Skill Registry

Find the right skill for the job your agent is doing.

Search by task, platform, trust profile, or GitHub adoption. OpenAgentSkill keeps the interface human-readable and the API ready for agents.

4
Shown
9
Tracks
77
Targets

Decision filters

Choose by scenario, quality, and trust signals.

Showing 1-4 of 4 ranked candidates matching "torch"

Best blend of quality, stars, freshness, and agent usage

1

Pytorch

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDCODING

Tensors and Dynamic neural networks in Python with strong GPU acceleration

$ npx skills add pytorch/pytorch
100.8K stars78 quality91 trustReviewedClaude Code1d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: License is unclear
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

Claude Code + CLI · 4 targets

pythonmachine-learning
by pytorchDetailsQuick view
2

LLMs From Scratch

VERIFIEDEXCELLENT · 100TRUST · 92SAFE · REVIEWEDCODING

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

$ npx skills add rasbt/LLMs-from-scratch
97.3K stars78 quality92 trustReviewedClaude Code + OpenAI Agents14d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: License is unclear
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario GitHub automation

Claude Code + OpenAI Agents · 4 targets

jupyter-notebookmachine-learning
by rasbtDetailsQuick view
3

Keras

VERIFIEDEXCELLENT · 100TRUST · 96SAFE · REVIEWEDCODING

Deep Learning for humans

$ npx skills add keras-team/keras
64.1K stars77 quality96 trustReviewedClaude Code4d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario GitHub automation

Claude Code + CLI · 4 targets

pythonmachine-learning
by keras-teamDetailsQuick view
4

Yolov5

VERIFIEDEXCELLENT · 100TRUST · 96SAFE · VERIFIEDCODING

Ultralytics YOLOv5 in PyTorch > ONNX > CoreML > TFLite

$ npx skills add ultralytics/yolov5
57.5K stars77 quality96 trustVerifiedClaude Code4d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Coding agents

Claude Code + CLI · 4 targets

pythonmachine-learning
by ultralyticsDetailsQuick view