typesafe-ai-dsh SKILL.md skillA

typesafe-ai-dsh from perrylink/jevcore is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add perrylink/jevcore/typesafe-ai-dsh@git:20260920.dbfada3

Pins git:20260920.dbfada3 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
perrylink/jevcore
Path
packages/dsh/skills/typesafe-ai-dsh/SKILL.md
Versions recorded
3
Latest version
git:20260920.dbfada3, committed Sep 20, 2026
First version recorded
Sep 20, 2026
Size
8,124 bytes
Repository stars
103
License
Apache-2.0

Use TypeSafe Jev for narrow judgments inside DeepSeek Harness — routing, classifying, scoring, verifying, reranking — instead of spending a model turn on them. Load this when a task turns on a decision with a small, fixed set of outcomes, or when you need a calibrated probability rather than prose.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Jev in DeepSeek Harness

Jev is a System One decision model. It does not write prose, explain, or generate
code. It answers typed questions and returns calibrated probabilities.

That constraint is the whole point: a judgment with a small, fixed answer set does
not need a model turn, and paying for one is the most common waste in an agent
loop.

## When to reach for it

Use Jev when **all** of these hold:

- the outcome is one of a small set you can name in advance;
- you need a probability, a ranking, or a yes/no, not text;
- you will branch on the answer in code.

Typical shapes: which of these N tools is relevant; is this result relevant to the
task; does this evidence support this claim; which team owns this ticket; how
risky is this operation; which of these two sources is more authoritative.

Do **not** use it to summarize, explain, draft, translate, or reason
step-by-step. Those need a generative model, and Jev will return a selection where
you wanted a sentence.

## The three primitives

| Primitive | Answers | Returns |
|---|---|---|
| `noul` | yes/no | probability of true |
| `choice` | one of a named set | the selection plus a distribution |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add perrylink/jevcore/typesafe-ai-dsh@sha256:429a288ee51ac4b3

The line at the top of this page pins the label git:20260920.dbfada3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_eikydqkeohgwlqf2.svg)](https://markdownregistry.com/a/art_eikydqkeohgwlqf2)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, all committed on Sep 20, 2026.

versioncommittedcommitsizeaudit
git:20260920.dbfada3 latest2026-09-20 dbfada3 8,124 BA view · diff
git:20260920.7bf54892026-09-20 7bf5489 3,969 BA view · diff
git:20260920.7dc7a3f2026-09-20 7dc7a3f 3,614 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8124 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

perrylink/jevcore · 103 stars · license Apache-2.0 · pushed 2026-11-09 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_eikydqkeohgwlqf2
GET https://markdownregistry.com/api/v1/resolve?ref=perrylink/jevcore/typesafe-ai-dsh
GET https://markdownregistry.com/api/v1/blob/429a288ee51ac4b3e249550e6144c90891b497143160932d52a8b4d928432ee1

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

Browse by kind, by grade A, or by owner.