Annuaire de skills

Découvrez des skills réutilisables pour les AI agents.

Recherchez de vrais skills GitHub par tâche et vérifiez Stars, confiance, audit, catégorie et chemin d’installation avant de les utiliser.

Chaque recommandation reste clairement reliée à son dépôt, son audit et son chemin d’installation.

Résultats de recherche: spotlight

Annuaire en anglais

Deep recommender models using PyTorch.

3.0K
Stars
70/100
Confiance
Catégorie: ml-automationAudit

Interactively explore unstructured datasets from your dataframe.

1.3K
Stars
77/100
Confiance
Catégorie: data-analysisAudit

[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
Confiance
Catégorie: media-automationAudit

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
Confiance
Catégorie: automationAudit

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
Confiance
Catégorie: ml-automationAudit

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
Confiance
Catégorie: productivity-automationAudit

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

312
Stars
68/100
Confiance
Catégorie: agent-frameworksAudit

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

527
Stars
69/100
Confiance
Catégorie: media-automationAudit

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

381
Stars
67/100
Confiance
Catégorie: agent-frameworksAudit

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
Confiance
Catégorie: securityAudit

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

856
Stars
61/100
Confiance
Catégorie: robotics-iotAudit

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

631
Stars
61/100
Confiance
Catégorie: robotics-iotAudit