Data Science & ML Agent Skills for Devin Desktop

Use when an SGLang, vLLM, TensorRT-LLM, or TokenSpeed serving/model optimization task needs prior model-family PR evidence.

Model Predictive Control configuration skill for MPC model identification, tuning, and implementation

Multiple comparison correction methods

NVIDIA Collective Communications Library integration for multi-GPU operations.

Skill for visualizing network and graph data

Solve general nonlinear optimization problems

Use when optimizing configurable system parameters against a measurable scalar objective.

PharmGKB pharmacogenomics annotation skill for drug-gene interaction assessment

Analyze randomized algorithms with probability theory tools and concentration inequalities

Use when writing Python code for DSGE models, HANK models, numerical economic computation, causal inference, or quantitative economic data…

Expert skill for SLAM algorithm selection, configuration, and tuning.

Snakemake workflow management skill for rule-based pipeline execution

spaCy NER model training and entity extraction for conversational AI

STAR alignment skill for splice-aware RNA-seq read mapping with comprehensive QC metrics

Look up Stata command documentation and display formatted help text.

Activate when users mention Stata commands, .do files, regressions, econometrics, stored results, graphs, dataset inspection, replication…

Generates publication-quality figures for ML papers from research context.

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms.

Analyze ML experiment results, compute statistics, generate comparison tables and insights.

Automate Bigml tasks via Rube MCP (Composio).

Bioconductor package discovery, workflow recommendation, setup inspection, and starter code generation grounded