jev-browser-use
Agent skill fromkerpopule/hermes-jev-skills
Use when driving a web page in a browser — clicking, typing, navigating, logged-in or JS-rendered pages. Jev picks each step from the elements observed, under a host allowlist and a step budget.
How to install jev-browser-use
install jev-browser-use
# install the hermes-jev-skills pack with the skills CLI
npx skills add kerpopule/hermes-jev-skills# or add only this skill to Claude Code: copy the folder
skills/jev-browser-use/
# into
~/.claude/skills/jev-browser-use/ (all projects)
.claude/skills/jev-browser-use/ (one project)
1# Browser use with Jev23If a plain HTTP fetch can read it, fetch it and leave the browser alone. This skill is for pages that need interaction.45Jev never writes selectors, code or coordinates. It picks one operation and one target from the list of elements your browser tool observed. There are two ways to run it.67## A. Your own browser tool + `jev choose` (works everywhere)89Same loop as `jev-computer-use`, with page elements as regions:10111. **Observe.** Read the page as an element list (accessibility tree, `read_page`, a snapshot). Keep role and a short label per element; leave page text out.122. **Build the table.** One row per action you would be willing to take now: `click-r12`, `type-email-r7`, `scroll-down`, `back`, plus the mandatory `reobserve` and `abstain`. Text to type is decided by you and lives in your row, not in the request.133. **Ask:** `jev choose < request.json` (Hermes: `jev_choose_action`). Schema `jev.action_choice_request_v1`; see `jev-computer-use` for the shape.144. **Do that one action, observe again, verify.** Never retry a browser mutation blindly: look first.15…
Excerpt shown under the repository's MIT license.
