
Spreadsheet toolkit (.xlsx/.csv). Create/edit with formulas/formatting, analyze data, visualization, recalculate formulas, for spreadsheet processing and analysis.
Presentation toolkit (.pptx). Create/edit slides, layouts, content, speaker notes, comments, for programmatic presentation creation and modification.
Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.
Use when comparing multiple named alternatives across several criteria, need transparent trade-off analysis, making group decisions requiring alignment, choosing between vendors/tools/strategies, stakeholders need to see decision rationale, balancing competing priorities (cost vs quality vs speed), user mentions "which option should we choose", "compare alternatives", "evaluate vendors", "trade-offs", or when decision needs to be defensible and data-driven.
Use when making quick order-of-magnitude estimates under uncertainty (market sizing, resource planning, feasibility checks), decomposing complex quantities into estimable parts, bounding unknowns with upper/lower limits, sanity-checking strategic assumptions, or when user mentions Fermi estimation, back-of-envelope calculation, order of magnitude, ballpark estimate, triangulation, or needs to assess feasibility before detailed analysis.
Use when you have implemented an equivariant model and need to verify it correctly respects the intended symmetries. Invoke when user mentions testing model equivariance, debugging symmetry bugs, verifying implementation correctness, checking if model is actually equivariant, or diagnosing why equivariant model isn't working. Provides verification tests and debugging guidance.
Expert guidance for regression analysis, statistical modeling, and outlier detection in Python using statsmodels, scikit-learn, scipy, and PyOD - includes model diagnostics, assumption checking, robust methods, and comprehensive outlier detection strategies
Use for materials analysis tasks in pymatgen.analysis: phase/Pourbaix/chemical-potential diagrams, reactions, structure matching, surfaces/interfaces, local environments, diffraction, elasticity, magnetism, and related analyses.
Use for VASP input generation, POTCAR handling, and parsing VASP outputs (vasprun.xml, OUTCAR, OSZICAR, PROCAR, CHGCAR, LOCPOT, EIGENVAL) via pymatgen.io.vasp and input sets.
Use for external data access via pymatgen.ext: Materials Project (MPRester), OPTIMADE endpoints, and COD lookups.
Use for pymatgen core objects and structure manipulation: Element/Specie/Composition, Lattice/Site/Structure/Molecule, oxidation states, structure edits, transformations, and serialization.
Use for symmetry analysis, space group determination, standardization, and k-path generation using pymatgen.symmetry.
Expert guidance for JAX (Just After eXecution) - high-performance numerical computing with automatic differentiation, JIT compilation, vectorization, and GPU/TPU acceleration; includes transformations (grad, jit, vmap, pmap), sharp bits, gotchas, and differences from NumPy
Structured brainstorming and ideation facilitation using proven creativity techniques. Use when users want to generate ideas, explore solutions, break through creative blocks, or need facilitated ideation sessions. Triggers include requests like 'help me brainstorm,' 'generate ideas for,' 'creative solutions to,' or 'think of alternatives.'
Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or geophysical flows. Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis.
Use when optimizing multi-factor systems with limited experimental budget, screening many variables to find the vital few, discovering interactions between parameters, mapping response surfaces for peak performance, validating robustness to noise factors, or when users mention factorial designs, A/B/n testing, parameter tuning, process optimization, or experimental efficiency.
Document toolkit (.docx). Create/edit documents, tracked changes, comments, formatting preservation, text extraction, for professional document processing.
Expert guidance for Meta's FAIRChem library - machine learning methods for materials science and quantum chemistry using pretrained UMA models with ASE integration for fast, accurate predictions
Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.
Expert assistant for accessing materials databases (AFLOW and Materials Project) - query crystal structures, materials properties, thermodynamic data, and computational results from comprehensive databases
Expert assistant for calculating materials properties from first-principles using ASE - structure relaxation, surface energies, adsorption, reaction barriers, phonons, elastic constants, and thermodynamic modeling with proper scientific methodology
a file-based long-term memory using a single JSONL file, with append-only writes and recent-window search via bash + jq.
Use for non-VASP input/output tasks in pymatgen.io: CIF/XYZ/Gaussian/OpenBabel and DFT/MD code IO such as CP2K, Q-Chem, ABINIT, LAMMPS, FEFF, NWChem, Quantum ESPRESSO, Wannier90, phonopy/shengbte, etc.
OpenMX (openmx) workflows with emphasis on OpenMX v3.9: write and validate input .dat files (System.Name, Atoms.SpeciesAndCoordinates, scf.Kgrid, Band.kpath), run SCF/geometry optimization/band/DOS/NEB/ESM/SOC(+U)/unfolding/Wannier90/NEGF examples, and interpret outputs (.out/.scfout/restart). Trigger this skill whenever the user mentions OpenMX/openmx.
PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.
Structured planning and project breakdown using proven methodologies for goals, projects, and strategic initiatives. Use when users need to create plans, break down complex projects, set milestones, estimate timelines, identify dependencies, or develop action plans. Triggers include 'help me plan,' 'create a roadmap for,' 'break down this project,' 'what are the steps to,' or 'how should I approach.'
Use for electronic structure analysis with pymatgen.electronic_structure: DOS, band structures, COHP/COOP, and plotting utilities.
Use for phonon band structure/DOS, Gruneisen, and IR spectra analysis with pymatgen.phonon and phonopy-compatible outputs.
Expert assistance with the Atomic Simulation Environment (ASE) Python library for atomistic simulations, including structure building, calculator setup, optimization, dynamics, and analysis
Expert guidance for multiobjective optimization in Python - Pareto optimality, evolutionary algorithms (NSGA-II, NSGA-III, MOEA/D), scalarization methods, Pareto front analysis, and implementation with pymoo, platypus, and DEAP
Expert guidance for mathematical optimization in Python - systematic problem classification, library selection (scipy, pyomo, cvxpy, GEKKO), solver configuration, and implementation patterns for LP, QP, NLP, MIP, convex, and global optimization problems
Comprehensive plotting and visualization in Python - matplotlib (static publication-quality plots), seaborn (statistical visualization), and plotly (interactive plots); includes plot types, customization, best practices, and library selection guidance
Use when you've identified candidate symmetries and need to map them to mathematical groups for architecture design. Invoke when user mentions cyclic groups, dihedral groups, Lie groups, SO(3), SE(3), permutation groups, or needs to formalize symmetries into group theory language. Provides taxonomy and mathematical foundations from Visual Group Theory principles.
Use when you need to empirically test whether hypothesized symmetries actually hold in your data or model. Invoke when user mentions testing invariance, validating equivariance, checking if symmetry assumptions are correct, debugging symmetry-related model failures, or needs data-driven validation before committing to equivariant architecture. Provides test protocols and metrics.
Use when problems involve interconnected components with feedback loops (reinforcing or balancing), delays, or emergent behavior where simple cause-effect thinking fails. Invoke when identifying leverage points for intervention (where to push for maximum effect with minimum effort), understanding why past solutions failed or had unintended consequences, analyzing system archetypes (fixes that fail, shifting the burden, tragedy of the commons, limits to growth, escalation), mapping stocks and flows (accumulations and rates of change), discovering feedback loop dynamics, finding root causes in complex adaptive systems, designing interventions that work with system structure rather than against it, or when user mentions systems thinking, leverage points, feedback loops, unintended consequences, system dynamics, causal loop diagrams, or complex systems. Apply to organizational systems (employee engagement, scaling challenges, productivity decline), product/technical systems (technical debt accumulation, performance degradation, adoption barriers), social systems (polarization, misinformation spread, community issues), environmental systems (climate, resource depletion, pollution), personal systems (habit formation, burnout, skill development), and anywhere simple linear interventions repeatedly fail while systemic patterns persist.
Expert assistant for VASP (Vienna Ab initio Simulation Package) calculations - input file generation, parameter selection, workflow setup, and best practices for accurate DFT calculations
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.
Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.
Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.
Use this skill when working with symbolic mathematics in Python. This skill should be used for symbolic computation tasks including solving equations algebraically, performing calculus operations (derivatives, integrals, limits), manipulating algebraic expressions, working with matrices symbolically, physics calculations, number theory problems, geometry computations, and generating executable code from mathematical expressions. Apply this skill when the user needs exact symbolic results rather than numerical approximations, or when working with mathematical formulas that contain variables and parameters.
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
Use when investigating why something happened and need to distinguish correlation from causation, identify root causes vs symptoms, test competing hypotheses, control for confounding variables, or design experiments to validate causal claims. Invoke when debugging systems, analyzing failures, researching health outcomes, evaluating policy impacts, or when user mentions root cause, causal chain, confounding, spurious correlation, or asks "why did this really happen?"
Use when dealing with complex systems that need simplification, identifying bottlenecks or critical failure points, redesigning architecture or processes for better performance, breaking down problems that feel overwhelming, analyzing dependencies to understand ripple effects, user mentions "this is too complex", "where's the bottleneck", "how do we redesign this", "what are the key components", or when optimization requires understanding how parts interact.
Use when you have validated symmetry groups and need to design neural network architecture that respects those symmetries. Invoke when user mentions equivariant layers, G-CNN, e3nn, steerable networks, building symmetry into model, or needs architecture recommendations for specific symmetry groups. Provides architecture patterns and implementation guidance.
Use when prompts produce inconsistent or unreliable outputs, need explicit structure and constraints, require safety guardrails or quality checks, involve multi-step reasoning that needs decomposition, need domain expertise encoding, or when user mentions improving prompts, prompt templates, structured prompts, prompt optimization, reliable AI outputs, or prompt patterns.
Use when analyzing failures, outages, incidents, or negative outcomes, conducting blameless postmortems, documenting root causes with 5 Whys or fishbone diagrams, identifying corrective actions with owners and timelines, learning from near-misses, establishing prevention strategies, or when user mentions postmortem, incident review, failure analysis, RCA, lessons learned, or after-action review.
Use when ML engineers need to identify symmetries in their data but don't know where to start. Invoke when user mentions data symmetry, invariance discovery, what transformations matter, or needs help recognizing patterns their model should respect. Works collaboratively through domain analysis, transformation testing, and physical constraint identification.