Agent Skills Hub

parxy

A unified document processing gateway for PDF parsing, text extraction, conversion, and document manipulation across multiple local and cloud providers.

scientific-visualization

Meta-skill for generating publication-ready scientific figures, multi-panel layouts, and journal-compliant visualizations using Python's matplotlib, seaborn, and plotly libraries.

pytorch-lightning

PyTorch Lightning skill for scalable deep learning: automates model training, multi-GPU orchestration, data pipelines, and distributed training strategies like DDP, FSDP, and DeepSpeed.

srt字幕转markdown笔记

Convert SRT subtitle files into structured Markdown notes with punctuation, paragraph formatting, and automated video screenshot placeholders.

pr

Automates the creation of draft GitHub pull requests using conventional commit standards and strict validation workflows.

test-reporting-analytics

Advanced QE reporting, quality dashboards, and predictive analytics for test metrics, code coverage, and deployment readiness to drive data-informed quality decisions.

debug-cuda-crash

Tutorial for identifying and resolving CUDA runtime crashes using FlashInfer's API logging framework.

ffmpeg-core

Production-grade FFmpeg automation for video and audio processing, including trimming, concatenation, format conversion, codec optimization, and filter application.

uv-rules

CLI tool that automatically renames academic PDF files using AI-extracted metadata, supporting multiple providers like Claude, OpenAI, Gemini, and Ollama.

mod-actions

A comprehensive moderation toolkit for Civitai, providing automated user management, strike systems, image review, content regulation, and CSAM reporting via tRPC API.

claude

Anthropic Claude AI models for high-performance coding, large-context analysis, and GUI interaction.

explaining-code

Explains code using visual diagrams, relatable analogies, step-by-step walkthroughs, and common pitfalls.