Analytics & Monitoring Agent Skills for Claude Code

Guides end-to-end Kaggle competition workflows from RAG knowledge base setup and feature engineering to model ensembling and submission…

Use when looking for top-solution tricks on a Kaggle competition, when needing CV-LB gap discussions, when validating a strategy against…

Standard Operating Procedure for ANY Kaggle experiment or competition entry.

Systematically replicate and learn from top Kaggle performers.

Analytics and attribution setup — tracking plan, UTM conventions, dashboard design, and attribution model selection.

Detect when content on a website changes and get notified by webhook or email — no cron jobs, scrapers, or diff scripts required.

Build agentic applications with GitHub Copilot SDK.

Execute Hugging Face Hub operations using the `hf` CLI.

Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement…

lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).

MemPalace — Local AI memory with 96.6% recall.

Browse and run any of the ~350 models served by the local cli-proxy-api (all OpenRouter models plus Codex).

Score any AI model on the DeepSWE coding-agent benchmark via the OpenRouter API.

High-throughput LLM inference on NVIDIA GPUs.

Pretrain LLMs at scale with PyTorch 4D parallelism.

Track and visualize ML training experiments with Trackio.

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging…

Deep agentic-flow@alpha integration implementing ADR-001.

W&B: log ML experiments, sweeps, model registry, dashboards.

Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps…

View and manage the evaluation harness — session metrics, baselines, trend analysis, and regression detection.