Claude skills and agent skills

Hugging FaceSkill

deploy-hf

huggingface/OpenEnv/.claude/skills/deploy-hf/SKILL.md

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

Hugging FaceSkill

generate-openenv-env

huggingface/OpenEnv/.claude/skills/generate-openenv-env/SKILL.md

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, asking key implementation questions, and building models/client/server/openenv.yaml. Do not use for model training or evaluation tasks.

Hugging FaceSkill

hf-space-recovery

huggingface/OpenEnv/.claude/skills/hf-space-recovery/SKILL.md

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 release collections need to be reconciled after targeted redeploys.

Hugging FaceSkill

implement

huggingface/OpenEnv/.claude/skills/implement/SKILL.md

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

Often used withsetup-ts-deep-modules·ask-matt·loop-me

Hugging FaceSkill

pre-submit-pr

huggingface/OpenEnv/.claude/skills/pre-submit-pr/SKILL.md

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.

Hugging FaceSkill

release

huggingface/OpenEnv/.claude/skills/release/SKILL.md

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

Often used withcreate-agent-adapter·documentation-consistency

Hugging FaceSkill

rfc-check

huggingface/OpenEnv/.claude/skills/rfc-check/SKILL.md

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

Hugging FaceSkill

simplify

huggingface/OpenEnv/.claude/skills/simplify/SKILL.md

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

Hugging FaceSkill

update-docs

huggingface/OpenEnv/.claude/skills/update-docs/SKILL.md

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

Hugging FaceSkill

watch-pr

huggingface/OpenEnv/.claude/skills/watch-pr/SKILL.md

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.

Hugging FaceSkill

work-on-issue

huggingface/OpenEnv/.claude/skills/work-on-issue/SKILL.md

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

Hugging FaceSkill

write-tests

huggingface/OpenEnv/.claude/skills/write-tests/SKILL.md

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

Often used withclose-spec·compare-screenshots·audit-agents

Hugging FaceSkill

cpu-kernels

huggingface/kernels/kernel-builder/skills/cpu-kernels/SKILL.md

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 (AVX512 with branching trial loop), runtime CPU dispatch, OpenMP threading, and brgemm integration for GEMM-heavy kernels.

Hugging FaceSkill

cuda-kernels

huggingface/kernels/kernel-builder/skills/cuda-kernels/SKILL.md

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 bindings only. Supports models like LTX-Video, Stable Diffusion, LLaMA, Mistral, and Qwen. Includes integration with HuggingFace Kernels Hub (get_kernel) for loading pre-compiled kernels. Includes benchmarking scripts to compare kernel performance against baseline implementations.

Hugging FaceSkill

rocm-kernels

huggingface/kernels/kernel-builder/skills/rocm-kernels/SKILL.md

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, autotune, diffusers integration patterns, and LTX-Video pipeline injection.

Hugging FaceSkill

triton-kernels

huggingface/kernels/kernel-builder/skills/triton-kernels/SKILL.md

This skill provides patterns and guidance for developing portable, optimized Triton kernels that run on NVIDIA and AMD GPUs without modification. For backend-specific tuning, see rocm-kernels (AMD) and xpu-kernels (Intel). Use this skill when: 1. **BLOCK_SIZE for reductions must cover the full reduction dimension.** Use triton.next_power_of_2(dim) in the Python wrapper. Never autotune BLOCK_SIZE when it controls the reduction axis — partial rows give wrong results silently. 2. Masked loads need a safe other value. Use other=0.0 for additive contexts (sum,…

Hugging FaceSkill

xpu-kernels

huggingface/kernels/kernel-builder/skills/xpu-kernels/SKILL.md

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), XPU-specific patterns (tensor descriptors, GRF mode, tile swizzling), KernelBench fused kernels, and Flash Attention.

Hugging FaceSkill

example-skill

huggingface/upskill/tests/fixtures/ci_action_repo/skills/example-skill/SKILL.md

Example fixture skill for action smoke tests

Hugging FaceSkill

optimum-model-enabler

huggingface/optimum-intel/.github/skills/optimum-model-enabler/SKILL.md

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

Hugging FaceSkill

tiny-model-creator

huggingface/optimum-intel/.github/skills/tiny-model-creator/SKILL.md

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