi-account browsing with fingerprint-proxy stability
- you want to integrate browser automation into Claude Code, Cursor, or Codex workflows

## When to avoid
- you need a lightweight HTTP-only scraper without browser overhead
- you require fully self-hosted infrastructure with no cloud dependency or credit-based pricing
- your target sites permit simple API access instead of browser automation
- you need strict offline operation

## Facets
- artifact type: cli-tool
- maturity: active
- function: web-scraping, browser-extension, agent-framework, workflow-automation, data-generation, cli
- domain: crawlers, developer-tools, web-development
- platform: python, cli, cross-platform, cloud
- tags: browser-automation, anti-bot-bypass, captcha-solving, stealth-fingerprinting, residential-proxies, claude-code-skills, human-handoff, multi-account-isolation, ai-agent-tools, no-code-scraping, ai-agents, automation

## Member repositories
- browser-act/skills (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:18.129406+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:56:50.803679+00:00, confidence not recorded.
  - readme: https://github.com/browser-act/skills (fetched 2026-08-28T04:09:18.129406+00:00, sha 2c440152a495)
  - homepage: https://www.browseract.com/?co-from=github (fetched 2026-08-29T08:52:02.555803+00:00, sha c636eb39d6d3)
  - site_page: https://docs.browseract.com/ (fetched 2026-08-29T08:52:02.566935+00:00, sha 0b40318bfde9)
  - site_page: https://www.browseract.com/about-us (fetched 2026-08-29T08:52:02.568798+00:00, sha 9429395ef6be)
  - site_page: https://www.browseract.com/pricing (fetched 2026-08-29T08:52:02.565046+00:00, sha 22aa05185e7e)
- Data as of 2026-08-30T08:39:29.467469+00:00.