Agent Skills
Instruction packs that give your AI agent know-how. Three different kinds — pick the right one below.
✦ Standalone skills4,610
Self-contained. Install one into any project and it works on its own — no other software needed.
🧰 Tool add-ons1,006
Come bundled with a specific tool and only work together with it — they teach your agent how to operate that tool.
✓ Official
48 companiesPublished by the companies themselves — pick one to see everything they ship.
openai9 skills
anthropics16 skills
google-gemini17 skills
microsoft98 skills
github8 skills
facebook4 skills
react1 skill
coinbase6 skills
stripe7 skills
shopify2 skills
cloudflare19 skills
vercel22 skills
vercel-labs63 skills
supabase4 skills
huggingface6 skills
pytorch2 skills
flutter3 skills
DataDog11 skills
getsentry92 skills
brave2 skills
googleworkspace95 skills
google-labs-code3 skills
genkit-ai9 skills
expo2 skills
n8n-io21 skills
sveltejs3 skills
nuxt1 skill
shadcn-ui2 skills
bitwarden2 skills
automattic36 skills
larksuite35 skills
browserbase2 skills
browser-use9 skills
apify2 skills
clickhouse8 skills
neondatabase11 skills
upstash10 skills
posthog165 skills
langfuse2 skills
resend3 skills
sanity-io25 skills
streamlit4 skills
remotion-dev3 skills
tldraw7 skills
apollographql1 skill
mastra-ai28 skills
triggerdotdev1 skill
mcp-use4 skills
add-or-fix-type-checking
✓★ 162,286by huggingface
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.
🧰 Not standalone — use together with huggingface/transformers
trl-training
✓★ 18,774by huggingface
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.
🧰 Not standalone — use together with huggingface/trl
cuda-kernels
✓★ 704by huggingface
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 perform
🧰 Not standalone — use together with huggingface/kernels
rocm-kernels
✓★ 704by huggingface
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.
🧰 Not standalone — use together with huggingface/kernels
cpu-kernels
✓★ 704by huggingface
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.
🧰 Not standalone — use together with huggingface/kernels
xpu-kernels
✓★ 704by huggingface
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.
🧰 Not standalone — use together with huggingface/kernels