Use case
Claude Code skills for ML & evaluation engineers
Measure what actually matters — agent behavior, harness fit, and context quality, not just leaderboard scores.
Quick answer
ML and evaluation engineers use Loreto skills to benchmark agents beyond model scores, audit whether context fits the task, and evaluate AI harnesses on real dimensions.
Skills to start with
AI Harnesses
Detecting Harness Lockin
Identifies and quantifies the compounding switching cost of an AI coding agent harness commitment before it becomes inv…
AI Evaluation
Evaluating AI Harness Dimensions
Evaluates AI coding agent platforms across five structural dimensions — execution philosophy, state and memory, context…
AI Harnesses
Routing Work Across AI Harnesses
Designs hybrid agent workflows that route tasks intelligently between AI coding agent harnesses based on task character…
Your workflow, as a skill
Loreto turns what you already know into a Claude Code skill your agent can run on demand.