**Guide materials discovery workflows from concept to crystal structures.** Generate, enumerate, and organize inorganic crystal structure candidates for screening, DFT, ML training, and experimental synthesis planning. Handles complete pipeline from elements-only input to ASE database storage with provenance tracking. **Trigger this skill for:** - Structure generation: "generate candidates", "create structures", "build crystal structures", "make supercells" - Chemical exploration: "screen compositions", "chemical substitution", "doping", "solid solutions", "ion exchange" - Materials classes: "battery cathodes", "perovskites", "isostructural analogues", "high-entropy oxides", "defects" - Configuration space: "enumerate orderings", "SQS generation", "disorder-to-ordered", "vacancy defects", "interstitials" - Scale: "generate 50 structures", "100 candidates", "high-throughput", "ML training set", "candidate library" - Starting points: Element lists ("Li-Mn-P-O system"), formulas ("LiCoO2 analogues"), struct
Generate a good first-guess synthesis recipe for an inorganic material as the seed of a lab campaign. Sources the route by best available evidence: literature-validated recipes (Materials Project) first, then a route reasoned from solid-state chemistry and analogous known systems. Produces a structured, robot-middleware-ready recipe (precursors with forms, ordered steps with parameters), defines the tunable parameter search space for downstream Bayesian-optimization refinement, and can quantify precursor masses for a target batch size. Use this skill WHENEVER the user wants a synthesis route, recipe, or procedure; asks how to make / prepare / synthesize a compound or formula; needs precursors, calcination/annealing conditions, or a solid-state route; or when a DFT-validated candidate needs a first synthesis plan to hand to a robotic lab. It does NOT execute synthesis or approve autonomous runs — a separate experiment-orchestration skill plus a human gate own that — and it does NOT run the optimization loop it
End-to-end guidance for running molecular quantum-chemistry with ORCA on an HPC via the dft_* MCP tools, plus ORCA-specific post-processing (orca_* tools) — designing the calculation (method/basis/solvation), submitting and monitoring jobs, triaging SCF/geometry failures, interpreting outputs, and generating visualization cubes. Covers single-point energies, geometry optimization, frequencies/thermochemistry, and design guidance for TD-DFT, scans, NEB-TS, and multireference. Use this skill WHENEVER the user wants to run, set up, debug, or interpret an ORCA calculation on a molecule; compute a molecular property (energy, HOMO/LUMO gap, dipole, frequencies, reaction/binding energy); optimize or verify a molecular geometry; analyze an existing ORCA output directory (.out/.gbw); generate HOMO/LUMO, electron-density, or ESP cube files; or asks about ORCA input (! keywords, %blocks), basis sets (def2-*), functionals, charge/multiplicity, SCF convergence, or orca_plot — even if they don't say "ORCA". For periodic/cr
End-to-end guidance for running periodic plane-wave DFT with VASP on an HPC via the dft_* MCP tools — designing the calculation, submitting and monitoring jobs, triaging failures, and interpreting results back into a materials-discovery decision. Covers the full calculation range: relaxation, static/SCF, DOS, band structure, dielectric/optical, magnetism + Hubbard U, phonons, AIMD, and NEB. Use this skill WHENEVER the user wants to run, set up, debug, or interpret a VASP calculation, validate a candidate with DFT, compute a solid-state property (formation energy, band gap, elastic/phonon/DOS), verify an ML-predicted property flagged by candidate-screener, or asks anything about INCAR/KPOINTS/POTCAR/POSCAR, ENCUT/k-point convergence, SLURM submission of VASP, or electronic/ionic convergence problems — even if they don't explicitly say "VASP". For molecular quantum chemistry use the `orca` skill instead; for fast ML property prediction (not DFT) use the matgl/matcalc tools.
Guide for screening and ranking materials candidates — validating structures, retrieving properties, and ranking by multi-objective criteria. Helps decide how to handle disordered structures (majority/enumeration/SQS ordering), suggests where to get properties (Materials Project, ASE cache, or ML predictions with MatGL/matcalc), and ranks candidates with confidence-aware multi-objective methods. Use this whenever candidates need property enrichment and ranking: validating candidate structures, predicting or retrieving formation energy / band gap / mechanical / vibrational / surface properties, filtering by application-specific criteria, or ranking by multiple objectives. Trigger keywords: screen candidates, validate structures, property retrieval, hierarchical data, rank materials, filter candidates, multi-objective optimization, battery screening, catalyst discovery, thermoelectric screening, phosphor screening, mechanical properties, phonon stability, surface energies, formation energy prediction, band gap
Analyze thermodynamic stability of inorganic materials by routing between two workflows: a cheap Materials Project-backed lookup path for known compositions, and a custom self-consistent MLIP hull workflow for novel or structure-specific materials. Use this skill whenever the user asks whether a material is stable, requests energy above hull, decomposition products, polymorph context, or wants to include stability as a screening criterion. This skill is intended to become the single orchestration layer for stability analysis, with workflow branching handled in the skill rather than inside an MCP tool.
Autonomous optimization using ARROWS (thermodynamically-guided synthesis) or Bayesian Optimization (generic process optimization). Orchestrates closed-loop experimentation from campaign setup through iterative learning to convergence.
Guides users through authoring or extending an Isaac Lab/Isaac Sim YAML scene file (robots, assets, positions, physics) and generates the ready-to-run `*_isaac.py` script via the bundled `isaac_scene_loader.py`. Use this skill whenever the user wants to set up a virtual robot lab scene in Isaac Sim, add or configure robots/assets in Isaac Lab, generate an Isaac Lab Python script from a YAML description, initialise a new simulation environment, or load USD models into an Isaac Sim stage — even if they don't say "YAML" or "Isaac Lab" explicitly.