235 skills · sorted by relevance
Design REST and GraphQL APIs by clarifying who will use them and how. Define data structures, errors, authentication, pagination, and versioning, then review examples to make the interface consistent and easier to use.
Design a database layer from business requirements, access patterns, and expected growth. Compare database technologies, define tables and relationships, and plan indexes, caching, scaling, migrations, backups, and recovery with clear reasons and trade-offs.
Investigate database slowdowns and plan measurable improvements to queries, indexes, caching, and scaling. The skill covers SQL and NoSQL systems, with guidance on monitoring, load testing, migrations, and balancing performance against cost.
Create patent line drawings from text or reference images through the PatentFig AI API. Convert existing drawings into scalable vector files for CAD, increase image resolution, and export figures in formats used for patent filing.
Set up model training with torchforge for reinforcement learning, where rewards guide improvement. Covers training configurations, custom reward and loss functions, and distributed execution with Monarch and TorchTitan, keeping algorithm experiments separate from infrastructure concerns.
Build searches with Qdrant that find similar content and filter results by attributes. The skill covers document retrieval for AI answers, vector storage, memory optimization, and distributed deployment for larger collections.
Evaluate language models with over 100 benchmark tests covering knowledge, math, coding, safety, and image understanding. Configure runs on Docker, Slurm computing clusters, or cloud infrastructure, compare models, and export results.
Organize PyTorch training code with LightningModule and Trainer. Follow examples for validation, logging, model saving, and distributed training across multiple GPUs, with callbacks that add monitoring or stop training when progress stalls.
Design and implement systems that collect, transform, validate, and store data for analysis. Covers scheduled and real-time processing, data warehouses, quality checks, monitoring, and cost tuning using tools such as Apache Spark, dbt, and Airflow.
Design systems that collect, transform, and store data. Choose between scheduled and continuous processing, generate workflow configurations, validate data quality, and analyze performance using guidance for tools including Python, SQL, Spark, Airflow, dbt, and Kafka.
Turn system structures, processes, and concepts into dark-themed diagrams. Create architecture diagrams, flowcharts, timelines, and other visual explanations as scalable SVG files, with PNG versions for use as images.
Build image export features for HTML elements with snapDOM. The skill covers SVG, PNG, JPG, and WebP output, preserving styles and fonts, adjusting dimensions, excluding elements, and troubleshooting missing resources.
Create pixel art illustrations as SVG files, a scalable image format, for READMEs, documentation, and slides. Build character portraits, conversations, or group scenes, then refine colors, speech bubbles, arrows, and spacing to fit the requested layout.
Build searches with Qdrant that find similar content and filter results by attributes. The skill covers document retrieval for AI answers, vector storage, memory optimization, and distributed deployment for larger collections.
Organize PyTorch training code with LightningModule and Trainer. This skill guides training, validation, logging, model checkpoint saving, early stopping when progress stalls, and configuration for running the same model across multiple GPUs.
Evaluate language models on knowledge, math, coding, safety, and image understanding benchmarks. The skill guides reproducible runs in containers using local Docker, Slurm clusters, or cloud execution, with shared configurations for model comparison and result export.
Guides reinforcement learning, where models learn from rewards, using torchforge and PyTorch. Covers reward design, custom loss functions, and distributed training so researchers can experiment with algorithms while keeping infrastructure concerns separate.
Design and implement a NestJS backend organized into business modules within one deployable application. The skill defines module boundaries, separates data ownership, builds layered code and event communication, and validates isolation through checks and tests.
Create SVG illustrations, a scalable vector image format, of people working in airy rooms or terraces. Use thin indigo outlines, mostly white shapes, and restrained color accents, with reusable drawing parts and checks for consistent scenes.
Create SVG illustrations, a scalable vector image format, with thick navy outlines, vivid colors, and chunky depth. Combine a cartoon character with overlapping props for product screens and marketing cards, then render, review, and refine the artwork.
Add shafts of sunlight to Three.js or similar 3D scenes. Shape rays with roofs and foliage, align them with the sun, and tune rendering effects so foreground surfaces keep their contrast while processing costs remain measurable.
Design reusable SEO page templates from a niche and data source. Get title patterns, page sections, internal linking rules, structured data for search engines, and requirements that keep each page useful and distinct.
Build queryable collections of genomic variants from VCF and BCF files, formats for recording genetic differences. Covers compressed storage, incremental sample additions, searches by genomic region or sample, and exporting subsets for further analysis.
Build production systems for machine learning models, from deployment to monitoring and retraining. The skill also guides LLM integration and retrieval augmented generation, which uses retrieved information to support answers, with scripts and architecture references.