
Customizes an autorater (evaluation metric) for an AI agent so its grades match the user's own judgment, starting from the agent's real traj
- Open source
- 24.4K GitHub stars
- AI models and LLM tooling

Customizes an autorater (evaluation metric) for an AI agent so its grades match the user's own judgment, starting from the agent's real traj

Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology

Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMa

Manages and orchestrates prompts in Agent Platform

Configures Google Cloud API Gateway to act as a remote Model Context Protocol (MCP) server (Public Preview) that exposes REST APIs as agent

Stands up an Apigee API proxy that a Google Cloud Agent Gateway calls as an ext-proc (Service Extension) callout on an agent's LLM traffic,

Automates the end-to-end detection engineering workflow in Google SecOps using MCP tools

Manages custom Agent resources on Gemini Enterprise Agent Platform

Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI, Google Cloud, or Agent Platform

Guides the usage of Gemini Interactions API on Gemini Enterprise Agent Platform

Generates a Gemini LiveAPI client service class in the user's chosen programming language

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the

Plan and coordinate the deployment of a model to Amazon SageMaker AI

Pick the right serving container for a SageMaker model deployment and find its current image URI

Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare

Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware

Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, do

Build Gradio web UIs and demos in Python

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructur

Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA

Publish and manage research papers on Hugging Face Hub

Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/dataset

Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loadi

Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help

Track and visualize ML training experiments with Trackio

Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3,

AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex

Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex