Model Training & Fine-tuning Agent Skills

Fine-tune instruction-following LLMs with Unsloth's optimized SFTTrainer, covering dataset formatting, chat templates, training configuration, and thinking-model patterns.

Generates Python code to batch-translate the English column of tab-separated CSV files while preserving the original Chinese column and output format.

Reads and preprocesses 5-minute stock candlestick CSV data, then clusters the time series using tslearn's TimeSeriesKMeans, including data cleaning, percentage change calculation, model training, saving, and representative sample extraction.

编写评估FastText文本分类模型的Python函数，计算accuracy、F1、recall和precision指标，并处理特定格式的标签文本分割。

Compiles SOUL.md character profiles into synthetic diploid genomes by mapping trait scores to alleles at defined loci, producing .genome.json files.

Analyzes raw genomic data (FASTQ/VCF) to generate non-medical wellness, longevity, and pharmacogenomic optimization protocols while keeping DNA processing local and private.

Guides users through participating in the SOMA decentralized training network, covering data submission, model training, reward claiming, and strategic optimization.

Runs time series machine learning tasks—classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search—using the scikit-learn compatible aeon toolkit.

Build, fit, validate, and compare Bayesian models using PyMC, including hierarchical models, MCMC sampling, variational inference, posterior predictive checks, and model comparison.

Runs an autonomous optimization loop that iteratively improves an artifact against an objective and evaluator using Hypothesis Tree Refinement, with subagent executors in isolated git worktrees.

Solves single- and multi-objective optimization problems with NSGA-II/III, MOEA/D, and other evolutionary algorithms, including constraint handling, Pareto front analysis, and benchmark problems.

Access AI-ready drug discovery datasets, benchmarks, and molecular oracles from Therapeutics Data Commons for therapeutic machine learning and pharmacological prediction.

Run cloud-native molecular modeling and drug-design workflows via a Python API, covering pKa prediction, docking, conformer and tautomer ensembles, molecular dynamics, and related small-molecule or protein tasks without local HPC infrastructure.

Trains machine learning models on genomic interval data from BED files, including region embeddings, single-cell ATAC-seq analysis, and consensus peak building.

Loads and processes whole-slide pathology images, builds spatial graphs, trains deep learning models, and analyzes multiplexed immunofluorescence data across 160+ slide formats.

Analyze RNA velocity in single-cell RNA-seq data with scVelo, estimating cell state transitions from unspliced/spliced mRNA dynamics, inferring trajectory directions, computing latent time, and identifying driver genes.

Orchestrates AI/ML workflows for building LLM applications, RAG systems, AI agents, and ML pipelines, covering design, integration, observability, and security.

Performs constraint-based metabolic modeling with COBRApy: FBA, FVA, gene knockouts, flux sampling, and SBML model handling for systems biology and metabolic engineering.

Filters and prioritizes compound libraries in drug discovery using drug-likeness rules, structural alerts, complexity metrics, and a query language.

Entrena modelos de machine learning con Scikit-learn, LightGBM y XGBoost, desde un baseline hasta un modelo productivo con validación robusta y explicabilidad.

Orquesta el ecosistema de agentes: decide qué modelo o tier usar, delega tareas a sub-agentes especializados y planifica arquitectura técnica.

Analiza series temporales: tendencia, estacionalidad y pronóstico con Prophet, statsmodels y ML, incluyendo descomposición, tests de estacionariedad y evaluación contra baselines.

Turn model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

Runs the open-source LLaVA vision-language model for image understanding, captioning, visual question answering, and multi-turn image conversations, including setup, inference, and training guidance.

Run ML workloads on Modal's serverless GPU cloud: deploy models as auto-scaling APIs, run batch jobs, and schedule tasks with pay-per-second GPU pricing.

Trains LLMs with SimPO, a reference-free preference optimization method that outperforms DPO, using configurable hyperparameters and workflows for various models and tasks.

Operate Hugging Face Hub repositories, models, datasets, and Spaces via the hf CLI, including downloads, uploads, authentication, and compute jobs.

Trains and analyzes Sparse Autoencoders (SAEs) with SAELens to decompose neural network activations into interpretable features, covering loading pre-trained SAEs, training custom ones, and feature steering.

Manage Hugging Face Hub resources via the `hf` CLI: download and upload models, datasets, and spaces; manage buckets, cache, collections, discussions, and inference endpoints; run SQL queries on datasets.

Monitors OpenClaw model API usage and prompts for user confirmation before switching models when quota is low.

Orchestrates AI/ML workflows for building LLM applications, RAG systems, AI agents, and ML pipelines, covering design, integration, observability, and security.

Build, optimize, and execute quantum circuits on IBM Quantum hardware or local simulators using Qiskit, including transpilation, primitives, and algorithm libraries.

Guides production LLM operations: RAG pipelines, embeddings, vector databases, fine-tuning, prompt engineering, cost estimation, quality evals, and AI architectures.

Predicts enhancer activity in DNA sequences using the hosted Genomic Intelligence G0 DeepSTARR model, returning per-window activity scores.

Statistical fine-mapping of GWAS loci using SuSiE, SuSiE-inf, and Approximate Bayes Factors to identify credible sets and posterior inclusion probabilities (PIPs) for causal variant discovery. SuSiE-inf adds an infinitesimal polygenic component for improved calibration at well-powered loci.

Simulates meiotic recombination to produce offspring genomes from parent pairs, modeling Mendelian segregation, de novo mutation, sex determination, trait inference, and clinical evaluation against a disease registry.