skills.rest
POWERFULMOVES
POWERFULMOVESCOMMUNITY
Explore all skills by this author →
GitHub

PMOVES Model Registry

Catalog, discover, and enrich PMOVES.AI models with HuggingFace data and TensorZero exports.

6|Updated Aug 26, 2025
Search Tags:#catalog#registry#gpu#model#enrichment#huggingface#tensorzero
One-click install
npx skills add https://github.com/POWERFULMOVES/PMOVES.AI --skill pmoves-model-registry
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: PMOVES Model Registry
Source: https://github.com/POWERFULMOVES/PMOVES.AI/tree/main/pbnj/pinokio/api/pmoves-model-registry
Command: npx skills add https://github.com/POWERFULMOVES/PMOVES.AI --skill pmoves-model-registry

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

PMOVES Model Registry provides a centralized system to query, discover, and enrich the PMOVES.AI model catalog. It coordinates model metadata (LLM, embedding, TTS, vision), HuggingFace enrichment, TensorZero TOML export, and GPU deployment tracking across the fleet.

Core Features & Use Cases

  • List models and fetch detailed metadata for editing or auditing.
  • Enrich models with HuggingFace data and export TensorZero configuration for deployment.
  • Track and manage GPU deployments across the PMOVES fleet.

Quick Start

List all models in the catalog and trigger HuggingFace enrichment for ones lacking metadata.

Frequently Asked Questions about PMOVES Model Registry

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I catalog and enrich LLM and embedding models with HuggingFace metadata?▼

You can catalog and enrich models by querying the Supabase-backed registry to fetch detailed metadata, then triggering HuggingFace API enrichment to populate missing data for LLMs, embeddings, TTS, and vision models.

What is the best way to export TensorZero TOML configurations for GPU deployment?▼

Exporting TensorZero TOML configurations involves querying the model catalog, enriching model metadata with HuggingFace data, and generating the TOML files needed to coordinate and track GPU deployments across the fleet.

Can I track GPU deployments using a Supabase model registry?▼

Yes, the Supabase-backed model registry allows you to track and manage GPU deployments across the fleet by centralizing model metadata and TensorZero export configurations in one catalog.

How do I list all models in a catalog and identify ones lacking metadata?▼

You can list all models in the catalog to audit existing entries, then identify and trigger HuggingFace enrichment specifically for models that are lacking detailed metadata.

Does the model registry support vision and TTS models or only LLMs?▼

The model registry supports multiple model types, allowing you to apply cataloging, discovery, and HuggingFace enrichment across LLMs, embeddings, TTS, and vision models for comprehensive fleet management.

Related Skills

Explore More Software Engineering Skills→
ironkid90ironkid90

supabase

Manage Supabase database migrations, authentication, and real-time updates.

Community
Intermediate
pmcdowallpmcdowall

serving-llms-vllm

Configure vLLM deployments with OpenAI-compatible APIs and performance tuning.

Community
Advanced
nrakownrakow
1

new-source-onboarding

Onboard new data sources through ingestion, staging, testing, documentation, and lineage phases.

Community
Advanced
NVIDIA-TAONVIDIA-TAO
83

tao-run-inference-service

Deploy TAO inference microservices on Docker, Brev, Slurm, or Kubernetes.

Official
Advanced