616 skills · sorted by relevance
Prepare text for language models by splitting it into tokens, small units represented by numbers. The skill covers batch processing, training custom vocabularies, tracking positions in the original text, and adjusting input lengths.
Set up GPU servers on Lambda Labs for machine learning training and inference. Follow workflows for SSH access, persistent storage, Python API operations, and distributed training that spreads work across multiple GPUs or servers.
Tune AgentDB memory use and search speed through quantization, which stores vectors more compactly, search indexes, caching, and batch operations. Includes configuration examples and benchmarks to help balance accuracy, speed, and storage as datasets grow.
Tune AgentDB memory use and search speed through quantization, which stores vectors more compactly, search indexes, caching, and batch operations. Includes configuration examples and benchmarks to help balance accuracy, speed, and storage as datasets grow.
Run Apify Actors, programs that collect web data, through the Composio integration. Retrieve structured results, create reusable tasks with preset inputs, and inspect execution logs for both quick collection jobs and longer runs.
Analyze CSV, Parquet, and JSON files to answer questions through grouping, joins, cleaning, time series, and charts. Chooses DuckDB or Polars and a suitable processing location based on the task and available memory.
Create and update dashboards with charts, metrics, and tables drawn from connected data sources or attached files. Link displayed values to their sources so readers can inspect queries, calculations, and freshness while reviewing business indicators or recurring reports.
Stress-test research plans by comparing possible scenarios, such as sample losses, unavailable materials, or methods failing to transfer. Record assumptions and evidence, compare response options, and define contingency plans and observable triggers for changing course.
Use Hugging Face Transformers to load pretrained models, generate text, and classify text, images, or audio. Prepare model inputs, control generation settings, and fine-tune models on custom datasets with the Trainer API.
Build Python workflows for filtering, grouping, joining, and reshaping table data with Polars. Get guidance on migrating pandas code and using lazy evaluation, which optimizes a processing plan before execution, for large datasets.
Work with genomic regions in Polars tables to find overlaps, nearby regions, covered bases, and gaps. Read and write bioinformatics files, query data with SQL, and check coordinate conventions when joining datasets or migrating from bioframe.
Analyze drug concentration and response data to calculate exposure, fit models of drug movement and effects, and simulate dosing schedules. Produces exploratory research results with explicit assumptions and diagnostic checks.
Inspect and transform local DICOM medical imaging files, including metadata, image frames, and compression formats. Generate technical inventories and preview images, check installed codecs, and review pseudonymized derivatives without treating those checks as proof of de-identification.
Finds papers, preprints, citation links, and openly available full text through 18 scholarly APIs. Selects databases for the task and returns relevant records with search parameters, identifiers, and access dates so the retrieval can be repeated.
Build molecular property prediction workflows with DeepChem for solubility, toxicity, and related chemistry tasks. Prepare molecular representations, choose compatible models, handle missing labels, and evaluate predictions using data splits designed for the intended scientific question.
Inspect FCS files from flow cytometry, a method for measuring cell properties, using FlowIO. Extract measurement data into NumPy arrays, review channel metadata, export tables, and create FCS 3.1 files for downstream work.
Manage Azure Machine Learning resources from Python with SDK v2. The skill provides implementation examples for registering data and models, configuring compute and environments, submitting training jobs, monitoring logs, and connecting steps into pipelines.
Investigate slow SQL using execution plans, which show how a database processes a query. Review indexes, filters, joins, and maintenance practices through PostgreSQL examples to identify bottlenecks and plan changes to queries or database structure.
Turn documents, notes, research, or code into a knowledge graph that maps identifiable things and their relationships. Create or update entity files and typed connections, with source evidence attached for inspection and later visualization.
Build an end-to-end evaluation pipeline for Python AI applications using pixie-qa and real language-model calls. Define criteria, prepare realistic test data, score application runs, and analyze the evidence to produce a prioritized improvement plan.
Write focused C# unit tests with XUnit, including tests that run against multiple input datasets. Apply consistent naming, setup, assertions, shared fixtures, and mock dependencies to keep tests readable, independent, and organized.
Finds and retrieves paid financial datasets when free sources lack coverage or detail. Guides comparison of providers, success rates, prices, and required inputs, while keeping execution costs and remaining credits visible.
Prepare text for language models using HuggingFace Tokenizers, which splits text into model-readable units. Train custom vocabularies, process batches, track original text positions, and configure input lengths for use with transformers.
Train language models with SimPO using pairs of preferred and rejected answers. Configure preference training without a separate reference model, adapt settings for base or instruction models, and address unstable training, memory limits, or lost capabilities.