Hugging Face Skills

Add descriptions for new models from the HuggingFace router to chat-ui configuration. Use when new models are released on the router and need descriptions…

Fixes broken typing checks detected by ty, make typing, or make check-repo. Use when typing errors appear in local runs, CI, or PR logs.

Review code changes for bugs and alignment with OpenEnv principles and RFCs. Use when reviewing PRs, checking code before commit, or when asked to review…

Provides guidance for writing, optimizing, and benchmarking C++ CPU kernels with SIMD intrinsics (AVX2/AVX512) for the Hugging Face kernels ecosystem. Includes…

Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers…

Deploy an OpenEnv environment to Hugging Face Spaces. Use when asked to deploy, push to Hugging Face, or update a space.

Example fixture skill for action smoke tests

Generate OpenEnv environments from a concrete use case (for example, "generate an env for the library textarena"). Use when asked to design or implement a new…

Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing repositories, models, datasets, and Spaces on the Hugging Face Hub. Replaces now…

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

Discover the user's local AWS context (active profile, region, account ID, caller identity) at the start of any AWS task. Use this skill before any other AWS…

Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be…

Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on…

Ensure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training…

Create a SageMaker endpoint (real-time or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a…

Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a…

Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio…

Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub

Generate Hugging Face Hub (huggingface_hub) release notes from cached PR JSON files. Use when asked to draft release notes from PR files.

Diagnose and recover failing or stuck Hugging Face Space deployments for OpenEnv environments. Use when deploying envs from `envs/` to the Hub (`openenv`…

Execute Hugging Face Hub operations using the `hf` CLI. Use when the user needs to download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run compute jobs on HF infrastructure. Covers authentication, file transfers, repository creation, cache operations, and cloud compute.

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.

Run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with tokens, secrets management, timeout configuration, and result persistence. Designed for general-purpose compute workloads including data processing, inference, experiments, batch jobs, and any Python-based tasks.

Train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on dataset preparation, hardware selection, cost estimation, and model persistence.

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.

Build reusable scripts and tools using the Hugging Face API. Useful when chaining or combining API calls, or when tasks will be repeated/automated. Creates reusable command line scripts to fetch, enrich, or process data from Hugging Face Hub.

Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.

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

Add evaluation results to Hugging Face model repositories using the .eval_results/ format. Uses HF CLI for PR management and manual YAML creation.

Trains and fine-tunes object detection models (D-FINE, RT-DETR v2, DETR, YOLOS) using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers…

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

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

Finds the best models for a task by querying official HF benchmark leaderboards, enriching results with model size data, filtering for what fits on the user's device, and returning a comparison table with benchmark scores.

Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between…

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

Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.

This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection,…

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO,…

Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact…

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo,…

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating…

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

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

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. This is especially useful…

Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or…

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

AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring…

Make tests pass. Invoke after /write-tests produces failing tests.

Start and test the prime-rl inference server. Use when asked to run inference, start vLLM, test a model, or launch the inference server.

How to install prime-rl and its optional dependencies. Use when setting up the project, installing extras like deep-gemm for FP8 models, or troubleshooting…

Use when adding a new model or pipeline to diffusers, setting up file structure for a new model, converting a pipeline to modular format, or converting weights…

Post-mortem analysis of a PhysicsIntern workspace run (Claude Code, Pi, or Codex host). Reconstructs the trajectory from the session JSONL(s), audits…

OpenEnv CLI (`openenv`) for scaffolding, validating, building, and pushing OpenEnv environments.

Validate changes before submitting a pull request. Run comprehensive checks including lint, tests, alignment review, and RFC analysis. Use before creating a…

Release workflow for deploying OpenEnv environments to Hugging Face Spaces and keeping canonical references in sync.

Determine if proposed changes require an RFC. Use when planning significant changes, before starting major work, or when asked whether an RFC is needed.

Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3,…

Refactor code after tests pass. The "Refactor" phase of Red-Green-Refactor.

Work on a batch of GitHub issues in parallel using Agent Teams. Creates one worktree per issue with TDD enforcement, coordinates via a lead agent, then…

Use when debugging or verifying numerical parity between pipeline implementations (e.g., research repo vs diffusers, standard vs modular). Also relevant when…

How to write and use TOML configs in prime-rl. Use when creating config files, running commands with configs, or overriding config values via CLI.

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity,…

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation,…

Convert Hugging Face transformers language models to MLX format for Apple Silicon inference. Use when asked to convert a model from transformers to MLX, port a…

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training…

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training…

Update documentation across the repo after API changes. Finds stale references in docs, examples, docstrings, and fixes them.

Monitor a PR's CI checks and Greptile code review after submission. Polls CI status, auto-fixes failures via ralph-loop, waits for Greptile review, addresses…

Start work on a GitHub issue. Extracts requirements, creates worktree, sets up TDD workflow.

Write failing tests from requirements. Invoke for each todo before /implement.

Provides guidance for writing, optimizing, and benchmarking Triton kernels for Intel XPU GPUs (Battlemage/Arc Pro B50) using the Xe-Forge optimization…