技能目录

为 AI Agent 发现可复用技能。

按任务搜索真实的 GitHub 技能,并在使用前查看 Stars、信任、审计、分类和安装路径。

每个推荐都保留与其仓库、审计和安装路径的明确关联。

搜索结果: spotlight

英文目录

Deep recommender models using PyTorch.

3.0K
Stars
70/100
信任
分类: ml-automation审计

Interactively explore unstructured datasets from your dataframe.

1.3K
Stars
77/100
信任
分类: data-analysis审计

[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
信任
分类: media-automation审计

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
信任
分类: automation审计

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
信任
分类: ml-automation审计

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
信任
分类: productivity-automation审计

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

312
Stars
68/100
信任
分类: agent-frameworks审计

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

527
Stars
69/100
信任
分类: media-automation审计

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

381
Stars
67/100
信任
分类: agent-frameworks审计

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
信任
分类: security审计

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

856
Stars
61/100
信任
分类: robotics-iot审计

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

631
Stars
61/100
信任
分类: robotics-iot审计