Quantitative research requires consistent data, statistical methods, and validation. This skill structures Longbridge workflows for analysis, screening, optimization, execution, and hedging.

Brokerage data and portfolio decisions are difficult to review across separate screens. This skill retrieves Longbridge account data and provides structured analysis and controlled actions.

Market data is fragmented across symbols, sessions, and formats. This skill retrieves Longbridge data and converts it into clear, sourced analysis.

Market research and account analysis often require several disconnected tools. This skill organizes Longbridge CLI, MCP, and SDK workflows for data, content, portfolios, and development.

Merchants need current supplier product data before choosing inventory. This skill queries LegendShop product, inventory, price, and balance data through the platform API.

Database schema design can become fragmented across notes, SQL drafts, and diagrams. DB Craft opens a local visual studio to model tables, validate structure, and export SQL.

Large tabular datasets often exceed local memory and make pandas workflows slow. This skill guides Claude, Codex, and Claude Code through Vaex workflows for lazy analysis, conversion, visualization, and ML.

Transformer workflows often require many APIs for inference, generation, tokenization, and training. This skill gives Claude, Codex, and Claude Code focused guidance for using Hugging Face Transformers.

Symbolic math tasks can become error-prone when formulas need exact algebraic results. This skill guides Claude, Codex, and Claude Code through SymPy workflows for solving, simplifying, differentiating, integrating, and generating mathematical output.

Protein interaction analysis often requires manual API queries and careful identifier mapping. This skill queries STRING, maps identifiers, retrieves networks, and summarizes enrichment results.

Reinforcement learning setup is easy to misconfigure. This skill guides SB3 training, custom environments, callbacks, evaluation, and model persistence.

DICOM files contain complex image data and medical metadata that are hard to inspect safely. This skill guides Claude, Codex, and Claude Code through pydicom workflows for reading, converting, anonymizing, and extracting DICOM data.

Bulk RNA-seq differential expression requires careful count preparation, design selection, and result interpretation. This skill guides PyDESeq2 workflows from input checks to tested genes, plots, and saved results.

Reinforcement learning experiments slow down when environments and training loops cannot scale. PufferLib helps Claude, Codex, and Claude Code design faster vectorized training workflows.

Computational pathology work needs careful choices for image loading, preprocessing, storage, and model workflows. This skill gives Claude, Codex, and Claude Code PathML guidance for whole-slide image analysis and multiplex imaging tasks.

Graph projects need clear methods for building and analyzing relationships. This skill guides NetworkX workflows for algorithms, formats, and visual outputs.

Molecular ML projects need consistent features from SMILES and RDKit molecules. This skill guides molfeat choices, batch featurization, pretrained embeddings, caching, and QSAR workflows.

Scientific teams need reliable help creating MATLAB and GNU Octave workflows. This skill provides focused guidance for analysis, visualization, compatibility, and script execution.

Metabolomics teams need reliable ways to clean spectra and compare unknown compounds against libraries. This skill guides Claude, Codex, and Claude Code through matchms workflows for filtering, similarity scoring, and compound identification.

Biology teams need reproducible data systems that connect datasets, metadata, workflows, and ontology terms. This skill guides LaminDB setup, curation, querying, lineage tracking, and integrations.