Analytics & Monitoring Agent Skills

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…

Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database.

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

This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure.

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

Semantica full-stack knowledge graph skill for context graphs, decision intelligence, explainability, extraction, reasoning…