huggingface

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or…

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for…

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 SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding…

Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`,…

Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on…

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 models by benchmark scores. Triggers on: "best model for X", "what model should I use for", "top models for [task]",…

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

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, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan,…

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 environment under envs/ by researching a target library/API, selecting matching OpenEnv examples,…

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

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing repositories, models, datasets, and Spaces on the Hugging Face Hub. Replaces now deprecated `huggingface-cli` command.

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

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

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 comments, and iterates until green.

Diagnose and recover failing or stuck Hugging Face Space deployments for OpenEnv environments. Use when deploying envs from `envs/` to the Hub (`openenv` namespace with version suffixes), when Spaces are in `BUILDING`/`APP_STARTING`/`RUNTIME_ERROR`, or when…

Validate changes before submitting a pull request. Run comprehensive checks including lint, tests, alignment review, and RFC analysis. Use before creating a PR, when asked if code is ready for review, or before pushing for PR.

Use when the user has written (or wants to write) a `ModularPipelineBlocks` subclass in a local Python file and needs to package it into a Hub-uploadable directory. Covers the workflow from a single `block.py` file to a published custom-block repo that…

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 for a new version of an already-supported model.

Use before opening a PR, or whenever asked to self-review a diffusers contribution. Applies the same rubric as the `@claude` CI (checks the diff against references/review-rules.md, traces call paths for dead code). Reports findings grouped by severity,…

Use when the user wants to run a diffusers pipeline from a terminal (one-off generation, batch jobs, smoke-testing a new model), run on HF Sandbox hardware via `--remote`, introspect a pipeline's input schema before calling it, or attach a LoRA at inference…

Provides guidance for writing, optimizing, and benchmarking Triton kernels for Intel XPU GPUs (Battlemage/Arc Pro B50) using the Xe-Forge optimization framework. Includes an LLM-driven trial-loop workflow (analyze, validate, benchmark, profile, finalize),…

Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers libraries. Kernels must be kernel-builder/ABI3-compliant: no pybind11, no setup.py, TORCH_LIBRARY_EXPAND…

Provides guidance for writing, optimizing, and benchmarking C++ CPU kernels with SIMD intrinsics (AVX2/AVX512) for the Hugging Face kernels ecosystem. Includes a two-phase workflow: Phase 1 correctness (generic → AVX2) and Phase 2 performance exploration…

Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle,…

Scaffold a PhysicsIntern research workspace in the current folder. Run only when the user explicitly invokes it to set up a new physics/maths research workspace.

Scaffold a PhysicsIntern research workspace in the current folder.

Post-mortem analysis of a PhysicsIntern workspace run (Claude Code, Pi, Codex, or OpenCode host). Reconstructs the trajectory from the session record — JSONL file(s) for Claude/Pi/Codex, the SQLite store for OpenCode — audits methodology adherence against the…

Use ML Claw's HF Broker for protected Hugging Face repository and bucket reads, writes, temporary grants, recovery, and revocation. Use instead of asking for or exposing a Hugging Face access token.

Use when setting up, operating, migrating, repairing, or explaining an OpenClaw deployment on Hugging Face with the ML Claw `mlclaw` CLI. Covers the browser Space gateway, Hugging Face OAuth, local gateway mode, private Storage Buckets, Telegram as an…

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or…

Add a new TRF rule to the mlinter. Checks for duplicates, creates the rule module and TOML entry, runs against all models, and handles violations (fix or allowlist).

Retire a TRF rule from the mlinter. Marks the rule deprecated in rules.toml, deletes its module and tests, and records the removal in the CHANGELOG. Use when asked to remove, retire, drop, or delete a rule.

Cut a new transformers-mlinter release. Bumps the version across all pinned locations, updates the CHANGELOG, runs local checks and a packaged smoke test, drives the tag-based GitHub Actions publish to PyPI, then opens the next development version on main.…

Add and validate support for a Hugging Face model architecture in the Optimum Intel OpenVINO backend, including exporter configuration, patching, repository tests, and documentation.

Create a small random Hugging Face model that preserves the original architecture and can serve as a local Optimum Intel repository test fixture.

Investigates an Autophysicist workspace run. Use to understand what went wrong and could be improved in the single-agent iterative research process.

Investigates PhysicsIntern workspace run. Use to understand what went wrong and could be improved in the multi-agent research process.

Plan and profile Harbor benchmark runs, then launch and monitor them. Repair and verify results before publishing through the hosted Harbor-HF control service and Hugging Face infrastructure.

Ask for project approval before starting repository work, record the approved scope in the control-plane project file indexed by canonical repository slug, and recover authorization after compaction or session changes. Use before implementing, deploying,…

Use this skill when the user wants a polished, shareable, source-grounded, self-contained HTML artifact in the Birch visual system for engineering, product, planning, review, status, incident, process, codebase, data, or benchmark communication. Trigger for…

Deploy fast-agent MCP Servers to Hugging Face Spaces using Docker. Use when the user wants to deploy an "agent card" as an MCP Server. Includes templates and CLI commands for deploying agent cards with custom tools to HF Spaces.

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.