AutoBrowse — self-improving browser automation skill

Prerequisites: Node.js 18+, the browse CLI, and an ANTHROPIC_API_KEY (each iteration burns real API calls); a Browserbase account for remote mode (paid cloud browsers) — the skill is guidance the agent follows, not software Install "AutoBrowse — self-improving browser automation skill" for me. It gives my agent @browserbase's auto-research loop: an inner agent browses a site via the browse CLI while the outer agent reads traces, forms one evidence-grounded hypothesis per iteration, and rewrites strategy.md until the task passes reliably — multi-task parallel runs, optional CDP-traced mode, and a graduation step that turns a converged strategy into a self-contained Claude Code skill. IMPORTANT: no LICENSE file was detected in the repo (frontmatter states MIT) — fetch from the link only, and reproduce nothing beyond the link. Repository: https://github.com/browserbase/skills/blob/main/skills/autobrowse/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "autobrowse". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. install the browse CLI, set ANTHROPIC_API_KEY, pick a task or URL to train; nothing else — it's a methodology). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.