Agent Skills Hub

qwen-asr

Transcribe audio files (wav, mp3, ogg) to text using the Qwen ASR model. Fast, local-friendly, and requires no API keys.

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.

qasai

A powerful CLI tool for image compression and conversion, supporting batch processing, multiple engines (mozjpeg, pngquant, sharp, etc.), format conversion (WebP, AVIF), and recursive directory optimization.

moollm

A microworld operating system for LLM-based agent living memory, transforming filesystems into navigable rooms and code into habitable worlds.

meteorology-driver-classification

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

markdown-token-optimizer

Analyzes markdown files to identify token-wasting patterns, providing actionable suggestions to optimize documentation for LLM consumption and token efficiency.

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.

memory-hygiene

Audit, prune, and maintain vector memory for Clawdbot. Prevents token waste, clears junk data, and automates memory hygiene via LanceDB maintenance.

context-compression

Optimize agent performance and token usage through advanced context compression, structured summarization, and task-oriented state management for long-running sessions.

notebooklm

Query Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Features persistent authentication, library management, and automated browser-based document retrieval.

browser-debugger

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

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.