Tooluck logoTooluck
SKILL.md

jev-search

Agent skill fromkerpopule/hermes-jev-skills

Use after any web or API search, before opening results or spending another round. Jev picks which results to read, whether the evidence is enough, and which query to run next from ones you wrote.

How to install jev-search

install jev-search
# 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-search/

# into

~/.claude/skills/jev-search/ (all projects)

.claude/skills/jev-search/ (one project)

skills/jev-search/SKILL.md

MITFull file
1# Searching with Jev
2
3A research turn is usually three decisions and one piece of writing:
4
5- which of the results to actually open (the other thirty are noise),
6- whether what has been read answers the question, or another round is needed,
7- which query to run next.
8
9Those are picks and a yes/no. Jev answers them in about half a second for a fraction of a cent, and the expensive model is left to do the writing — which is the only part of this Jev cannot do. **Jev never writes a query.** You write the candidates; Jev picks one or says none of them would add anything.
10
11`jev search` runs one round of that loop and hands back the decision. Use it instead of guessing, and instead of burning a frontier turn on "should I search again?".
12
13## Do this
14
151. Search the way you always do (`web_search`, an API, a site). Give it the question, and write two to five candidate queries for the next round if this one is not enough.
162. Run one round:
17
18 ```bash
19 echo '{"question":"what does the decision API cost",
20 "queries_tried":["decision model pricing"],
21 "candidate_queries":["typesafe pricing page","decision api rate limits","free tier"],
22 "round_index":1,
23 "results":[{"id":"a","title":"...","url":"https://...","snippet":"..."}]}' | jev search
24 ```
25
26 Or call the `jev_search` tool with the same fields.
27
283. Read `decision` and do exactly that:
29
30| `decision` | What it means | What you do |
31|---|---|---|
32…

Excerpt shown under the repository's MIT license.

More skills in hermes-jev-skills

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

pbakaus /

impeccable
108k

The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.

2 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates