Analytics & Monitoring Agent Skills for Claude Code

Run, read, and compare dataset-backed experiments to find evidence that a prompt or pipeline is improving.

Fast vector similarity search at billion scale.

Speed up long-sequence transformer training and inference.

GitHub repository analytics dashboard — stars, forks, contributors, issues, pull requests, recent activity, and top contributors.

Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help.

Run PyTorch training across GPUs with minimal changes.

Fast BPE/WordPiece tokenization and custom vocab training.

Interact with Langfuse and access its documentation.

Create refreshable, auditable Open Design artifacts backed by connector or local data.

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and…

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM.

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining.

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT.

Curate LLM training data: dedupe, filter, PII redaction.

OpenAI Images API: batches, prompt sampler, gallery.

Autonomously optimize code for performance using CodSpeed benchmarks, flamegraph analysis, and iterative improvement.

Outlines: structured JSON/regex/Pydantic LLM generation.

Add and manage evaluation results in Hugging Face model cards.

Build and run evaluators for AI/LLM applications using Phoenix.

Clean training loops with built-in distributed support.

SAM: zero-shot image segmentation via points, boxes, masks.