Skill Claude CodeCodex
Hypothesis-driven research workflow for turning research ideas into auditable study plans, experiment designs, execution tracking, and evaluation reports in markdown. Use this skill whenever the user is managing an AI or ML study across framing, experiment design, execution, evaluation, or research iteration; checking…
Agent
Diagnose why a result is strong, weak, contradictory, or tainted, then choose the next action that maximizes evidence gain.
Agent
Turn raw experiment outputs into statistical evidence with explicit assumptions, effect sizes, confidence intervals, and robustness checks during the evaluating stage.
Agent
Turn a vague research direction into a measurable problem statement, explicit scope, and falsifiable hypotheses during the framing research stage.
Agent
Convert proposed hypotheses into experiment designs that are statistically defensible and budget-aware during the designing stage.
Agent
Execute experiments deterministically through approved IDE tools (terminal, python) during the executing stage.
Skill Claude CodeCodex
Convert LaTeX manuscripts (especially ctex / ctexart Chinese academic papers) to editable Word (.docx) while preserving cross-references for figures, tables, equations, and bibliography numbering, and while matching a target journal template's styling. Use this skill whenever the user wants to export a .tex file to…
Skill Claude CodeCodex
Construct, verify, and communicate mathematical proofs for ML theory — convergence rates, generalization bounds, architecture properties, optimization analysis, generative model theory, and scaling laws. Use when the user asks to prove a theorem about an ML algorithm, verify a convergence bound, analyze Lipschitz…
Skill Claude CodeCodex
PyTorch model design, computation graph analysis, profiling, and optimization — from architecture implementation to production-ready training and inference. Use when the user asks about implementing neural architectures in PyTorch, profiling FLOPs/memory/throughput, optimizing training speed or memory usage, debugging…