Direktori skill

Temukan skill yang dapat digunakan kembali untuk AI agents.

Cari skill GitHub nyata berdasarkan tugas lalu periksa stars, trust, audit, kategori, dan jalur pemasangan sebelum digunakan.

Setiap rekomendasi tetap terhubung dengan repositori, audit, dan jalur pemasangannya.

Hasil pencarian: part-segmentation

Direktori bahasa Inggris

Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

18K
Stars
87/100
Kepercayaan
Kategori: design-creativeAudit

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

13K
Stars
87/100
Kepercayaan
Kategori: ml-automationAudit

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

7.8K
Stars
77/100
Kepercayaan
Kategori: ml-automationAudit

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
Kepercayaan
Kategori: ml-automationAudit

An open-source authorization as a service inspired by Google Zanzibar, designed to build and manage fine-grained and scalable authorization systems for any application. โ€” Permify is now part of FusionAuth ๐ŸŽ‰

5.9K
Stars
86/100
Kepercayaan
Kategori: devopsAudit

markdown processor powered by plugins part of the @unifiedjs collective

8.9K
Stars
77/100
Kepercayaan
Kategori: document-processingAudit

AI agent skill that reads academic papers and generates structured Obsidian notes.

621
Stars
78/100
Kepercayaan
Kategori: productivityAudit

Semantic segmentation on aerial and satellite imagery. Extracts features such as: buildings, parking lots, roads, water, clouds

2.1K
Stars
85/100
Kepercayaan
Kategori: ml-automationAudit

Tfsec is now part of Trivy

7.0K
Stars
77/100
Kepercayaan
Kategori: developmentAudit

An agent skill that transforms AI assistants into expert economics paper writers by synthesizing best practices from over 50 authoritative guides.

470
Stars
78/100
Kepercayaan
Kategori: researchAudit

A lightweight configuration/utility that prevents coding agents like Codex and Claude Code from over-engineering tasks with unnecessary modules, subagents, dependencies, and hashes.

141
Stars
77/100
Kepercayaan
Kategori: coding-agentsAudit

An exam cram coach skill for Claude agents that creates chaptered knowledge bases and quiz banks from course materials, with source-labeled answers and abstention when out of scope.

256
Stars
75/100
Kepercayaan
Kategori: productivityAudit