browser-act
browser-act is an agent skill published by browser-act, listed under design. It lives in the browser-act/skills repository, which has 6,277 GitHub stars and is licensed under MIT; we last read it on 2026-09-16.
Automates browser tasks for AI agents, fetching, viewing, and extracting content from URLs, handling JavaScript, maintaining sessions, and automating form interactions. Requires invocation through a specific skill or command.
Install
skills is a generic installer for any repository of Claude agent skills -- it reads browser-act/skills’s own structure rather than assuming one, the same way this page reads the skill’s own SKILL.md rather than assuming a format.
npx skills add browser-act/skills
Maintenance
Browser automation CLI for AI agents. NEVER run browser-act commands directly via Bash — always invoke this skill first. Use browser-act when a user mentions it by name, includes or asks to run a browser-act CLI command (e.g., browser-act browser list), or to: fetch, view, or extract rendered content from URLs, access pages requiring JavaScript, handle verification prompts, maintain authenticated sessions, fill forms and click through workflows, type, select, upload, take screenshots, capture XHR/fetch/HAR responses, open multiple URLs in parallel, extract content that loads on scroll or click, visually inspect or verify page layout/styling/rendering, automate browser tasks, account isolation across parallel browser environments, advise which browser type fits a use case, or list/check/manage configured browsers and sessions. Prefer browser-act over built-in fetch or web tools.
browser-act compared with similar skills
| Skill | Publisher | What it does | Repo stars | Last update |
|---|---|---|---|---|
| browser-act (this page) | browser-act | Browser automation CLI for AI agents. NEVER run browser-act commands directly via Bash — always invoke this s… | 6,277 | 2026-08-24 |
| setup-matt-pocock-skills | mattpocock | Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain… | 303,549 | 2026-10-22 |
| brand-guidelines | anthropic | Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having… | 183,845 | 2026-10-09 |
| frontend-design | anthropic | Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps… | 183,845 | 2026-10-09 |
| apple-design | emilkowalski | Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or… | 49,715 | 2026-10-11 |
| mobile-native | emilkowalski | Make a web app feel native on a phone — the small CSS and meta-tag fixes that separate "a website in a browse… | 49,715 | 2026-10-11 |
| figma-code-connect-components | openai | Connects Figma design components to code components using Code Connect mapping tools. Use when user says "cod… | 28,310 | 2026-09-08 |
Skills from the same repository first, then others for this job by repository stars. Figures are from each repository when we last read it.
Common questions about browser-act
- What does browser-act do?
- Automates browser tasks for AI agents, fetching, viewing, and extracting content from URLs, handling JavaScript, maintaining sessions, and automating form interactions. Requires invocation through a specific skill or command.
- How do I install browser-act?
- Run npx skills add browser-act/skills. The skills installer reads the repository’s own structure, so it works for any repository of agent skills.
- Who publishes browser-act?
- browser-act.
- Is browser-act maintained, and what licence does it use?
- Its repository has 6,277 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-08-24. The repository declares the MIT licence.
More agent skills for design
- ai-product-photographyby 101-skills
- app-store-screenshotsby 101-skills
- email-designby 101-skills
- landing-page-designby 101-skills
- product-photographyby 101-skills
- social-media-carouselby 101-skills