Jev

What it does

When your agent uses it

• The user runs /jev

Example prompts

• “/jev”

Requirements

• A credential in TYPESAFE_API_KEY

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Ask every independent question in one request (speculative fan-out).
2. 2Keep control flow, weights, and side effects in code.
3. 3Gate on confidence for Choice/Score; gate on the probability for Noul.
4. 4Do not reuse a Noul threshold on a Choice.
5. 5Send only the state the questions need. Point at fields with ticket.messages[0].text .
6. 6A second HTTP call is only for true dependencies (next options or next state cannot be built yet).
7. 7Pin jev-1.13.0 if thresholds were tuned against that version; jev-latest moves.

What it can do on your machine

Read from SKILL.md and the folder at commit c636087. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are http and json).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • api.typesafe.ai

  Also links to:

  • docs.typesafe.ai

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • TYPESAFE_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Jev loads about 708 tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 245 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~56

When it runs · the whole SKILL.md, loaded when a task matches

~708

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cobusgreyling/Jev at commit c636087, republished under its MIT licence (© cobusgreyling). 245 words, ~708 tokens.

name

jev

description

Use TypeSafe Jev for typed judgments (Choice, Score, Noul) instead of asking a chat model to classify. Pair with a generative model for prose. Use when classifying, routing, scoring, guardrailing, or the user runs /jev.

POST https://api.typesafe.ai/v1/systemone
Authorization: Bearer $TYPESAFE_API_KEY

{
  "state": "I was charged twice. Please refund the duplicate today.",
  "model": "jev-latest",
  "questions": {
    "department": {
      "type": "choice",
      "instructions": "Which team should handle this?",
      "criteria": {
        "billing": "Payments and refunds",
        "technical": "Bugs or integrations",
        "other": "Neither fits"
      }
    },
    "refund_requested": {
      "type": "noul",
      "instructions": "Does the message request a refund?"
    },
    "urgency": {
      "type": "score",
      "instructions": "How time-sensitive is this?",
      "criteria": ["No deadline", "Within a week", "Today or sooner"]
    }
  }
}

© cobusgreyling, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/jev of cobusgreyling/Jev.

Open the folder on GitHubat commit c636087