Analytics & Monitoring Agent Skills for DeepSeek Harness

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

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics…

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.

This skill should be used when designing multi-agent systems that need context isolation, supervisor or swarm coordination, explicit…

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

OBLITERATUS: abliterate LLM refusals (diff-in-means).

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.

Fine-tune large LLMs with LoRA on limited GPU memory.

Agent skill for performance-benchmarker - invoke with $agent-performance-benchmarker

Agent skill for performance-analyzer - invoke with $agent-performance-analyzer

Agent skill for performance-monitor - invoke with $agent-performance-monitor

Debug LLM applications using the Phoenix CLI.

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

This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at…

Clean training loops with built-in distributed support.

Distributed training orchestration across clusters.

Debug and optimize AI agents by analyzing reasoning traces, context degradation, tool confusion, instruction drift, repeated task…