huggingface/skills
Give your agents the power of the Hugging Face ecosystem
https://skillcdn.ai/gh/huggingface/skillsConnect this address to your AI to use these skills. How to connect
- Default branch
main - Commit
25910b3 - License
Apache-2.0 - Searchwords and meaning
Explore this repository
Searches the original text of skills and documents by words and by meaning; display translations are not searched.
Documents
- CUDA extensions for 3D Spaces on ZeroGPUGeneral ZeroGPU rules live in zerogpu.md; wheel-tag anatomy and the prebuilt Blackwell wheel dataset live in requirements.md. This file covers what makes 3D generation models harder than diffusion im…skills/huggingface-spaces/references/3d-cuda-extensions.md
- 3D generation SpacesBuilding a Space whose output is a 3D asset — image (occasionally text) in, downloadable and in-browser-viewable mesh (GLB/OBJ/PLY/STL) or gaussian splat (.ply/.splat) out. Read this whenever the use…skills/huggingface-spaces/references/3d-generation.md
- Gaussian splatting referenceImage-to-3D models whose output is a gaussian splat (a point cloud of oriented 3D gaussians) rather than a mesh. Deliverable file: gaussian .ply (the INRIA convention — the interchange format everyth…skills/huggingface-spaces/references/3d-gsplat.md
- 3D models: TRELLIS / TRELLIS.2, TripoSR, Stable Fast 3D, SPAR3D, Hunyuan3DPer-family deployment recipes for mesh-generation models, distilled from the live files of their official Spaces. Gaussian splatting models live in 3d-gsplat.md; the overall workflow in 3d-generation…skills/huggingface-spaces/references/3d-models.md
- Mesh outputs: formats, viewers, preprocessingGLB is the default output format. It's self-contained (geometry + materials + textures in one binary file), renders in every in-browser viewer, and is what all the major official 3D Spaces produce. O…skills/huggingface-spaces/references/3d-outputs.md
- Persistent storage with BucketsSpaces are stateless. All data is wiped on restart / rebuild. For state that must survive (user uploads, generations, dynamic feeds, logs, growing databases): mount an HF Bucket — S3-like object stor…skills/huggingface-spaces/references/buckets.md
- Debugging and iterationHow to iterate cheaply, read logs, and smoke-test. Dev mode + SSH exists as a last resort (covered at the bottom).skills/huggingface-spaces/references/debugging.md
- Gradio for SpacesPatterns and quirks specific to running Gradio inside a Space. Assumes you're already comfortable with stock Gradio components and gr.Blocks / gr.Interface.skills/huggingface-spaces/references/gradio.md
- Community GPU grantsWhen a user has a good use case (open research demo, hobbyist project, educational tool, institutional showcase) and can't pay for the hardware it needs, they can request a free community grant from…skills/huggingface-spaces/references/grants.md
- Inference Providers — when not to host the modelSome Spaces don't need a GPU at all. If the model is available through HF Inference Providers (Cerebras, Fireworks, Together, Replicate, OpenRouter, etc.), the Space can be a thin Gradio shell that p…skills/huggingface-spaces/references/inference-providers.md
- Known errorsCheck if this is a known issue before trying your own fix. Entries are keyed by the substring that actually appears in runtime.errorMessage, the build log, or a Python traceback — grep this file for…skills/huggingface-spaces/references/known-errors.md
- requirements.txt for SpacesRules for what to pin, what to leave alone, where to source CUDA wheels, and which torch-side-cars drift silently.skills/huggingface-spaces/references/requirements.md
- ZeroGPURead this whenever the Space targets ZeroGPU (zero-a10g flavor). The SKILL.md's 3-rule summary is a starting point; this file covers the model in enough detail to debug and design.skills/huggingface-spaces/references/zerogpu.md
Skipped (3)
These manifests were not served. Fix them and push: the next commit is indexed again.
skills/huggingface-trackio/references/retrieving_metrics.mdlink_missing2 links name no file of the repository (docs/source/cli_commands.md, docs/source/api_mcp_server.md)skills/huggingface-vision-trainer/references/image_classification_training_notebook.mdlink_missing9 links name no file of the repository (../model_doc/vit, /docs/transformers/v5.2.0/en/main_classes/data_collator#transformers.DefaultDataCollator, /docs/transformers/v5.2.0/en/main_classes/trainer#transformers.Trainer, ...)skills/huggingface-vision-trainer/references/object_detection_training_notebook.mdlink_missing6 links name no file of the repository (/docs/transformers/v5.1.0/en/model_doc/auto#transformers.AutoImageProcessor, /docs/transformers/v5.1.0/en/main_classes/trainer#transformers.Trainer, /docs/transformers/v5.1.0/en/model_doc/auto#transformers.AutoModelForObjectDetection, ...)