1.2K skills · sorted by relevance
Create AgentDB learning plugins that use recorded experience to improve agent decisions. Choose a learning method, store states, actions, and rewards, train models, and evaluate suggested actions through CLI and API workflows.
Create AgentDB learning plugins that use recorded experience to improve agent decisions. Choose a learning method, store states, actions, and rewards, train models, and evaluate suggested actions through CLI and API workflows.
Review JavaScript loops and replace suitable ones with standard array and object methods. Make transformations, filtering, and aggregation easier to understand, with practical explanations and browser checks to confirm that changes preserve the intended behavior.
Implement caching and data conversion for syncable entities in Twenty's server code. Build lookup maps, convert stored records and inputs into flat representations, and resolve references to universal identifiers for later validation and processing.
Organize research sources in self-hosted Open Notebook, then search them, ask questions with citations, create notes, transform text, or generate podcasts with multiple speakers. Supports REST API automation and configuration of local or cloud AI providers.
Helps plan and implement database structure changes and data transformations using Sequelize, TypeORM, or Prisma. Includes staged changes intended to avoid downtime, plus transaction and backup examples for rolling back failed migrations.
Design dbt data transformations with clearly organized models, data quality tests, documentation, and incremental processing that updates only part of a dataset. Use it to structure analytics tables and organize a dbt project.
Reduce the memory needed to run large language models with GPTQ quantization, which stores model weights at lower precision. Covers loading compressed models, quantizing your own models, choosing execution backends, and connecting to memory-efficient fine-tuning.
Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.
Use Outlines to make language models produce data in a defined format. The skill covers extracting information into JSON, restricting classification labels, and applying Pydantic models, which define fields and data types, with local model backends.
Extend the amount of text a language model can process at once. Compares RoPE, YaRN, ALiBi, and position interpolation, with implementation examples, additional training guidance, and memory optimization approaches for long document processing.
Extract fields, filter records, and reshape JSON from API responses, configuration files, or logs using Crush’s built-in jq. Get help writing and debugging transformations, constructing new JSON, and formatting output for other commands.
Write JavaScript for n8n Code nodes to aggregate, filter, and transform workflow data. Guidance covers data access, output formats, execution modes, common errors, and performance choices when processing large numbers of records.
Build n8n workflows that download, transform, and send files without losing their contents. Learn how file data differs from JSON, how to preserve attachments, and how to use storage keys or URLs with AI tools and chat messages.
Helps extend how much text a language model can process at once. Covers choosing RoPE, YaRN, ALiBi, or position interpolation, implementing position information, fine-tuning on longer documents, and managing memory during inference.
Use Outlines to make language models produce data in a defined format. The skill covers extracting information into JSON, restricting classification labels, and applying Pydantic models, which define fields and data types, with local model backends.
Use SAELens to train and analyze sparse autoencoders, which break model activations into a small set of interpretable features. Explore pretrained features, evaluate reconstruction quality, troubleshoot training, and test how individual features influence generated text.
Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.
Helps reduce GPU memory use by loading large language models in 4-bit or 8-bit formats, a technique called quantization. Covers bitsandbytes configuration, memory checks, QLoRA fine-tuning, and training with memory-saving optimizers.
Build Apache Spark pipelines for large datasets, including transformations, aggregations, and streaming analysis. Get PySpark or Scala code, partitioning strategies for dividing data across workers, and configuration advice to investigate slow jobs and resource usage.
Build JavaScript or TypeScript applications that run text, image, and audio models in browsers or server runtimes. Guides compatible model selection, GPU or CPU execution, caching, and memory cleanup without requiring a Python server.
Prepare 3D models for browser games by cleaning source assets, exporting GLB or glTF, and optimizing geometry and textures. It also guides collision shapes, distance-based detail levels, and runtime checks for the chosen engine.
Write JavaScript for n8n Code nodes to aggregate, filter, and transform workflow data. Guidance covers data access, output formats, execution modes, common errors, and performance choices when processing large numbers of records.
Build n8n workflows that download, transform, and send files without losing their contents. Learn how file data differs from JSON, how to preserve attachments, and how to use storage keys or URLs with AI tools and chat messages.