Agent Skills

MessyData

messydata

Generate realistic synthetic datasets with configurable anomalies (missing values, duplicates, invalid categories, bad dates, outliers) using YAML configs, CLI,

Python Cheat Sheets

pysheeet

Comprehensive Python reference and examples for coding, debugging, performance, concurrency, networking, ML/LLM workflows, and HPC — use to answer Python questi

Paper Review Pipeline

ai-collab-playbook

Run a structured, no-omission review of near-final ML conference papers: section-by-section edits, prioritized P0/P1/P2 issue list, and rebuttal drafting.

Python Quality & Testing

aiekit

Improve Python/ML code quality with type annotations, contract docstrings, exception audits, Hypothesis property-based tests, and mutmut mutation testing.

Scikit-learn Reference — Classical ML Workflows

auto-college

Authoritative guidance for classical machine learning with scikit-learn: preprocessing, pipelines, model selection, evaluation, and example scripts for producti

Runtime Communication (research_mvp)

tinykaggleclaw

Rules and workflows for messaging, delegation, and task coordination in the research_mvp local multi-agent runtime (leader, researcher, trainer).

Weights & Biases (wandb)

zorai

Integrate Weights & Biases for ML experiment tracking: log metrics, hyperparameters, checkpoints, run sweeps and view collaborative dashboards.

ComfyClaw

comfyclaw

CLI for discovering, inspecting, and running ComfyUI workflows with tag-based parameter overrides and live-server introspection.

vLLM-Omni Video Generation

vllm-omni-skills

Generate videos (text→video, image→video, text+image→video) using vLLM-Omni and Wan2.2-style diffusion models, with guidance on parameters and performance trade

PolicyPulse Development

insurance-skills

Guides AI agents to build PolicyPulse: a Python-based synthetic population simulator with clean architecture, type-safe code patterns, and Streamlit dashboard d

PolicyPulse Development

insurance-skills

Guidance for building PolicyPulse — a synthetic-population simulation dashboard with clean architecture, strong Python typing, and Streamlit UI patterns.

ArXiv Watcher

hermeshub

Monitor ArXiv for new papers by topic, author, or keyword and produce concise relevance-scored summaries for each match.

NeuriCo — Autonomous Research Framework

neurico

Orchestrates end-to-end AI research: literature review, experiment execution, analysis, and paper drafting from a structured idea spec.

AutoResearch Toolkit

wjgoarxiv

Autonomous research and experimentation loop for iterative optimization of code, prompts, and configs.

W&B (Weights & Biases) Integration

application-skills

Integrate with Weights & Biases via the Membrane CLI to manage runs, projects, artifacts, and automate ML workflow tasks.

ML Intern — Hugging Face Workflow Orchestrator

claude-ml-intern-skill

Autonomous ML intern that researches, implements, trains, verifies, and publishes ML experiments using the Hugging Face ecosystem, with budgeted retry loops and

AI/ML Workflow Bundle

agent-skills-library

A comprehensive workflow bundle for designing, building, and operating LLM applications, RAG systems, AI agents, and ML pipelines.

Litmus — Parallel ML Research

litmus

Orchestrates parallel autonomous ML research agents with git-backed experiment branches, a director/synthesizer layer, and nightly synthesised findings.