Skill 디렉토리

AI Agent를 위한 재사용 가능한 Skill을 찾으세요.

작업으로 실제 GitHub Skill을 검색하고 사용 전에 Stars, 신뢰, 감사, 카테고리, 설치 경로를 확인하세요.

모든 추천은 리포지토리, 감사, 설치 경로와 명확하게 연결됩니다.

검색 결과: sota

영문 디렉토리

BoxMOT: Pluggable python and c++ SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes

8.2K
Stars
86/100
신뢰
카테고리: ml-automation감사

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]

7.8K
Stars
86/100
신뢰
카테고리: ml-automation감사

A simple SWE style browser agent framework that achieves SOTA results on long horizon web tasks.

5.5K
Stars
84/100
신뢰
카테고리: agent-frameworks감사

A Python toolkit/library for reality-centric machine/deep learning & data mining on partially-observed time series, with 50+ SOTA neural network models for scientific analysis tasks (imputation, classification, clustering, forecasting, anomaly detection, cleaning) on incomplete industrial irregularly-sampled multivariate TS with NaN missing values

2.0K
Stars
83/100
신뢰
카테고리: data-analysis감사
R2R79

SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

7.9K
Stars
79/100
신뢰
카테고리: data감사

Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.

1.9K
Stars
83/100
신뢰
카테고리: media-automation감사

Build your own Cowork, AI Scientist and other SoTA Agents just by editing config files. Support anthropic skills. An infinite-horizon agent framework designed for long-running, complex tasks.

1.2K
Stars
83/100
신뢰
카테고리: agent-frameworks감사

SOTA Re-identification Methods and Toolbox

3.9K
Stars
70/100
신뢰
카테고리: robotics-iot감사

Self-evolving cognitive memory and context engine for AI agents in Java. Empowering 24/7 proactive agents like OpenClaw with understanding and SOTA performance.

901
Stars
73/100
신뢰
카테고리: agent-frameworks감사

A minimalist SOTA LaTeX OCR model with only 20M parameters, running in browser. Full training pipeline available for self-reproduction. | 超轻量SOTA LaTeX公式识别模型,仅20M参数量,可在浏览器中运行。训练全流程代码开源,以便自学复现。

883
Stars
71/100
신뢰
카테고리: robotics-iot감사

GenZ-ICP: SOTA robust LiDAR odometry (IEEE RA-L 2025)

675
Stars
67/100
신뢰
카테고리: robotics-iot감사

SOTA fast and robust ground segmentation using 3D point cloud (accepted in RA-L'21 w/ IROS'21)

584
Stars
71/100
신뢰
카테고리: robotics-iot감사