Skill Claude CodeCodex
Same-epoch comparison of training runs across wandb, neptune, tensorboard, or mlflow. Aligns runs at the student's current step (never current-vs-final-of-baseline) and separates proxy metrics from downstream targets. Use when the user asks to compare runs, check if a run is improving, track lag against a baseline…
Skill Claude CodeCodex
Evidence-before-action diagnosis of failing ML experiments. Probes the system before guessing causes, process list, dmesg, GPU stats, log scrollback, checkpoint state, then states a hypothesis as a hypothesis and runs a smoke before claiming a root cause. Use when the user asks why a run is failing, diverging, OOMing…
Skill Claude CodeCodex
Use when the user wants to verify paper claims against code or data, audit numerical accuracy, check formula-code alignment, or validate citation accuracy. Triggers on phrases like "verify claims", "check numbers", "do the numbers match", "formula vs code", "audit the paper", or "cross-check results".
Skill Claude CodeCodex
Research paper writing assistant that enforces Arpit Gupta's editorial principles, voice profile, and writing workflow. MANDATORY TRIGGERS: Use this skill whenever the user mentions writing a paper, drafting a section, revising a section, editing a paper, reviewing a draft, rewriting an introduction, writing an…
Skill Claude CodeCodex
Score a PhD applicant's profile and rank candidate advisors using a connection-first 4.0-scale scoring system. Best-supported for physics / HEP and materials science (MSE), with the scoring engine extensible to chemistry, biology, CS, math, EE, ChemE, earth science (each with field-specific caveats — see…