Agent Skills Hub

training-data-curation

Guidelines for curating high-quality datasets for LLM post-training (SFT/DPO/RLHF), covering data formats, quality filtering, and collection strategies.

tool-design

Expert framework for designing agent-facing tools, optimizing tool descriptions, enforcing contract-based APIs, and implementing architectural reduction for reliable AI agent tool selection.

gemini-video-understanding

Perform advanced video analysis using Google's Gemini API: summarize content, transcribe audio, extract timestamps, clip segments, and analyze YouTube URLs or local files with support for multiple models and long contexts.

ae-mcp

Automate Adobe After Effects tasks using the Model Context Protocol. Manage compositions, layers, keyframes, effects, and expressions for motion graphics, title cards, and logo reveals.

Delegating to AWS Agent

Implement an AI agent delegation architecture to keep your main context clean, reduce token costs, and isolate specialized infrastructure or API tasks.

Fluxwing Screen Scaffolder

Build complete UI screens by composing multiple uxscii components. Use when you need to create, scaffold, or build .uxm screens like login, dashboard, profile, settings, or checkout pages.

vibe-prd

A structured PRD generator for vibe-coding MVPs. It guides you through defining product requirements, target audiences, and success metrics, ensuring a clear foundation for your development workflow.

videocut:剪口播

AI-powered video editing agent for talking head videos, featuring speech-to-text, disfluency detection, and browser-based review workflows.

dgame-dev

Expert assistant for the DGame Unity framework, facilitating development, architecture, hotfix, and resource management within the TEngine-based ecosystem.

stable-baselines3

Production-ready reinforcement learning using Stable Baselines3. Train agents, design custom environments, implement training callbacks, and optimize workflows with a scikit-learn-style API.

pymc

Bayesian modeling and probabilistic programming with PyMC. Build hierarchical models, perform MCMC sampling (NUTS), variational inference, and conduct rigorous model comparison using LOO and WAIC.

scikit-learn

Classical machine learning with scikit-learn. Use for classification, regression, clustering, dimensionality reduction, preprocessing, model evaluation, and building robust ML pipelines in Python.