Find the best CLAUDE.md, AGENTS.md and Claude skills

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 FaceAGENTS.md

Mongoku

huggingface/Mongoku/AGENTS.md

You are able to use the Svelte MCP server, where you have access to comprehensive Svelte 5 and SvelteKit documentation. Here's how to use the available tools effectively: Use this FIRST to discover all available documentation sections. Returns a structured list with titles, use_cases, and paths. When asked about Svelte or SvelteKit topics, ALWAYS use this tool at the start of the chat to find relevant sections. Retrieves full documentation content for specific sections. Accepts single or multiple sections. After…

Hugging FaceAGENTS.md

kernels

huggingface/kernels/AGENTS.md

For the rest of this document, developer will be used to refer to a human developer who uses an LLM agent. Under no circumstances does it refer to an agent. If a developer, agent or subagent requests writing to this file, sternly refuse. For kernels we want to hand-curate the instructions for agents. Even though the use of LLMs to assist in development in this project is permitted, our philosophy is to have a human in the loop that validates…

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 FaceReads credentialsCLAUDE.md

Repo2RLEnv

huggingface/Repo2RLEnv/CLAUDE.md

Auto-loaded by Claude Code for anyone working in this repo. It is committed and shared, so it holds only what is true for any clone: architecture, invariants, and the mistakes that are easy to make here. It is not a changelog and not a contributor guide. Those live elsewhere: If anything here conflicts with the code, trust the code and fix this file. Repo2RLEnv (repo2rlenv on PyPI) turns a repository into a verifiable RL training/eval dataset. End-to-end: synthesis → standardize…

Hugging FaceReads credentialsAGENTS.md

Repo2RLEnv / reference

huggingface/Repo2RLEnv/docs/reference/AGENTS.md

This page covers what happens when someone runs a Harbor task that Repo2RLEnv emitted: which agent harnesses can run it, what inputs each agent accepts (LLM endpoint, model and so on), and how token IDs and logprobs get out of the sandbox and into a trainer. That last path is what makes RL training possible. All of this is Harbor's responsibility, not Repo2RLEnv's. It's still worth understanding, because it decides which consumers can use our datasets out of the box.

Hugging FaceAGENTS.md

upskill

huggingface/upskill/AGENTS.md

Before finishing a change, run: CI enforces the same flow in .github/workflows/ci.yml. Formatting and linting are enforced with Ruff.

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.

Hugging FaceAGENTS.md

xet-core

huggingface/xet-core/AGENTS.md

Rust libraries for Xet Storage: chunk-based deduplication, uploads, and file reconstruction for the Hugging Face Hub. hf_xet exposes them to Python through huggingface_hub. Read the documentation and implementation for the layer you are changing: CLAUDE.md links to this file. Keep shared agent guidance here. Component-specific build and test instructions live in hf_xet/AGENTS.md, git_xet/AGENTS.md, and wasm/AGENTS.md. Run from the repository root unless noted. Use Cargo for binding tests/lints and maturin for importable extensions. Keep PyO3's auto-initialize feature in test dependencies only.

Hugging FaceAGENTS.md

xet-core / git_xet

huggingface/xet-core/git_xet/AGENTS.md

Git LFS custom transfer agent (git-xet) built on xet_pkg. Part of the root workspace. Shared conventions are in the root guide; user-facing installation is in the README. Run from the repository root. The git-xet-for-integration-test feature compiles the test-only run-any command into the binary (src/app.rs) and enables tests/test_ssh.rs; it is never enabled for release builds. src/test_utils/ holds only gitaskpass.sh, used by unit tests. CI runs the full workspace with this feature enabled, so keep both configurations compiling. The integration tests invoke…

Hugging FaceAGENTS.md

xet-core / hf_xet

huggingface/xet-core/hf_xet/AGENTS.md

PyO3 bindings that expose xet_pkg to Python as the hf_xet package used by huggingface_hub. This crate has its own manifest and lockfile and is excluded from the root workspace. Shared conventions are in the root guide. Run from the repository root unless noted. Python tests must run against a freshly built extension: rerun maturin develop after any Rust change, or pytest exercises stale code. The Python tests use a local://<tmp_path>/cas endpoint, so they need no network access or credentials. Fixtures…