Hugging FaceSkillhuggingface-gradio
huggingface/skills/skills/huggingface-gradio/SKILL.md
Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.
Find the best CLAUDE.md, AGENTS.md and Claude skills
One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Most stars first · from page 3Worked for most · soon
Hugging FaceSkillHugging FaceSkillhuggingface-llm-trainer
huggingface/skills/skills/huggingface-llm-trainer/SKILL.md
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Hugging FaceSkillhuggingface-local-models
huggingface/skills/skills/huggingface-local-models/SKILL.md
Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.
Hugging FaceSkillhuggingface-lora-space-builder
huggingface/skills/skills/huggingface-lora-space-builder/SKILL.md
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, FLUX, SDXL, or other diffusion base models. Also triggers when someone describes a LoRA they trained or hosts on the Hub and wants to share it. Covers picking the right base pipeline and `diffusers` inference recipe, designing a UI tailored to the LoRA's task and inputs (Union/multi-task control, edit, video, image, etc.), respecting model-card recommendations (trigger words, steps, guidance, LoRA scale, example inputs), and shipping to ZeroGPU hardware as a private Space by default.
Hugging FaceSkillhuggingface-paper-publisher
huggingface/skills/skills/huggingface-paper-publisher/SKILL.md
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
Hugging FaceSkillhuggingface-papers
huggingface/skills/skills/huggingface-papers/SKILL.md
Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.
Hugging FaceSkillhuggingface-spaces
huggingface/skills/skills/huggingface-spaces/SKILL.md
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 Hugging Face, port code onto ZeroGPU, fix a Space that won't build or run, or otherwise work with `hf spaces …`, `@spaces.GPU`, Space README frontmatter, or the `spaces` Python package.
Hugging FaceSkillhuggingface-tool-builder
huggingface/skills/skills/huggingface-tool-builder/SKILL.md
Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.
Hugging FaceSkillhuggingface-trackio
huggingface/skills/skills/huggingface-trackio/SKILL.md
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output for automation.
Hugging FaceSkillhuggingface-vision-trainer
huggingface/skills/skills/huggingface-vision-trainer/SKILL.md
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
Hugging FaceSkillhuggingface-zerogpu
huggingface/skills/skills/huggingface-zerogpu/SKILL.md
AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific code constraints — pickle-based process isolation, `gr.State` semantics across the worker boundary, no `torch.compile` (use AoTI instead), CUDA wheel-only builds (no `nvcc` at build or runtime), large vs xlarge sizing, and dynamic duration callables. Make sure to use this skill whenever the user mentions ZeroGPU, `@spaces.GPU`, or the `spaces` Python package, or hits ZeroGPU-specific code errors like `PicklingError` across the worker boundary, `illegal duration`, or `flash-attn` wheel-build failures — even when the user does not explicitly ask for ZeroGPU coding guidance. Trigger on `import spaces` or `@spaces.GPU` in code.
Hugging FaceSkilltransformers-js
huggingface/skills/skills/transformers-js/SKILL.md
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.
Hugging FaceSkilltrl-training
huggingface/skills/skills/trl-training/SKILL.md
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.
Hugging FaceCLAUDE.mdchat-ui
huggingface/chat-ui/CLAUDE.md
Chat UI is a SvelteKit application that provides a chat interface for LLMs. It powers HuggingChat (hf.co/chat). The app speaks exclusively to OpenAI-compatible APIs via OPENAIBASEURL. Tests are split into three workspaces (configured in vite.config.ts): MCP servers are configured via MCPSERVERS env var. When enabled, tools are exposed as OpenAI function calls. The router can auto-select tools-capable models when LLMROUTERENABLETOOLS=true. Smart routing via Arch-Router model. Configured with: Copy .env to .env.local and configure: See .env for full list of variables…
Hugging FaceSkillsync-models
huggingface/chat-ui/.claude/skills/sync-models/SKILL.md
Sync chat-ui's model config with the HuggingFace router — add descriptions for new models, flag reasoning-capable ones, enable artifacts for models with 32B+ parameters, and prune deprecated models the router no longer serves. Use when models are released or removed on the router and prod.yaml/dev.yaml need syncing. Triggers on requests like "add new model descriptions", "update models from router", "sync models", "remove deprecated models", "prune models no longer on the router", or when explicitly invoking /sync-models.
Hugging FaceAGENTS.mdhuggingface_hub
huggingface/huggingface_hub/AGENTS.md
Python client library for the Hugging Face Hub. Source code is in src/huggingface_hub/, tests in tests/. Always run make style then make quality before committing.
Hugging FaceSkillhf-release-notes
huggingface/huggingface_hub/.opencode/skills/hf-release-notes/SKILL.md
Generate Hugging Face Hub (huggingface_hub) release notes from cached PR JSON files. Use when asked to draft release notes from PR files.
Hugging FaceAGENTS.mddatatrove
huggingface/datatrove/AGENTS.md
DataTrove is a library to process, filter, and deduplicate text data at very large scale. It provides prebuilt pipeline blocks with a framework to add custom functionality. Pipelines are platform-agnostic, running locally, on Slurm, or on Ray clusters. See README.md for detailed documentation on terminology, pipeline blocks, executors, and usage examples.
Hugging FaceAGENTS.mdtau
huggingface/tau/AGENTS.md
Tau is a Python implementation of Pi's minimalist coding-agent harness architecture. The goal is to develop it incrementally, with each phase clearly documented and tested. The implementation roadmap is tracked in GitHub issue #1: Use that issue as the primary reference for phase ordering and architectural intent. Preserve Pi's core separation of concerns: Tau should be organized around these layers: Keep the core agent package independent of CLI, Textual, Rich rendering, session file locations, and application-specific resource loading. Use Textual…
Hugging FaceCursor rulenanotron / rules
huggingface/nanotron/.cursor/rules/performance-optimization.mdc
Better pattern:
Agent instruction files
What are agent instruction files?
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.