huggingface

huggingface/OpenEnv

Skill Claude CodeCodex

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

huggingface/OpenEnv

Skill Claude CodeCodex

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 produces stacked PRs.

huggingface/OpenEnv

Skill Claude CodeCodex

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

huggingface/OpenEnv

Skill Claude CodeCodex

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.

huggingface/OpenEnv

Skill Claude CodeCodex

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

huggingface/OpenEnv

Skill Claude CodeCodex

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

huggingface/OpenEnv

Instructions file CodexOpenCode

AGENTS.md instructions for huggingface/OpenEnv, covering agents.md, cursor cloud specific instructions, project shape, environment / dependencies and running an environment end-to-end (no docker needed).

huggingface/OpenEnv

Instructions file

Claude Code instructions for huggingface/OpenEnv, covering claude.md, new here? start with these, agentic-first workflow, getting started and install git hooks for the team.

huggingface/upskill

Instructions file CodexOpenCode

Instructions for huggingface/upskill, covering agent guidance, code quality baseline, required local checks, ruff rules and type checking.

huggingface/upskill

Skill Claude CodeCodex

Example fixture skill for action smoke tests.

huggingface/kernels

Skill Claude CodeCodex

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…

huggingface/kernels

Skill Claude CodeCodex

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, TORCHLIBRARYEXPAND bindings only. Supports models like LTX-Video, Stable Diffusion…

huggingface/kernels

Skill Claude CodeCodex

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…

huggingface/kernels

Skill Claude CodeCodex

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).

huggingface/kernels

Skill Claude CodeCodex

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…

huggingface/hf-mcp-server

Instructions file CodexOpenCode

Instructions for huggingface/hf-mcp-server, covering repository guidelines, subagents, project structure & module organization, build, test, and development commands and coding style & naming conventions.

huggingface/leLab

Instructions file

Instructions for huggingface/leLab, covering claude.md, repository purpose, common commands, architecture and backend module layout (lelab/).

huggingface/pwc-cli

Skill Claude CodeCodex

Papers With Code CLI (pwc) for searching and reading AI/ML papers, discovering recent and trending research, finding related work and paper lineage, browsing tasks, methods, conferences, organizations, frameworks, and benchmark leaderboards through the public Papers With Code catalog. Use whenever the user asks to…

huggingface/transformers-to-mlx

Skill Claude CodeCodex

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 model to MLX, create an MLX implementation of a model, or test/validate an MLX model conversion. Triggers include mentions of "convert to MLX", "MLX…

huggingface/hf-discover

Instructions file CodexOpenCode

Instructions for huggingface/hf-discover: It should help humans quickly understand the big idea and help future agents know which scripts, workflows, specs, and plans to inspect for detailed question-answering. Prefer concise summaries with explicit artifact pointers over duplicating shell/script logic.

huggingface/s2-cli

Skill Claude CodeCodex

Semantic Scholar CLI (s2) for on-demand citation graph lookup: papers a work cites, papers that cite a work, and graph search across 200M+ papers. Use whenever the user asks for Semantic Scholar, S2, cited papers, references, bibliography, citing papers, citation count from Semantic Scholar, or papers outside a local…

huggingface/physics-intern-skills

Skill Claude CodeCodex

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 workspace's own CLAUDE.md / AGENTS.md and skill/agent…

huggingface/physics-intern-skills

Instructions file

Claude Code instructions for huggingface/physics-intern-skills, covering physicsintern project, rules and development skills.

huggingface/physics-intern-skills

Agent

Perform symbolic and numerical computation for a target claim. Default backend SymPy + NumPy. Runs symbolic and numerical paths together when both are feasible and flags disagreements. Writes computations/C-NNN.md (narrative) and computations/C-NNN.py (executed script).