Agent Skills Hub

debug-distributed

Debugging guide for AReaL distributed training issues, including hangs, NCCL errors, OOM, and numerical consistency in FSDP2/TP/CP/EP.

ring:testing-skills-with-subagents

A meta-skill for building robust AI agent skills using a TDD approach: define failure (RED), implement the skill (GREEN), and plug rationalization loopholes (REFACTOR).

voice-extractor

Extract and document authentic writing voice from samples. Create comprehensive voice guides for AI training, ghostwriting, and brand consistency.

meteorology-driver-classification

Classify and group meteorological and environmental variables into specific driver categories for consistent attribution analysis and environmental modeling.

pyhealth

Comprehensive Python healthcare AI toolkit for clinical data processing, medical coding translation, and developing deep learning models like RETAIN and Transformers for EHR, physiological signals, and clinical prediction tasks.

datarobot-model-deployment

Tools for deploying, managing, and monitoring DataRobot models, including prediction environment configuration, champion/challenger workflows, and deployment operations.

startup-financial-modeling

Build comprehensive 3-5 year startup financial models, including revenue projections, cost structures, cash flow analysis, and scenario planning for fundraising and operations.

browser-debugger

Comprehensive UI testing, visual fidelity analysis, and browser debugging using Chrome DevTools MCP and AI-driven vision models.

model-registry-maintainer

Maintain and update the MassGen model registry, including backend capabilities, model metadata, pricing structures, and context window configurations for new and existing AI models.

tweet-rl-tracker

A Notion-based tracking system for tweet performance to enable data-driven content experimentation using reinforcement learning principles.

customer-research

Multi-source research tool for customer inquiries, bug investigations, and account history synthesis with source attribution and confidence scoring.

update-llm-model-list

Audit and synchronize the supported LLM model list in assets.py against the authoritative litellm registry.