Skill ディレクトリ

AI Agent のための再利用可能な Skill を見つける。

タスクで実際の GitHub Skill を検索し、利用前に Stars、Trust、監査、カテゴリ、インストール経路を確認できます。

すべての推奨は、リポジトリ、監査、インストール経路に明確につながっています。

検索結果: spotlight

英語版ディレクトリ

Deep recommender models using PyTorch.

3.0K
Stars
70/100
信頼
カテゴリ: ml-automation監査

Interactively explore unstructured datasets from your dataframe.

1.3K
Stars
77/100
信頼
カテゴリ: data-analysis監査

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

3.4K
Stars
79/100
信頼
カテゴリ: media-automation監査

Generate highly simplified personified IP mascot logos with Flat-first geometry, rounded heavy forms, two IP colors plus one background color by default, and extremely subtle neo-skeuomorphic shading. Use when creating an animal, creature, robot, ghost, plant, object, or other character as a minimal square logo or app-icon artwork, including when the agent should infer three distinct IP directions from product-repository context.

2.0K
Stars
73/100
信頼
カテゴリ: automation監査

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

2.1K
Stars
73/100
信頼
カテゴリ: ml-automation監査

An open-source, cross OS, community-driven launcher. A lightweight alternative to Spotlight and Raycast. I'm working on this project with AI agents.

346
Stars
70/100
信頼
カテゴリ: productivity-automation監査

Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)

312
Stars
68/100
信頼
カテゴリ: agent-frameworks監査

[NeurIPS 2025 Spotlight] A Unified Tokenizer for Visual Generation and Understanding

527
Stars
69/100
信頼
カテゴリ: media-automation監査

Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight)

381
Stars
67/100
信頼
カテゴリ: agent-frameworks監査

AI-powered PPT generation — 40,000+ style combinations, narrative-driven, design-intelligent, AI images, fully editable .pptx. Three modes: Build (default) + VI Build + FreeStyle (quick draft). 8 goal-type layouts, 35 moods, README parsing, size-aware image assignment, 3 structurally-different build.py proposals, brand compliance. Engines: Seedream, GPT Image, DALL-E, Wanx, Kimi.

240
Stars
64/100
信頼
カテゴリ: security監査

Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)

856
Stars
61/100
信頼
カテゴリ: robotics-iot監査

LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)

631
Stars
61/100
信頼
カテゴリ: robotics-iot監査