Autobrowse
Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser automation skills for specific website tasks.
Install
/plugin marketplace add browserbase/skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add browserbase/skills --skill autobrowsegit clone --depth 1 https://github.com/browserbase/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/autobrowse ~/.claude/skills/autobrowsePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# AutoBrowse — Self-Improving Browser Skill
Build reliable browser automation skills through iterative experimentation. An inner agent browses the site (`evaluate.ts`). You — the outer agent — read what happened and improve the instructions (`strategy.md`). Repeat until it passes consistently.
## Entry Points
Invocation is flexible — both explicit flags and free-form natural language work:
```
/autobrowse --task google-flights
/autobrowse --task google-flights --iterations 10 --env remote
/autobrowse --task google-flights --browser-trace
/autobrowse --tasks google-flights,amazon-add-to-cart
/autobrowse --all
# Also fine — parse freely:
/autobrowse https://flights.google.com/
/autobrowse book a flight on delta.com
/autobrowse fix the existing google-flights skill
```
`--browser-trace` (default off, remote-only): pairs each iteration with the sibling `browser-trace` skill — wraps the inner agent in a CDP capture for per-page network/console/page-lifecycle evidence. Implies `--env remote`; errors if combined with `--env local`. Requires the sibling `browser-trace` skill present at `${CLAUDE_SKILL_DIR}/../browser-trace/`, and the `BROWSERBASE_API_KEY` env var.
When the user drops a URL or free-form instruction instead of `--task <name>`:
- If an existing task in `${WORKSPACE}/tasks/` clearly matches the site/intent, use it.Details
- Skill name
autobrowse- Repository
- browserbase/skills
- Path
skills/autobrowse/SKILL.md- Repo updated
- 17 November 2026
- Copies
- Found in 2 GitHub repos
FAQ
What does the Autobrowse skill do?
Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser automation skills for specific website tasks.
How do I install the Autobrowse skill?
Claude Code plugin: /plugin marketplace add browserbase/skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Autobrowse popular?
It lives in browserbase/skills, which has 3,757 GitHub stars and 239 forks.
Related skills
Browser
3.8kbrowserbase/skills
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. Supports remote Browserbase sessions with Browserbase Identity, Verified browsers, automatic CAPTCHA solving, and residential proxies — ideal for protected websites and JavaScript-heavy pages.
Browser to API
3.8kbrowserbase/skills
Turn a website's observable HTTP traffic into a best-effort OpenAPI 3.1 spec by analyzing a `browser-trace` capture. Use when the user wants to discover/extract API endpoints from a browser session, build an OpenAPI doc from network traffic, or document a third-party site's XHR/fetch surface for client integration.
Browser Trace
3.8kbrowserbase/skills
Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page summaries back into an agent loop so its next iteration learns from the last one.
Gtm Engineering
7.2ktech-leads-club/agent-skills
When the user wants to build GTM automation with code, design workflow architectures, use AI agents for GTM tasks, or implement the 'architecture over tools' principle. Also use when the user mentions 'GTM engineering,' 'GTM automation,' 'n8n,' 'Make,' 'Zapier,' 'workflow automation,' 'Clay API,' 'instruction stacks,' 'AI agents for GTM,' or 'revenue automation.' This skill covers technical GTM infrastructure from workflow design through agent orchestration. Do NOT use for technical implementation, code review, or software architecture.
1start Mathmodel
6.4kjihe520/MathModelAgent
数学建模竞赛工作流入口。用于启动完整建模流程:询问用户偏好,生成 plan.md 和 todo.md,并按阶段调用赛题分析、建模、代码与图表、流程图、论文撰写、验证验收等 skills。
Meeting Minutes
13kgenspark-ai/genoffice
Turn a transcript, chat log or loose notes into structured meeting minutes with decisions and action items, delivered as a Word document
Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.