laya SKILL.md skillB

laya from jzkk720/cubecloud-skills-bundle-kit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jzkk720/cubecloud-skills-bundle-kit/laya@git:20260930.5d224cb

Pins git:20260930.5d224cb in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
jzkk720/cubecloud-skills-bundle-kit
Path
upstream/laya/SKILL.md
Versions recorded
1
Latest version
git:20260930.5d224cb, committed Sep 30, 2026
Size
15,687 bytes
Repository stars
4
License
a license file GitHub does not identify

Add fast, LOCAL, typed decisions to any project with Laya, an open-source non-generative decision model. Runs offline via `pip install laya`; classifies, routes, scores and answers yes/no questions about a piece of text, returning calibrated probabilities in ~20-35 ms on a laptop GPU, no LLM call, no data leaving the machine. Also use it when the user mentions Jev, a "System 1 model", "typed decisions" or a "decision model" for LOCAL/offline use, even if they never name Laya. Use when: routing…

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

# Integrating Laya

Laya answers typed questions about a piece of text. You give it a `state` (the text) and a dict
of questions; it returns a probability for every option of every question in one forward pass.
It never generates text, so it cannot answer off-schema, and it is small enough (322M-421M
parameters) to run inside the user's own process.

Reach for it when the project needs a **decision**, not a sentence: which queue, is this spam,
how urgent, should the agent stop. Do not reach for it when the task needs reasoning over
several steps, arithmetic, extraction of free-form values, or any generated text. For those,
keep the LLM and use Laya in front of it as a cheap first pass (see "Cascade" below).

## Install and first call

```bash
pip install laya        # pulls torch, transformers, safetensors, huggingface_hub
```

```python
import laya

agent = laya.load("convaiinnovations/laya")          # English checkpoint

result = agent.predict(
    {"subject": "Charged twice", "body": "Refund the duplicate today or we cancel."},
    {
        "department": {
            "type": "choice",
            "instructions": "Which department should handle this request?",
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jzkk720/cubecloud-skills-bundle-kit/laya@sha256:8f084373e6c99348

The line at the top of this page pins the label git:20260930.5d224cb, 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_nweezixpsuqqocxa.svg)](https://markdownregistry.com/a/art_nweezixpsuqqocxa)

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

Versions

The registry has recorded 1 version of this file, committed on Sep 30, 2026.

versioncommittedcommitsizeaudit
git:20260930.5d224cb latest2026-09-30 5d224cb 15,687 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No link to a raw IP address (matched: http://127.0.0.1:8770)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (15687 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 script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

jzkk720/cubecloud-skills-bundle-kit · 4 stars · license a license file GitHub does not identify · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_nweezixpsuqqocxa
GET https://markdownregistry.com/api/v1/resolve?ref=jzkk720/cubecloud-skills-bundle-kit/laya
GET https://markdownregistry.com/api/v1/blob/8f084373e6c9934892e881cadfbc1bc726faaf136de4a6c2ab1cbe79dca57e13

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.

More from jzkk720/cubecloud-skills-bundle-kit

AGENTS.md AGENTS.md file
jzkk720/cubecloud-skills-bundle-kit · AGENTS.md
git:20261102.dfe6aa7 · audit A · 4 stars
agent-reach SKILL.md skill
jzkk720/cubecloud-skills-bundle-kit · upstream/agent-reach/SKILL.md · MUST USE when user wants to research/search/look up/find anything on the internet — e.g. "research this topic", "do a…
git:20260922.391e00a · audit A · 4 stars
airunway-aks-setup SKILL.md skill
jzkk720/cubecloud-skills-bundle-kit · upstream/airunway-aks-setup/SKILL.md · Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU…
v1.1.1 · audit A · 4 stars
anti-slop SKILL.md skill
jzkk720/cubecloud-skills-bundle-kit · upstream/anti-slop/SKILL.md · Anti-AI-slop design and copy rules for any UI work (website, web app, or interface). Use whenever building, refining…
v1.0 · audit A · 4 stars
archify SKILL.md skill
jzkk720/cubecloud-skills-bundle-kit · upstream/archify/SKILL.md · Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable…
v2.17 · audit A · 4 stars
aris-idea-creator SKILL.md skill
jzkk720/cubecloud-skills-bundle-kit · upstream/aris-idea-creator/SKILL.md · Generate and rank research ideas given a broad direction. Use when user says "brainstorm ideas", "generate research…
git:20260723.723e6c6 · audit A · 4 stars
aris-novelty-check SKILL.md skill
jzkk720/cubecloud-skills-bundle-kit · upstream/aris-novelty-check/SKILL.md · Verify research idea novelty against recent literature. Use when user says "novelty check", "check novelty", "has…
git:20260723.723e6c6 · audit A · 4 stars
aris-research-lit SKILL.md skill
jzkk720/cubecloud-skills-bundle-kit · upstream/aris-research-lit/SKILL.md · Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related…
git:20260723.723e6c6 · audit A · 4 stars
book-to-skill SKILL.md skill
jzkk720/cubecloud-skills-bundle-kit · upstream/book-to-skill/SKILL.md · Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW) into structured agent skills…
v1.0 · audit A · 4 stars
crucible SKILL.md skill
jzkk720/cubecloud-skills-bundle-kit · upstream/crucible/SKILL.md · Three-phase plan hardening — supersedes /grill-me-codex and /grill-with-docs-codex. PHASE 0 RECON — Claude scouts the…
git:20260817.87a6498 · audit A · 4 stars
design-md-library SKILL.md skill
jzkk720/cubecloud-skills-bundle-kit · upstream/design-md-library/SKILL.md · Curated library of 74 real-world DESIGN.md files (Google Stitch spec) extracted from sites like Apple, Stripe, Linear…
git:20260719.023c906 · audit A · 4 stars
diagram-design SKILL.md skill
jzkk720/cubecloud-skills-bundle-kit · upstream/diagram-design/SKILL.md · Create branded architecture, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane…
v2.5 · audit A · 4 stars

Every file in jzkk720/cubecloud-skills-bundle-kit

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