LabKits

Design and run scientific or engineering experiment loops that optimize toward falsifiable predictions, evaluate whether results support a hypothesis, and revise or replace the hypothesis from first-principles reasoning when evidence contradicts it. Use when the user asks to design experiments, test a hypothesis, iterate until results meet a target, diagnose why an expected result failed, optimize an experiment, build an ablation plan, update a theory from data, or decide whether the original hypothesis is wrong.

Design, run, analyze, and package machine-learning fine-tuning experiments with disciplined hyperparameter search. Use when the user wants to fine-tune an ML model, tune learning rate/batch size/optimizer/regularization/LoRA or adapter parameters, configure Optuna/Ray/W&B/Hugging Face Trainer/Keras/scikit-learn sweeps, compare trials, avoid overfitting, select a final checkpoint, or produce a reproducible training recipe and search report.

Write, revise, audit, and prepare LaTeX research manuscripts for high-standard journals and ML conferences, including Nature, Science, ICLR, ICML, and NeurIPS. Use when the user asks to draft a paper, convert research notes into a manuscript, improve a LaTeX paper, meet venue standards, prepare submission or camera-ready files, strengthen narrative and claims, check anonymization, align with author kits, or preflight LaTeX sources for publication readiness.

Run a methodological agentic loop for exploring a solution space, simulating alternatives, testing hypotheses, pruning weak paths, and converging on a verified answer or implementation. Use when the user asks for an agent to solve an ambiguous, open-ended, multi-step, research, design, engineering, debugging, planning, optimization, or strategy problem where multiple approaches are possible; when they ask to search the solution space, think agentically, run iterative trials, compare candidate solutions, or avoid premature convergence; or when the task needs explicit loop state, evidence, decision criteria, and stop conditions.

Convert dense mathematical statements, theorem/proof fragments, model definitions, equations, losses, algorithms, and notation-heavy research-paper sections into composable knowledge graphs whose labeled edges capture the reasoning flow. Use when the user asks to understand, unpack, explain, verify, teach, simplify, or compare complex math in a paper; when they ask what an equation/model means; when they want a theorem, proof, objective, architecture, or derivation explained at levels from elementary school through Ph.D or expert; or when they need a graph of dependencies, assumptions, transformations, and implications.

Rapidly understand a scientific paper through active reading — visualization plus section-by-section quizzing so the user thinks WITH the AI instead of receiving a passive summary. Use this skill whenever the user shares a paper (arXiv link, PDF upload, or pasted text/abstract) and wants to understand, read, digest, break down, or study it — even if they just say "explain this paper", "help me read this", "what's this paper about", or "walk me through this". Also use when the user wants to prepare to review a paper, discuss related work, or compare a paper against their own research.