agentleFS
Sign inStart free
GastonGelhornGastonGelhorn/jevmate/skills/setup/SKILL.md

setup

Skill1 starsChanged 39 days agoMITView on GitHub

Set up jev on this machine: where its judge runs (Ollama here, Ollama on another machine such as a Mac on Tailscale, or an API key for TypeSafe or OpenRouter), checked end to end.

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run jev doctor and say in one line where the judge runs now and whether it answered.

    line 11
  2. Very specific:

    If the remote one cannot be reached, pass on the hint the command prints: Ollama there listens only on 127.0.0.1 unless it sets …

    line 23

“Common” is measured: kept by at least 6 in 10 of the 171 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Set jev up. Never ask the person to paste an API key into the chat, and never run a command that contains one.

  1. Run jev doctor and say in one line where the judge runs now and whether it answered.
  2. Unless the person already said, ask where it should run (one question):
    • local: Ollama 0.35+ on this machine. Free and private, about a second a check.
    • remote: Ollama on another machine they reach, such as a Mac on their Tailscale network or a box on the LAN. Ask for its address: host, host:port or URL.
    • typesafe or openrouter: a hosted API with a key. The fastest; the text jev judges leaves this machine.
    • keep: as it is.
  3. Apply it with jev setup, which prepares the judge and makes one real decision through it:
    • local: jev setup --judge local --yes; remote: jev setup --judge remote --url <address> --yes. --yes makes tev1-32k from tev1 when only tev1 is there (no download). When tev1 is missing the command says so: ask before adding --pull, a 4.5 GB download on that machine. If the remote one cannot be reached, pass on the hint the command prints: Ollama there listens only on 127.0.0.1 unless it sets OLLAMA_HOST=0.0.0.0, and it has no password, so only on a private network.
    • typesafe or openrouter: when jev doctor showed no key, tell the person to run jev auth set <key> in their own terminal (TypeSafe keys at console.typesafe.ai, OpenRouter keys start with sk-or-), then run jev setup --judge typesafe or jev setup --judge openrouter. The plugin's settings (/config, jev section) take the key too; it is written to the key file at the next session start.
    • keep: jev setup --judge keep.
  4. Report the last lines: backend, model and round-trip time. Every tool on this machine that runs jev shares that backend (Shelflife's memory, if installed, among them).
  5. Offer the three commands that pay first: jev sift before reading, jev tests on a change, jev session for what it saved.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free