Deep methodology knowledge for ML-NMR including IPD/AgD integration, population adjustment, numerical integration, and prediction to target populations. Use when conducting or reviewing ML-NMR analyses.
This skill should be used when the user asks to analyze BAM/SAM/CRAM alignment files from WGS/WES sequencing. Triggers include requests to extract reads from specific regions, identify insertions and deletions, calculate coverage statistics, or export read data as JSON for downstream analysis.
Match essential genes in target genome using orthology and literature
RFdiffusion3 protein design reference. Use when working with RFD3, contigs, symmetry, hotspots, fixed atoms, RASA conditioning, H-bond conditioning, or Foundry API. Covers all input parameters, design types, and best practices.
Screen dsRNA candidates for off-target matches in human and honeybee
BindCraft protein binder design reference. Use when working with AF2 backpropagation, binder design, interface optimization, PyRosetta metrics, design filtering, or comparing with RFdiffusion approaches.
Spatial region-aware cell matching for CODEX/scRNAseq integration
Comprehensive skill for CellPhoneDB - Database of cell type markers and cell-cell communication analysis for single-cell data. Use for cell type annotation, ligand-receptor analysis, cell-cell interaction inference, and communication network visualization.
Gene, drug compound, and disease research using NCBI Extended databases. Triggers: 基因, gene, 藥物, drug, compound, PubChem, ClinVar, 變異, variant, 臨床意義
AI-assisted sanitization of Bruker NMR datasets for blind CASE studies. Removes compound identity from metadata while preserving spectroscopic data for valid CASE evaluation.
Find and acquire computational science resources autonomously. Use when you need force field parameters, pseudopotentials, crystal structures, or any other scientific data. You are a researcher - you find what you need.
Run Quantum ESPRESSO DFT calculations. Use when asked to perform first-principles calculations, SCF, structural relaxation, band structure, DOS, phonons, or any ab initio quantum mechanical calculation.
Reference documentation for PDBx/mmCIF dictionary queries and category lookup
Search and download NMR spectroscopy datasets from nmrxiv.org. Use when the user asks to find NMR data, search for HSQC/HMBC/COSY/DEPT experiments, look up compounds by name or SMILES, download NMR datasets, or access nmrxiv.org data programmatically. Outputs JSON for easy parsing.
Query materials databases for structures and properties. Use when asked to get crystal structures, material properties, phase diagrams, or thermodynamic data. Primary source is Materials Project, with NIST, PubChem as secondary.
Deep technical assistant for projects that combine Neural Quantum States (FFNN and Transformer-based) with Sample-based Quantum Diagonalization (SQD). Trigger this skill whenever the task involves: (1) designing or analyzing NQS architectures for quantum chemistry, (2) connecting classical samplers to qiskit-addon-sqd, (3) studying sample-efficiency, bias, and variance in few-sample regimes (e.g. 12–14-bit H2).
Analyze simulation data and compute properties. Use when asked to parse LAMMPS/QE output, calculate diffusion coefficients, RDF, MSD, energies, or generate plots and visualizations.
Randomly select items from lists using various algorithms for fair and unbiased selection
Python development for scientific computing and SciTeX projects. Includes testing, debugging, ML practices, and environment management.
Design Science Research Methodology for rigorous artifact development. Use this skill when: (1) Creating new tools, frameworks, or systems that solve real problems (2) Need structured approach to build-evaluate-iterate cycles (3) Want scientific rigor in development process (4) Evaluating artifacts against clear criteria (5) Documenting research contributions systematically Based on Hevner et al. (2004) and Peffers et al. (2007) - foundational DSR papers.
Modern polynomial API for fitting, root finding, and working with orthogonal series like Chebyshev and Legendre. Triggers: polynomial, polyfit, Chebyshev, Legendre, root finding.
