jev-evidence-eval SKILL.md skillA
jev-evidence-eval from laguagu/jev-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add laguagu/jev-skills/jev-evidence-eval@git:20260928.aef8bb2Pins git:20260928.aef8bb2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- laguagu/jev-skills
- Path
skills/jev-evidence-eval/SKILL.md- Versions recorded
- 6
- Latest version
- git:20260928.aef8bb2, committed Sep 28, 2026
- First version recorded
- Sep 20, 2026
- Size
- 2,376 bytes
- Repository stars
- 3
- License
- MIT
Evaluates TypeSafe Jev evidence and classification workflows for accuracy, review coverage, latency and cost. Use when testing citation or support checks, building a labelled test set or eval harness for Jev decisions, choosing or validating confidence thresholds, or comparing a Jev workflow with a classifier, cross-encoder or LLM before adopting it.
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
# Evaluate decisions against evidence Use the current [TypeSafe API](https://docs.typesafe.ai/api) and [confidence guide](https://docs.typesafe.ai/confidence) when implementing requests. Define the claim and candidate passages; keep expected labels outside model state. Use a Noul for whether a passage fully supports a claim, or a Choice when code must distinguish support, contradiction and silence. Include entity, time, qualifiers and scope. Missing evidence is not a denial. Copy receipts from source spans in code; a verbatim receipt establishes provenance, not correctness. Measure retrieval coverage separately from the judgments on retrieved passages. Include ordinary cases, missing facts, contradictions, negation, different entities, numerical mismatches, dropped conditions, changes from allowed to required, valid inferences and instructions embedded in documents. Keep synthetic fixtures public and customer inputs private. Sweep thresholds on development cases and freeze the policy before testing unseen cases. Report accuracy on accepted cases together with review rate, coverage and errors per category. …
Read the whole file at its exact version.
How to install
mdr add laguagu/jev-skills/jev-evidence-eval@sha256:23b8ec52b18e6169The line at the top of this page pins the label git:20260928.aef8bb2, 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.
[](https://markdownregistry.com/a/art_t2f3hffpqh4jwmtr)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Sep 20, 2026 and Sep 28, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260928.aef8bb2 latest | 2026-09-28 | aef8bb2 | 2,376 B | A | view · diff |
| git:20260927.7c5bbbd | 2026-09-27 | 7c5bbbd | 2,253 B | A | view · diff |
| git:20260927.a0bfebe | 2026-09-27 | a0bfebe | 4,095 B | A | view · diff |
| git:20260927.aef4e76 | 2026-09-27 | aef4e76 | 3,315 B | A | view · diff |
| git:20260922.f88ccdf | 2026-09-22 | f88ccdf | 2,684 B | A | view · diff |
| git:20260920.c66fb6e | 2026-09-20 | c66fb6e | 2,372 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2376 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
laguagu/jev-skills · 3 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_t2f3hffpqh4jwmtr GET https://markdownregistry.com/api/v1/resolve?ref=laguagu/jev-skills/jev-evidence-eval GET https://markdownregistry.com/api/v1/blob/23b8ec52b18e61693f88b07a6b76e7d8c4df981b2293311174021a96a4246053
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.