Menu
SkillsMP has collected 10 skills from kerpopule/hermes-jev-skills. Open a skill to review its source and details.
Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/kerpopule/hermes-jev-skills.A collection that uses TypeSafe’s Jev decision model for model routing, search-result selection, memory filtering, turn selection, Skill selection, mailbox sorting and browser or desktop action choices. Jev answers typed questions with choices, scores or probabilities; the host carries out the work.
For Hermes model routing, the README recommends starting with /jev routing shadow: record decisions before allowing them to switch models.
The package requires Python 3.9 or newer and a TypeSafe API key. The installer detects supported Hermes, Claude Code and Codex installations; some integrations are specific to Hermes.
Jev is a cloud API. Depending on the feature, redacted user turns, passage excerpts or action labels leave the machine; profiles handling text that must stay local need the documented private_profiles setting. Action choices are limited to the candidate actions supplied by the host. Jev does not write the final prose.
Sources
aigeeknews recommends hermes-jev-skills for routine decisions such as model routing, screening search results, checking content, selecting Skills and routing email. The post introduces a multi-Skill repository and cites the project’s evaluation results.
Showing 10 of 10 collected 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.
Use to pick the cheapest model that is good enough for a turn — choosing a model, delegating a sub-task to a sub-agent, cutting model spend, or setting up and tuning Jev routing pools.
Use when unsure which of many installed skills applies to a request, if any, or when asked to make skill loading cheaper or more accurate. Jev ranks the whole catalog and may say no skill is needed.
Use when driving a desktop GUI through a computer-use driver — windows, menus, native apps, OS dialogs. You build a table of safe actions; Jev picks the next one in about 0.4 seconds.
Use on a mailbox export to sort mail into needs reply, updates, promotional, sales and spam — which messages are addressed to the person at all. For a support queue use jev triage.
Use when a transcript has to be cut to a fixed size and you must choose which turns go. Jev marks each turn keep, summarize or drop. Measured: it does not make a handoff better.
Use when Jev is not working yet, a Jev tool reports no_key or auth_failed, or the person asks to connect or fix Jev. Gets their TypeSafe or OpenRouter key into the secret store, unseen by you.
Use on passages a search just returned (memory, vault, session history, wiki, web) before reading them in. Jev ranks them, drops the irrelevant, and flags prompt injection hidden in the text.
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.
Use when a task is already judged hard — pick which paid frontier seat takes it, then keep Jev watching the delegated run so it interrupts you only when the run needs a decision.