Skills / Category
Machine learning
738 skills
Showing 385–408 of 738
- 0.560score
ffcv
VectorSpaceLab
Use FFCV to convert datasets into .beton files, build fast PyTorch loader pipelines, handle image and custom fields/transforms, and tune cache, traversal, and…
SkillBFreshness: B★ 341Claude Code +9 - 0.560score
flashrag
VectorSpaceLab
Use FlashRAG for retrieval-augmented generation research workflows: config/data validation, retrieval and index building, generation/refinement components…
SkillBFreshness: B★ 341Claude Code +9 - 0.560score
flashvsr
VectorSpaceLab
Routes official FlashVSR diffusion-based streaming video super-resolution setup, model preparation, and CUDA inference for v1 and v1.1.
SkillBFreshness: B★ 341Claude Code +9 - 0.560score
flow-forecast
VectorSpaceLab
Repository operating skill for using Flow Forecast's flood_forecast package for time-series forecasting, data preparation, training, inference, evaluation…
SkillBFreshness: B★ 341Claude Code +9 - 0.560score
foolbox
VectorSpaceLab
Foolbox operating guidance for wrapping vision models, running adversarial attacks, measuring clean and robust accuracy, handling NumPy/PyTorch/TensorFlow/JAX…
SkillBFreshness: B★ 341Claude Code +9 - 0.560score
frustum-pointnets
VectorSpaceLab
Operate the legacy Frustum PointNets code release for KITTI or SUN RGB-D data preparation, TensorFlow runtime setup, training, inference, and 3D detection…
SkillBFreshness: B★ 341Claude Code +9 - 0.560score
geemap
VectorSpaceLab
Use geemap for Google Earth Engine interactive mapping, geospatial conversion, visualization, timelapse, and ML helper workflows.
SkillBFreshness: B★ 341Claude Code +9 - 0.559score
other-llm
YoniChechik
Get an independent second opinion or delegate work to the OTHER coding CLI — whichever model family is NOT currently active.
SkillAFreshness: AClaude Code +9 - 0.559score
docs-align
hedypamungkas
This skill should be used when the user asks to "align docs", "sync documentation", "update README", "update CLAUDE.md", "fix stale docs", "audit…
SkillBFreshness: B★ 5Claude Code +9 - 0.558score
prompt-injection-eval
SecurityMindedSolutions
Score prompts for prompt injection with TypeSafe's Jev before they reach an LLM: a reference gate function a backend can call (allow / review / block with a…
SkillBFreshness: B★ 2Claude Code +9 - 0.558score
resume-mirror-eval
SecurityMindedSolutions
Bulk-evaluate a folder of resumes against one job description and flag the ones whose wording mirrors the posting closely enough that a human should look…
SkillBFreshness: B★ 2Claude Code +9 - 0.558score
3d-resnets-pytorch
VectorSpaceLab
Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.
SkillBFreshness: B★ 341Claude Code +9 - 0.558score
alpamayo-r1
VectorSpaceLab
Router for Alpamayo R1 multimodal driving inference and trajectory sampling.
SkillBFreshness: B★ 341Claude Code +9 - 0.558score
background-matting-v2
VectorSpaceLab
Routes BackgroundMattingV2 tasks for background matting inference, export, and training workflows.
SkillBFreshness: B★ 341Claude Code +9 - 0.558score
baichuan2
VectorSpaceLab
Route Baichuan2 chat inference, deployment/quantization, and fine-tuning workflows.
SkillBFreshness: B★ 341Claude Code +9 - 0.558score
bert-pytorch
VectorSpaceLab
Use BERT-pytorch for corpus preparation, vocabulary building, and tiny BERT pretraining workflows.
SkillBFreshness: B★ 341Claude Code +9 - 0.558score
bertopic
VectorSpaceLab
Route BERTopic topic modeling, embedding, vectorizer, labeling, visualization, and serialization workflows.
SkillBFreshness: B★ 341Claude Code +9 - 0.558score
bi-ref-net
VectorSpaceLab
Route BiRefNet image segmentation, matting, inference, configuration, training, evaluation, and model-export workflows.
SkillBFreshness: B★ 341Claude Code +9 - 0.558score
chinese-llama-alpaca
VectorSpaceLab
Route Chinese-LLaMA-Alpaca model reconstruction, inference/deployment, training/fine-tuning, and evaluation workflows.
SkillBFreshness: B★ 341Claude Code +9 - 0.558score
chinese-llama-alpaca-2
VectorSpaceLab
Routes Chinese-LLaMA-Alpaca-2 training, inference, serving, evaluation, and integration workflows.
SkillBFreshness: B★ 341Claude Code +9 - 0.558score
clip
VectorSpaceLab
Use OpenAI CLIP for zero-shot image-text inference, prompt engineering, feature extraction, and responsible evaluation.
SkillBFreshness: B★ 341Claude Code +9 - 0.558score
damo-yolo
VectorSpaceLab
Training, inference, and deployment workflows for DAMO-YOLO object detection.
SkillBFreshness: B★ 341Claude Code +9 - 0.558score
deblur-gan
VectorSpaceLab
Route DeblurGAN users to data preparation, training, and single-image inference workflows.
SkillBFreshness: B★ 341Claude Code +9 - 0.558score
distil-whisper
VectorSpaceLab
Routes Distil-Whisper inference, PyTorch distillation training, and Flax reproduction workflows.
SkillBFreshness: B★ 341Claude Code +9