Individual skill
ego-jev
Entry point for every browser task in ego (ego lite, ego-browser) — load this instead of the `ego-browser` skill: it starts by running `ego-browser skill`, the guide that skill points to. Multi-step clicking (fill known values into a form, set filters, open a row/card/menu by name, reach a page via nav or site search) runs on Jev, one ~0.4 s typed decision per step instead of an LLM turn. Reading, extraction, screenshots, login and free text stay plain ego calls.
skills/ego-jev/SKILL.md
Source commit 783fc69e514b33ba5f358d3f68f040681608df8d
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- Yes
- Skill scan complete
- Yes
- Observed behavior
- Not checked yet
- Last checked
- Nov 7, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 17
- Repository last updated
- Oct 23, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- browser-automation Repository topic
- claude-skills Repository topic
- codex-skills Repository topic
- skill-md Repository topic
- ego-lite Repository topic
- typescript Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 11,007 bytesreference.mddoc · 17,395 bytesscripts/backend.test.tsruns · 21,498 bytesscripts/debug-report.tsruns · 8,423 bytesscripts/fixture-800x600.pngasset · 2,789 bytesscripts/jev-loop.test.tsruns · 36,242 bytesscripts/jev-loop.tsruns · 67,519 bytesscripts/record.test.tsruns · 17,484 bytesscripts/record.tsruns · 11,198 bytesscripts/selftest.mjsruns · 6,788 bytesscripts/types.tsruns · 1,436 bytes
Read excerpt
# ego-jev
ego executes; Jev decides. Each step: snapshot → number the interactive
elements (a11y refs `@N` + DOM-discovered clickables `dN`: `div` cards,
`cursor:pointer`, iframe/shadow content) → one System One call picks the
operation and its target together → ego clicks/fills/selects. Jev never writes
text and never sees a screenshot by default; `screenshot: true` opts into the
image path in [Run](#run).
Requires: [ego lite](https://lite.ego.app/) installed and onboarded (provides
the `ego-browser` command, whose Node 24 runtime loads the `.ts` scripts
directly — no build step), the `ego-browser` skill, and `TYPESAFE_API_KEY` or
`AI_GATEWAY_API_KEY` resolvable in that runtime (see [backend and keys](reference.md#backend-and-keys)).